{"meta":{"query_hash":"b13bc4f485d2","filters":{"topic":"Advanced Text Analysis Techniques"},"cohort_total":552,"direct_labels_cover":2,"predictions_cover":552,"exported":552,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/b13bc4f485d2","api":"https://metacan.xera.ac/api/v1/cohort?topic=Advanced+Text+Analysis+Techniques"},"results":[{"id":"W103177335","doi":"10.7202/1032997ar","title":"Indexation manuelle et indexation assistée par ordinateur : comparaison de la performance de deux index d’une monographie","year":2015,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Indexation","score_opus":0.03547252047443438,"score_gpt":0.35930764876178134,"score_spread":0.32383512828734695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W103177335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32424352,0.0019568647,0.6622203,0.0035766293,0.00023878281,0.0003830664,0.0000071455224,0.00048805465,0.006885641],"genre_scores_gemma":[0.92731684,0.0066248747,0.06232679,0.0017371159,0.000114173614,0.00015640825,0.000104667044,0.00005402124,0.0015651206],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99512213,0.00168763,0.000823038,0.0007347372,0.0009340178,0.00069844077],"domain_scores_gemma":[0.9970576,0.00043232966,0.0008837148,0.0006432593,0.0006186363,0.00036443915],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0037386876,0.00048515736,0.00046212593,0.004081856,0.00029476086,0.004453088,0.0008078675,0.0004001548,0.00018144045],"category_scores_gemma":[0.00023338424,0.00055673457,0.00017042247,0.009164471,0.00037493245,0.021380937,0.00027291029,0.00067925703,0.00006683566],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016230243,0.0007807177,0.76402324,0.00021230735,0.00022420687,0.000042801166,0.01594127,0.019377254,0.0015554046,0.116929814,0.027020974,0.053729717],"study_design_scores_gemma":[0.0022797082,0.0006086728,0.5267068,0.00040722222,0.00015811199,0.00011673143,0.00086157984,0.28000563,0.019602166,0.10783578,0.060259078,0.0011584935],"about_ca_topic_score_codex":0.0028109432,"about_ca_topic_score_gemma":0.0006046497,"teacher_disagreement_score":0.6030733,"about_ca_system_score_codex":0.0007069156,"about_ca_system_score_gemma":0.00067639793,"threshold_uncertainty_score":0.9996884},"labels":[],"label_agreement":null},{"id":"W112330709","doi":"10.1007/978-3-642-14616-9_38","title":"A Survey of Text Extraction Tools for Intelligent Healthcare Decision Support Systems","year":2010,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Decision support system; Field (mathematics); Data science; Newspaper; Domain (mathematical analysis); Process (computing); Intelligent decision support system; Health care; Domain knowledge; Information extraction; Knowledge management; Artificial intelligence","score_opus":0.07491786707459162,"score_gpt":0.33351585440880405,"score_spread":0.2585979873342124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W112330709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034175106,0.0027272739,0.9901963,0.00024716105,0.0012063109,0.001908064,0.0001707056,0.0013610712,0.0018413936],"genre_scores_gemma":[0.8710901,0.0026530793,0.097918816,0.000047248603,0.00017532974,0.00097389775,0.0007803853,0.00016623449,0.026194872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665076,0.000030164341,0.0017244414,0.0008112833,0.00048540373,0.00029796816],"domain_scores_gemma":[0.993015,0.0006826253,0.0018088724,0.0014103177,0.003053852,0.000029358545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018737494,0.00044348254,0.0009748806,0.0015379442,0.00020602084,0.00033190774,0.0009268204,0.0011763185,0.0000021316598],"category_scores_gemma":[0.00096558715,0.00039278905,0.00009627776,0.00073772005,0.00020698326,0.0006903105,0.00037342688,0.0005700882,0.0000055168066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001073623,0.000014580908,0.0003850976,0.00036061788,0.00006543146,0.0000020279376,0.00002445325,0.0000050076874,0.0003089626,0.7845779,0.0007521283,0.21349302],"study_design_scores_gemma":[0.0005543348,0.0012458309,0.0015363692,0.0026192076,0.000091222384,0.00017916206,0.00050131534,0.003487522,0.0074992906,0.22481003,0.7555447,0.0019310004],"about_ca_topic_score_codex":0.0004390031,"about_ca_topic_score_gemma":0.00031024424,"teacher_disagreement_score":0.8922775,"about_ca_system_score_codex":0.00014285094,"about_ca_system_score_gemma":0.00020161716,"threshold_uncertainty_score":0.9998524},"labels":[],"label_agreement":null},{"id":"W115958420","doi":"","title":"Comparing Out-of-Sample Predictive Ability of PLS, Covariance, and Regression Models","year":2014,"lang":"en","type":"article","venue":"QUT ePrints (Queensland University of Technology)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Partial least squares regression; Covariance; Structural equation modeling; Regression; Regression analysis; Computer science; Sample (material); Predictive modelling; Analysis of covariance; Range (aeronautics); Econometrics; Statistics; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.01629929383035682,"score_gpt":0.23156226924726164,"score_spread":0.2152629754169048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W115958420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2924564,0.00002166075,0.7063235,0.0001340592,0.000017290715,0.00009384686,0.0000055146,0.00014281734,0.0008049177],"genre_scores_gemma":[0.7849559,0.0000509576,0.21497081,0.0000027764486,0.0000020457342,2.5056607e-7,0.0000012092031,0.0000029127723,0.000013084461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990348,0.00005054428,0.0002197634,0.0003846426,0.00016144077,0.00014876184],"domain_scores_gemma":[0.998495,0.0001151452,0.00036137566,0.00078038825,0.00020756783,0.000040545176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002791621,0.00012050648,0.00045224058,0.00034248695,0.000073349496,0.0000036848392,0.00082375004,0.00017099481,0.0000037995549],"category_scores_gemma":[0.000116133,0.00012140933,0.00006749577,0.0003704682,0.0005100712,0.00029123746,0.0008337634,0.00017347427,7.3105633e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019793291,0.00038452793,0.44503057,0.00022238503,0.00022717484,0.0000071818276,0.0015536938,0.002080247,0.013414358,0.4792251,0.00015406653,0.057502758],"study_design_scores_gemma":[0.0014466874,0.00037511997,0.08686214,0.00037407668,0.00009361219,0.000003407956,0.0003007444,0.29635945,0.05162416,0.5603742,0.0017929686,0.00039346237],"about_ca_topic_score_codex":0.00016949254,"about_ca_topic_score_gemma":0.00005035661,"teacher_disagreement_score":0.49249956,"about_ca_system_score_codex":0.0000334765,"about_ca_system_score_gemma":0.00002689898,"threshold_uncertainty_score":0.49509287},"labels":[],"label_agreement":null},{"id":"W135208616","doi":"","title":"Bayesian Structural Equation Models for Cumulative Theory Building in Information Systems.","year":2012,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Structural equation modeling; Latent variable; Bayesian probability; Proxy (statistics); Reuse; Item response theory; Context (archaeology); Statistical model; Econometrics; Information theory; Machine learning; Data mining; Artificial intelligence; Mathematics; Statistics; Engineering","score_opus":0.022186923798461936,"score_gpt":0.29285704316334377,"score_spread":0.27067011936488183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W135208616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023727112,0.000084623876,0.9942944,0.00013610344,0.0014654626,0.0010353342,0.000020921103,0.00004410109,0.0005463541],"genre_scores_gemma":[0.9846475,0.0000040609507,0.014931875,0.00008013595,0.000173812,0.00008199487,0.000013867863,0.000005687847,0.000061061364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971534,0.000226496,0.0015562809,0.000053252596,0.0007284863,0.00028208926],"domain_scores_gemma":[0.99314094,0.00061407586,0.004591678,0.00021964117,0.001375682,0.00005801474],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005754593,0.00013752493,0.00031648562,0.0005377293,0.00020588073,0.00044377285,0.0005734239,0.00014132838,2.0068182e-7],"category_scores_gemma":[0.0010733721,0.00010066501,0.0002154054,0.00051295577,0.000008263295,0.023159206,0.00006090525,0.00015805638,0.0000021636959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029864583,0.000008312869,0.0023282655,0.00008700114,0.00007543219,1.002356e-8,0.005813526,0.3015355,0.00002125937,0.6874472,0.0004111773,0.0022425011],"study_design_scores_gemma":[0.00076920487,0.000041874533,0.0009663487,0.000115281095,0.000034895165,0.000009143238,0.0009325986,0.97030264,0.00021061172,0.020573212,0.005898312,0.0001458728],"about_ca_topic_score_codex":0.000014583451,"about_ca_topic_score_gemma":8.9443915e-7,"teacher_disagreement_score":0.9822748,"about_ca_system_score_codex":0.0014020101,"about_ca_system_score_gemma":0.000085287495,"threshold_uncertainty_score":0.9905034},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Extraction (chemistry); Web mining; World Wide Web; Web page","score_opus":0.04399676745781409,"score_gpt":0.3191097352841954,"score_spread":0.2751129678263813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486865875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34069973,0.0003095153,0.65529794,0.0002051333,0.0006513252,0.00025869245,0.0000020545706,0.00076899386,0.0018066555],"genre_scores_gemma":[0.8700726,0.00016175516,0.12819728,0.0003090204,0.0001505136,0.00013164557,0.00001988276,0.00003851875,0.00091879437],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972146,0.00016269131,0.00057077775,0.0011720211,0.00043385878,0.00044603448],"domain_scores_gemma":[0.9970845,0.00010305394,0.0005688661,0.0019056482,0.00017957164,0.00015833703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039654528,0.00044827396,0.0004989083,0.0002955291,0.00015281214,0.00014856293,0.0013968223,0.00035748605,0.00008856856],"category_scores_gemma":[0.00009715125,0.00046547147,0.00028890066,0.0004249987,0.00005958653,0.0005081909,0.0011097143,0.0008305334,0.0002202134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000467456,0.0016941633,0.54810095,0.00059047283,0.0011275305,0.0008819703,0.0023884198,0.004415721,0.14701836,0.0075609675,0.018573564,0.2676011],"study_design_scores_gemma":[0.002603175,0.00067088,0.19546257,0.0020018846,0.0010231229,0.00037271096,0.00032065107,0.23449798,0.33054698,0.093516134,0.12853526,0.010448648],"about_ca_topic_score_codex":0.000035407662,"about_ca_topic_score_gemma":0.00004516877,"teacher_disagreement_score":0.5293729,"about_ca_system_score_codex":0.00027407063,"about_ca_system_score_gemma":0.00015908503,"threshold_uncertainty_score":0.9997797},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.04241724093842392,"score_gpt":0.43682276115090307,"score_spread":0.39440552021247915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494478641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.778415e-7,0.0018390019,0.99362135,0.00024082333,0.00014312394,0.0003229695,0.0028167113,0.0000308449,0.0009846049],"genre_scores_gemma":[0.00029645738,0.0061587896,0.9733283,0.00037030512,0.00006555268,0.000038118236,0.0025453556,0.000018417428,0.017178727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99836963,0.00008388935,0.0006582354,0.0004072265,0.000129778,0.00035124703],"domain_scores_gemma":[0.9969296,0.0016779605,0.0006494544,0.00043728025,0.0001962935,0.000109433604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012662759,0.00018353637,0.0006893912,0.0003163643,0.00026232545,0.000012115845,0.0004561247,0.00017849247,0.000004388939],"category_scores_gemma":[0.00011912828,0.00013239708,0.000094838244,0.0002120888,0.00029679819,0.000020460886,0.00014023877,0.00023228688,0.0000010120124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000978739,0.000011924423,0.000105220046,0.0000478925,0.00038897648,4.0658114e-7,0.00003198848,9.523905e-7,1.5028458e-7,0.80699563,0.0106986575,0.18170844],"study_design_scores_gemma":[0.00010438771,0.0006148924,0.0016438094,0.000022729799,0.00034261378,5.9247634e-7,0.000002506909,0.006178811,0.0000014220857,0.89593124,0.095005624,0.0001513568],"about_ca_topic_score_codex":0.000029511053,"about_ca_topic_score_gemma":0.0007366113,"teacher_disagreement_score":0.18155709,"about_ca_system_score_codex":0.00012003384,"about_ca_system_score_gemma":0.0004358872,"threshold_uncertainty_score":0.53989965},"labels":[],"label_agreement":null},{"id":"W1495605239","doi":"10.18438/b8v03n","title":"The Usefulness of Related Functions in Web of Science and Scopus","year":2011,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Scopus; Web of science; Information retrieval; Relevance (law); Computer science; Wilcoxon signed-rank test; Mathematics; Statistics; Medicine; MEDLINE; Mann–Whitney U test; Meta-analysis; Internal medicine","score_opus":0.02176733728420697,"score_gpt":0.25292333423715113,"score_spread":0.23115599695294417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1495605239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27841604,0.0035696109,0.6274922,0.041459184,0.0004915218,0.0015257663,0.000009843509,0.0006374371,0.04639844],"genre_scores_gemma":[0.9674263,0.0005578719,0.031008964,0.00097207463,0.0000017978218,0.000011743675,5.650238e-7,0.00000170819,0.000019001873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989942,0.00010527446,0.0004135773,0.00011154391,0.00027304172,0.00010241588],"domain_scores_gemma":[0.99800014,0.0010021911,0.0004510211,0.00034150388,0.00016323045,0.00004191313],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013806844,0.00006210883,0.000091499365,0.0003456275,0.00016646719,0.00011093448,0.00044694982,0.000030878968,0.00000845084],"category_scores_gemma":[0.0019609975,0.000046268262,0.000013688981,0.0018652797,0.0005126975,0.20095913,0.00020983291,0.00011810926,0.0000018853428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008588678,0.00003566626,0.0025505389,0.00004451714,0.0000067153196,9.305648e-7,0.0010588217,0.000045739907,0.0005966298,0.9541052,0.00008898177,0.041380346],"study_design_scores_gemma":[0.0014737482,0.0012117707,0.15886642,0.0017494193,0.00010224802,0.000104223276,0.006342177,0.36882964,0.35606045,0.02089457,0.08354264,0.0008227031],"about_ca_topic_score_codex":0.0000076324595,"about_ca_topic_score_gemma":1.5495372e-7,"teacher_disagreement_score":0.9332107,"about_ca_system_score_codex":0.000007132427,"about_ca_system_score_gemma":0.00036177412,"threshold_uncertainty_score":0.81021667},"labels":[],"label_agreement":null},{"id":"W1499244104","doi":"10.1007/978-3-642-24469-8_27","title":"Making Sense in the Margins: A Field Study of Annotation","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University; Dalhousie University","funders":"","keywords":"Annotation; Computer science; Hypertext; Field (mathematics); Style (visual arts); Information retrieval; World Wide Web; Artificial intelligence","score_opus":0.040288491415573,"score_gpt":0.3078085936347314,"score_spread":0.2675201022191584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499244104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014959605,0.00011264774,0.99514896,0.00017254965,0.00019933347,0.00056036393,5.6133007e-7,0.00007251639,0.0022371286],"genre_scores_gemma":[0.8122632,0.000012648447,0.18686949,0.00074533036,0.000058879865,0.000013609582,5.1530117e-7,0.0000116215015,0.000024715388],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99722284,0.00009152185,0.00057129207,0.00093989394,0.0008299495,0.00034447535],"domain_scores_gemma":[0.9972179,0.00063971354,0.00040516185,0.0015326346,0.00017524096,0.000029338447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011655699,0.00032395657,0.00044245532,0.0010404801,0.000103103,0.000152408,0.0028224117,0.00016233888,0.0000068267004],"category_scores_gemma":[0.00011493988,0.0002445968,0.000087270644,0.0010411886,0.00021080433,0.00049962965,0.00081228645,0.0006485172,0.0000038264093],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014975674,0.0002681185,0.000846205,0.00003710798,0.000019849025,0.00033648516,0.026570408,0.007964753,0.00011069002,0.029700378,0.000015790767,0.93411523],"study_design_scores_gemma":[0.0006086143,0.0016822029,0.0035256438,0.00082373264,0.000035591987,0.00010517587,0.000015459418,0.23048835,0.0021218238,0.759128,0.00034122984,0.0011241944],"about_ca_topic_score_codex":0.0000911161,"about_ca_topic_score_gemma":0.00057392515,"teacher_disagreement_score":0.932991,"about_ca_system_score_codex":0.00010415806,"about_ca_system_score_gemma":0.00010531076,"threshold_uncertainty_score":0.99743676},"labels":[],"label_agreement":null},{"id":"W1499800862","doi":"10.1007/3-540-45637-6_4","title":"Extracting Keyphrases from Spoken Audio Documents","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Utterance; Natural language processing; Speech recognition; Artificial intelligence; Robustness (evolution); Transcription (linguistics); Word error rate; Linguistics","score_opus":0.01822006719168502,"score_gpt":0.2707262638742662,"score_spread":0.2525061966825812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499800862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011285841,0.00082651566,0.9886834,0.00036835027,0.00086000125,0.00032534322,0.000007439263,0.00060590624,0.0082102055],"genre_scores_gemma":[0.100125,0.00021903036,0.89649224,0.001150722,0.00063682534,0.000014397319,0.000010694332,0.00006038804,0.0012906803],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944054,0.000045129116,0.000791119,0.0023901684,0.0015007694,0.0008674287],"domain_scores_gemma":[0.9956086,0.00087288686,0.00064233906,0.0024111518,0.00023340655,0.00023161678],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005904764,0.0007741007,0.0008245967,0.0011040453,0.00034090414,0.0008677696,0.005330717,0.00039608293,0.00017085423],"category_scores_gemma":[0.00017747252,0.0007420782,0.00025492575,0.0008440294,0.00055320846,0.0018149707,0.0021584842,0.0011422883,0.0001744206],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030455599,0.000044829983,0.0001983128,0.000012281839,0.000034590008,0.00028137528,0.00045039822,0.0054936456,0.00042075233,0.0059149098,0.000093050694,0.9870528],"study_design_scores_gemma":[0.00037984212,0.00016900824,0.00024030107,0.0008949844,0.000044995995,0.0000690742,2.5273573e-7,0.3592879,0.011071108,0.6151019,0.010773501,0.001967168],"about_ca_topic_score_codex":0.00010703768,"about_ca_topic_score_gemma":0.00007952111,"teacher_disagreement_score":0.98508567,"about_ca_system_score_codex":0.0005621972,"about_ca_system_score_gemma":0.00019750948,"threshold_uncertainty_score":0.999503},"labels":[],"label_agreement":null},{"id":"W1506516332","doi":"10.1007/978-3-540-73351-5_22","title":"Combining Vector Space Model and Multi Word Term Extraction for Semantic Query Expansion","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Ranking (information retrieval); Computer science; Vector space model; Margin (machine learning); Artificial intelligence; Semantic similarity; Term (time); Word (group theory); Natural language processing; Cluster analysis; Similarity (geometry); Space (punctuation); Vector space; Information retrieval; Machine learning; Mathematics","score_opus":0.03547433304624778,"score_gpt":0.3152286062239996,"score_spread":0.2797542731777518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506516332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004530317,0.00041129164,0.9971739,0.00026291423,0.00050615374,0.0006399085,0.0000025597496,0.00037440218,0.00017582024],"genre_scores_gemma":[0.18824191,0.000074424264,0.8108493,0.00037604335,0.00013834097,0.000017699607,0.0000043998134,0.00004080488,0.0002570836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996327,0.000021169013,0.000559453,0.0017195375,0.00069982273,0.00067303487],"domain_scores_gemma":[0.99730575,0.0006564818,0.00043317894,0.0011476331,0.00028095773,0.00017598197],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010022622,0.00057161314,0.0006261806,0.0011710124,0.00035100715,0.00041213483,0.0015321911,0.00039382256,0.0000016977783],"category_scores_gemma":[0.000114051174,0.0005516978,0.00015677094,0.00048062083,0.0004677286,0.0011085859,0.00085512473,0.0007144255,0.0000033761514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001593497,0.00005057953,0.00005783765,0.00008241246,0.000015771702,0.00004033813,0.0007829811,0.04079197,0.005948209,0.015178107,0.00000911232,0.93702674],"study_design_scores_gemma":[0.00027144016,0.00010057373,0.00011155269,0.00041550354,0.000017107208,0.000041592823,2.751278e-7,0.9174881,0.0049888305,0.075883575,0.000092559276,0.00058891607],"about_ca_topic_score_codex":0.000014850021,"about_ca_topic_score_gemma":0.00015557132,"teacher_disagreement_score":0.93643785,"about_ca_system_score_codex":0.00031903898,"about_ca_system_score_gemma":0.00023406114,"threshold_uncertainty_score":0.99969345},"labels":[],"label_agreement":null},{"id":"W1506605920","doi":"10.1007/978-1-4020-5347-4_15","title":"TOWARDS A CHANGE-BASED CHANCE DISCOVERY","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Knowledge base; Computer science; Seekers; Data science; Knowledge extraction; Artificial intelligence; Political science","score_opus":0.035014388041817154,"score_gpt":0.27531860109267586,"score_spread":0.2403042130508587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506605920","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9431754e-7,0.00041560215,0.58454156,0.0010326536,0.00006768792,0.00021830409,0.0000042088705,0.00074912957,0.4129707],"genre_scores_gemma":[0.0014577059,0.00033281,0.24835879,0.005522444,0.0003685045,0.00006329285,0.000026902995,0.00005517176,0.74381435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977849,0.000012201035,0.00035246884,0.0009085448,0.00058366917,0.00035821996],"domain_scores_gemma":[0.9978082,0.000034085435,0.00029114145,0.0016368469,0.00012321064,0.000106476335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014363616,0.00050569547,0.0005832502,0.00041174603,0.000072657116,0.00022606218,0.0017053296,0.0003069772,0.0000954885],"category_scores_gemma":[0.000010526929,0.00044586032,0.00037464267,0.00012699887,0.000069789945,0.001058272,0.0003105578,0.000349266,0.00013733291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020356204,0.000013561917,4.0392612e-7,0.0000093526805,0.000017865983,0.00003552901,0.00001695517,0.0000021948777,0.000018259812,0.6597423,0.0009002616,0.3392413],"study_design_scores_gemma":[0.00019879609,0.00024577885,0.000028143462,0.00032127154,0.000051136936,0.00000825597,6.587575e-7,0.0053964783,0.0036244253,0.47949576,0.5093651,0.0012642106],"about_ca_topic_score_codex":0.000021424545,"about_ca_topic_score_gemma":0.000040707397,"teacher_disagreement_score":0.5084648,"about_ca_system_score_codex":0.00016137233,"about_ca_system_score_gemma":0.000121725345,"threshold_uncertainty_score":0.9997993},"labels":[],"label_agreement":null},{"id":"W1509964004","doi":"10.7202/1032764ar","title":"L’analyse du texte littéraire assistée par ordinateur : essai d’illustration avec Regards et jeux dans l’espace, de Saint-Denys Garneau, traité avec le logiciel SATO","year":2015,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université de Montréal","funders":"","keywords":"Humanities; Art","score_opus":0.0358857120120147,"score_gpt":0.3253563984386073,"score_spread":0.2894706864265926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509964004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036540147,0.004409645,0.9070619,0.03298694,0.00043198236,0.00072970847,0.00005332157,0.0010455624,0.016740803],"genre_scores_gemma":[0.8514247,0.004905069,0.10252546,0.0032049825,0.00050105713,0.00021103428,0.00024315351,0.00012045756,0.036864094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99222195,0.0022776749,0.0014365615,0.0014994728,0.0014710819,0.0010932578],"domain_scores_gemma":[0.9952857,0.0003862471,0.00118476,0.0012841573,0.0012369414,0.000622187],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0044391947,0.0008711872,0.0009110162,0.00330713,0.00045218397,0.007250534,0.0013863854,0.0005211188,0.00029852198],"category_scores_gemma":[0.000618811,0.00091990514,0.0004958448,0.007985429,0.0005441363,0.019747647,0.00046335554,0.00076041016,0.000096066535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001650648,0.0013682061,0.020335855,0.00018949898,0.0004986855,0.00046606513,0.02150948,0.01109511,0.0062526357,0.8215411,0.08122747,0.03535086],"study_design_scores_gemma":[0.0052267523,0.0017241668,0.07802481,0.0007798108,0.001013339,0.0008233306,0.0075698807,0.11807718,0.07640262,0.44490042,0.2616374,0.0038202838],"about_ca_topic_score_codex":0.0065551912,"about_ca_topic_score_gemma":0.01873523,"teacher_disagreement_score":0.81488454,"about_ca_system_score_codex":0.0013859153,"about_ca_system_score_gemma":0.0013547328,"threshold_uncertainty_score":0.99932516},"labels":[],"label_agreement":null},{"id":"W1510117420","doi":"","title":"Extracting semantically-coherent keyphrases from speech","year":2004,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"University of Pennsylvania","keywords":"Computer science; Extractor; Artificial intelligence; Similarity (geometry); Word (group theory); Natural language processing; Speech recognition; Key (lock); Semantic similarity; Pattern recognition (psychology); Linguistics; Image (mathematics)","score_opus":0.015152472103937215,"score_gpt":0.27316790850334316,"score_spread":0.25801543639940594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510117420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093330726,0.000036077163,0.89324,0.001189089,0.00007425268,0.00008966419,0.000001289484,0.0006154084,0.0114235],"genre_scores_gemma":[0.53796726,0.000009577778,0.4617307,0.00016818503,0.000054814165,0.0000064611927,0.0000016640278,0.0000066875164,0.00005467819],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99869215,0.000026798978,0.00023811233,0.00042936308,0.00033525238,0.00027834694],"domain_scores_gemma":[0.99895567,0.00012768178,0.00009442067,0.00066574797,0.000059762842,0.00009671146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012555368,0.00014131897,0.00018764361,0.000077895595,0.00009386947,0.00012434952,0.0007689211,0.00005754297,0.00015573432],"category_scores_gemma":[0.00011099699,0.00012996011,0.00009289178,0.00030142983,0.000039513026,0.0005192086,0.00024774295,0.00017862205,0.00016764246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000590529,0.00029564803,0.0011494877,0.000007910279,0.00006050727,0.00026297633,0.0004070405,0.00016090456,0.4661017,0.16128679,0.00057579845,0.36968535],"study_design_scores_gemma":[0.000234469,0.00003981027,0.0010065079,0.000049790935,0.000015260284,0.000012616469,0.000021016911,0.002584573,0.37087092,0.6231477,0.001760447,0.00025684983],"about_ca_topic_score_codex":0.00006882366,"about_ca_topic_score_gemma":0.000036909503,"teacher_disagreement_score":0.46186095,"about_ca_system_score_codex":0.000081565544,"about_ca_system_score_gemma":0.00004107804,"threshold_uncertainty_score":0.52996194},"labels":[],"label_agreement":null},{"id":"W1510360741","doi":"10.1016/s0166-4115(08)10003-6","title":"Short- vs. Long-Term Memory","year":2008,"lang":"en","type":"book-chapter","venue":"Advances in psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Psychology; Cognitive psychology; Term (time); Long-term memory; Short-term memory; Construct (python library); Cognitive science; Cognition; Working memory; Computer science; Neuroscience","score_opus":0.02490165379644471,"score_gpt":0.3572531390102625,"score_spread":0.3323514852138178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510360741","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003022603,0.028652728,0.36423078,0.0002731734,0.0010001466,0.00032353977,0.0000042532165,0.0005410947,0.60494405],"genre_scores_gemma":[0.02568678,0.41892436,0.26756802,0.008305444,0.0011494518,0.00032090745,0.00013327932,0.00041387833,0.2774979],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99668694,0.000048929844,0.0007860325,0.0015340222,0.00038181985,0.0005622321],"domain_scores_gemma":[0.9970855,0.00013361963,0.00032909727,0.0022391963,0.00009788233,0.000114670846],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017999281,0.0005891697,0.0009158629,0.00077999174,0.00007960448,0.00002512695,0.0025615408,0.0005954219,0.00011740244],"category_scores_gemma":[0.000020972513,0.000616535,0.00026366668,0.00020554516,0.00045589524,0.0009189125,0.00044214167,0.0009395353,0.00024088842],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023233131,0.000063369764,0.0007609242,0.000024817058,0.000043808235,0.0011840785,0.00008146404,0.000024151112,0.000021540849,0.048285898,0.0026013996,0.9468853],"study_design_scores_gemma":[0.0006193146,0.00039734758,0.0031259183,0.00032472875,0.0000412182,0.000835693,0.0000011222642,0.00007652615,0.0002419537,0.28475836,0.70775574,0.0018220531],"about_ca_topic_score_codex":9.111534e-7,"about_ca_topic_score_gemma":0.000080390855,"teacher_disagreement_score":0.9450633,"about_ca_system_score_codex":0.00012367805,"about_ca_system_score_gemma":0.000039795006,"threshold_uncertainty_score":0.9996286},"labels":[],"label_agreement":null},{"id":"W1511980079","doi":"10.1023/a:1021855607270","title":"Categorisation Techniques in Computer-Assisted Reading and Analysis of Texts (CARAT) in the Humanities","year":2003,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Computational linguistics; Set (abstract data type); Process (computing); Reading (process); Natural language processing; Linguistics; Artificial intelligence; Programming language; Philosophy","score_opus":0.026891381403847812,"score_gpt":0.25621449946644526,"score_spread":0.22932311806259745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511980079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1599532,0.0015134453,0.83458894,0.00020175605,0.00007665539,0.0005270656,0.000002554917,0.00017156557,0.0029648268],"genre_scores_gemma":[0.9793939,0.000161316,0.019899447,0.0004437746,0.000019664249,0.000036169113,0.000004987995,0.000006898339,0.000033866847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984226,0.0004440607,0.00043495113,0.00029976532,0.0002039484,0.00019465387],"domain_scores_gemma":[0.99868816,0.00058103766,0.0002071128,0.00044667962,0.00006671535,0.0000102958265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010326516,0.00018496509,0.00046869036,0.0008025924,0.00029397837,0.00048005907,0.00055410276,0.000049828406,0.000001129417],"category_scores_gemma":[0.000018531673,0.0001216295,0.000091463706,0.00084632053,0.00064968946,0.00041019646,0.00017134218,0.00016819168,1.6103711e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079731635,0.00005181447,0.0025561946,0.000024827703,0.00012843091,0.000008596936,0.02260356,0.00013524451,0.000028229999,0.94762236,0.00004300149,0.026789784],"study_design_scores_gemma":[0.0030623395,0.0006224035,0.12985444,0.00046222474,0.0008958615,0.000106725,0.007635079,0.43620616,0.0033223054,0.40904832,0.0072085513,0.0015755974],"about_ca_topic_score_codex":0.00038736087,"about_ca_topic_score_gemma":0.00079666317,"teacher_disagreement_score":0.81944066,"about_ca_system_score_codex":0.00004154248,"about_ca_system_score_gemma":0.000020432646,"threshold_uncertainty_score":0.4959907},"labels":[],"label_agreement":null},{"id":"W1514107135","doi":"","title":"Building Systematic Reviews Using Automatic Text Classification Techniques","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Workflow; Exploit; Classifier (UML); Process (computing); Protocol (science); Data mining; Machine learning; Systematic review; Artificial intelligence; Data science; Information retrieval; MEDLINE; Database","score_opus":0.05575739337578075,"score_gpt":0.36121581644412903,"score_spread":0.3054584230683483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514107135","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003005392,0.00011366151,0.9921245,0.00013228736,0.00008550308,0.0010227486,9.456524e-8,0.0019188026,0.001596986],"genre_scores_gemma":[0.21485415,0.000021233918,0.784715,0.00012738768,0.0000329891,0.00014911992,3.2153136e-7,0.000011697356,0.00008809809],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818295,0.0001568185,0.0007440494,0.00040885666,0.0002710806,0.00023625027],"domain_scores_gemma":[0.99776906,0.00016343001,0.00047237895,0.0014005939,0.00012004902,0.00007450964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013943391,0.00019584692,0.00049678,0.00029180307,0.00014309649,0.0002182544,0.0011656543,0.000100539255,0.000024855604],"category_scores_gemma":[0.00050867203,0.00014700311,0.00014103192,0.0007746372,0.00004406453,0.0010065164,0.00019567047,0.00023051423,0.000056359047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.425311e-7,0.000039842496,0.000047977082,0.0022394715,0.000013547085,0.0000019142312,0.00007212356,0.0000012046834,0.5854517,0.33694732,0.00021264498,0.07497209],"study_design_scores_gemma":[0.00004469435,0.000023733763,0.00007676873,0.0018871302,0.000059519425,0.00006896873,0.000014154801,0.8451571,0.12251354,0.027542725,0.002160497,0.00045119718],"about_ca_topic_score_codex":0.000012911348,"about_ca_topic_score_gemma":0.000010164861,"teacher_disagreement_score":0.8451559,"about_ca_system_score_codex":0.000075192285,"about_ca_system_score_gemma":0.00003175155,"threshold_uncertainty_score":0.5994613},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016401369174372914,"score_gpt":0.3180775501979433,"score_spread":0.3016761810235704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152717974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15291478,0.0000037083362,0.84457487,0.0008809917,0.000051103285,0.00008712077,5.67995e-8,0.00010959032,0.0013777554],"genre_scores_gemma":[0.77932954,0.00000251996,0.22047794,0.00012584616,0.000009233047,0.000011043175,3.2840035e-7,0.0000018230227,0.000041720752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993591,0.000034974168,0.0001539991,0.00013329896,0.00021899506,0.000099657336],"domain_scores_gemma":[0.9993582,0.000110622714,0.00006883599,0.0004094089,0.00004052488,0.000012447842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047323908,0.000050366398,0.000085858366,0.00013287106,0.000026544722,0.000051414692,0.0006453936,0.000026198866,0.000020435653],"category_scores_gemma":[0.00007414127,0.000032816322,0.00002466496,0.0005926313,0.000032904965,0.00028410938,0.000087702174,0.00010168597,0.0000061696483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011208327,0.000106902655,0.0062160473,0.00003583606,0.00001007738,0.000008210855,0.0061408877,0.00001124685,0.098761976,0.7909017,0.0001134441,0.097692534],"study_design_scores_gemma":[0.00038332932,0.00012453868,0.10904467,0.000095548065,0.000028094022,0.000026890286,0.0010688128,0.27195293,0.2857227,0.3306896,0.0004505949,0.00041226269],"about_ca_topic_score_codex":0.00002937163,"about_ca_topic_score_gemma":0.0009158296,"teacher_disagreement_score":0.6264148,"about_ca_system_score_codex":0.000005668612,"about_ca_system_score_gemma":0.0000101496125,"threshold_uncertainty_score":0.13382107},"labels":[],"label_agreement":null},{"id":"W1532575505","doi":"10.1007/3-540-47922-8_22","title":"Text Summarization as Controlled Search","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Automatic summarization; Computer science; Generator (circuit theory); Reliability (semiconductor); Set (abstract data type); Segmentation; Artificial intelligence; Process (computing); Quality (philosophy); Natural language processing; Information retrieval; Power (physics)","score_opus":0.016158621043454276,"score_gpt":0.27138025263504706,"score_spread":0.2552216315915928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532575505","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016100157,0.0004101989,0.9764542,0.00079327216,0.00045785136,0.00070498226,0.0000017379393,0.00048344076,0.020678194],"genre_scores_gemma":[0.14537017,0.00033462892,0.8447387,0.0023757485,0.00054951647,0.00004071703,0.000012222634,0.000084841755,0.0064934636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99486136,0.00007027718,0.0007379689,0.0018841963,0.0016581081,0.0007880867],"domain_scores_gemma":[0.9962695,0.0006598502,0.00036295652,0.0019866496,0.00051039737,0.00021059575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010637123,0.0006305665,0.0009676984,0.0016844615,0.00031746604,0.000745331,0.0043605715,0.0004132658,0.00012200931],"category_scores_gemma":[0.00021748384,0.0005647029,0.00027071626,0.0012560765,0.0006925369,0.0010013813,0.0015608231,0.0009904886,0.00023829953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015418824,0.000050099712,0.00003694225,0.000019892947,0.000032676344,0.00012833838,0.00041827178,0.022567065,0.0003153809,0.117887475,0.000048865008,0.85847956],"study_design_scores_gemma":[0.0007310397,0.00018498342,0.000018165872,0.00019190495,0.00001628133,0.00004507797,6.760131e-8,0.7325559,0.0027586892,0.2609909,0.0017933359,0.0007136698],"about_ca_topic_score_codex":0.000026062533,"about_ca_topic_score_gemma":0.000030957814,"teacher_disagreement_score":0.8577659,"about_ca_system_score_codex":0.0004704659,"about_ca_system_score_gemma":0.00037561628,"threshold_uncertainty_score":0.99968046},"labels":[],"label_agreement":null},{"id":"W1538612309","doi":"10.1007/978-3-540-88808-6_5","title":"Connecting Legacy Code, Business Rules and Documentation","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; USable; Documentation; Legacy system; Source code; Reverse engineering; Legacy code; Software engineering; Code (set theory); Business rule; Semantics of Business Vocabulary and Business Rules; Internal documentation; KPI-driven code analysis; Programming language; Business process; World Wide Web; Static program analysis; Software development; Software; Set (abstract data type); Engineering","score_opus":0.016064652009727676,"score_gpt":0.2751270604093387,"score_spread":0.25906240839961103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538612309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008731004,0.0008161093,0.9953192,0.0004989985,0.00038733077,0.00027145154,0.0000024269636,0.00037234012,0.0014590464],"genre_scores_gemma":[0.13359722,0.0005224824,0.8648602,0.00062649837,0.00022199853,0.000008000816,0.000008530216,0.000035099496,0.00011996586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967886,0.000028178123,0.00049603684,0.0014682688,0.000746964,0.00047195345],"domain_scores_gemma":[0.9977276,0.0004148405,0.00038677518,0.000980272,0.00037159154,0.00011896635],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004515399,0.000473023,0.000523909,0.0009286654,0.00042148354,0.00088540383,0.0018614008,0.00022073861,0.000010190335],"category_scores_gemma":[0.00013126509,0.00045261552,0.00007588584,0.00074381597,0.00052708155,0.0024564522,0.0012545132,0.00051487755,0.000016774422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029243731,0.000014809017,0.00005892508,0.000029230232,0.0000123916625,0.00010577721,0.00083853723,0.008229408,0.00024162003,0.015767088,0.000017211742,0.9746821],"study_design_scores_gemma":[0.0006160781,0.00019148744,0.0009303304,0.00084580085,0.000032966072,0.0007747988,9.93494e-7,0.5496661,0.006200065,0.43219063,0.0064890464,0.002061715],"about_ca_topic_score_codex":0.0000492495,"about_ca_topic_score_gemma":0.000120758064,"teacher_disagreement_score":0.97262037,"about_ca_system_score_codex":0.00023189237,"about_ca_system_score_gemma":0.00022193363,"threshold_uncertainty_score":0.9997926},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.025876714810008236,"score_gpt":0.31183386811917013,"score_spread":0.2859571533091619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544240449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020241254,0.0005558684,0.99419147,0.00052671094,0.0005555977,0.00058641605,0.000005567061,0.0004827605,0.0028931878],"genre_scores_gemma":[0.07828948,0.000106026964,0.91806984,0.0027719282,0.00041115965,0.000016236145,0.000004402255,0.000057567475,0.00027335284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99409443,0.000049854494,0.00083041174,0.002428661,0.0015448396,0.0010518249],"domain_scores_gemma":[0.9961856,0.00030982838,0.00033740682,0.0025235354,0.00023730038,0.00040630312],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080154685,0.0008493769,0.00086590374,0.0018183689,0.00036903808,0.0008799173,0.004735611,0.00032708998,0.000115911804],"category_scores_gemma":[0.00007938177,0.00081050023,0.00026650605,0.0014109885,0.0004896864,0.001350065,0.0016064424,0.00083891023,0.0001261041],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008562523,0.00004396748,0.00001893735,0.000015009824,0.000016331647,0.00022751193,0.00036828403,0.07397829,0.0008479581,0.009247679,0.000028279725,0.91519916],"study_design_scores_gemma":[0.00035684803,0.00044768583,0.0000412519,0.0011348245,0.000046160116,0.0002626024,2.4457376e-7,0.4026644,0.016289279,0.55762875,0.01854985,0.002578116],"about_ca_topic_score_codex":0.000075337746,"about_ca_topic_score_gemma":0.000107774824,"teacher_disagreement_score":0.9126211,"about_ca_system_score_codex":0.00091422646,"about_ca_system_score_gemma":0.0005884468,"threshold_uncertainty_score":0.9994346},"labels":[],"label_agreement":null},{"id":"W1546953651","doi":"10.1007/11581062_61","title":"Automatic Keyword Extraction by Server Log Analysis","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Web page; Information retrieval; Static web page; World Wide Web; Web server; Web navigation; The Internet","score_opus":0.011167238721283796,"score_gpt":0.27492132079478504,"score_spread":0.26375408207350126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546953651","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014312551,0.0006139075,0.9951696,0.000681608,0.0003619662,0.00030606418,0.0000046574637,0.0007360274,0.0019830675],"genre_scores_gemma":[0.14750925,0.00012224755,0.8490627,0.0013564457,0.00030787417,0.000019298783,0.000023534649,0.000047774116,0.0015508843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946909,0.000055985016,0.00086122716,0.002130135,0.0014882628,0.00077352213],"domain_scores_gemma":[0.9959197,0.00041815784,0.00066155905,0.0024918648,0.00029252007,0.00021617819],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009566785,0.00072124635,0.0009866881,0.002411108,0.00027636462,0.0006663454,0.0041801916,0.00045886883,0.00017009577],"category_scores_gemma":[0.000072111434,0.00068518135,0.00045607603,0.0029828486,0.00050812133,0.0016638825,0.0011144945,0.0009844884,0.000090475325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014259092,0.000046336936,0.00009268912,0.000016491802,0.00012648234,0.00003900125,0.00017122919,0.029220557,0.00021460236,0.0045089778,0.00011436141,0.96544784],"study_design_scores_gemma":[0.000120028606,0.000080638,0.0001868048,0.00011074495,0.00016279775,0.000028359465,7.109492e-8,0.91219795,0.0023838452,0.079817064,0.0040269974,0.0008847205],"about_ca_topic_score_codex":0.000037385034,"about_ca_topic_score_gemma":0.00028721127,"teacher_disagreement_score":0.96456313,"about_ca_system_score_codex":0.0007547525,"about_ca_system_score_gemma":0.00025454018,"threshold_uncertainty_score":0.99955994},"labels":[],"label_agreement":null},{"id":"W1578895891","doi":"10.2224/sbp.2009.37.2.145","title":"Public recognition of major works in psychology: Rise and fall over time","year":2009,"lang":"en","type":"article","venue":"Social Behavior and Personality An International Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Psychology; Period (music); History of psychology; Cognition; Psychoanalysis; Social psychology; Social science; Sociology; Psychiatry; Philosophy; Aesthetics","score_opus":0.06413617509517439,"score_gpt":0.3821694435155543,"score_spread":0.31803326842037993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578895891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98479724,0.00011118442,0.012137657,0.0025123104,0.000072037554,0.000054946242,0.00001338656,0.00002752938,0.00027373456],"genre_scores_gemma":[0.99091816,0.00017797075,0.008363383,0.0003672928,0.00014366776,0.0000034601692,0.000008713331,0.0000033966282,0.0000139737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989743,0.00011969891,0.00026448249,0.00020494973,0.00030355205,0.0001330218],"domain_scores_gemma":[0.9994567,0.000021639975,0.00016740877,0.00007168396,0.00020308886,0.0000794794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047872303,0.00009056552,0.00015265241,0.0002192861,0.0001007218,0.0002065745,0.00035144528,0.00009950058,0.00007151116],"category_scores_gemma":[0.000025747862,0.000092539536,0.00006915167,0.00014574477,0.000098549885,0.0013363406,0.00004548064,0.00028150107,0.0000012577412],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046226713,0.00038743592,0.09242787,0.0000013657009,0.000026278252,0.000041441974,0.0014768015,9.2583434e-8,0.0026172397,0.0033397728,0.000084204774,0.8995513],"study_design_scores_gemma":[0.000710741,0.0001341941,0.94886893,0.000024920662,0.000019981919,0.0001210454,0.000043624095,0.0002505652,0.0000730516,0.049460422,0.00014420443,0.00014832242],"about_ca_topic_score_codex":0.000036988877,"about_ca_topic_score_gemma":0.00004245109,"teacher_disagreement_score":0.899403,"about_ca_system_score_codex":0.000050544742,"about_ca_system_score_gemma":0.000028473842,"threshold_uncertainty_score":0.37736526},"labels":[],"label_agreement":null},{"id":"W1593294079","doi":"10.1007/11424918_33","title":"A Document Browsing Tool: Using Lexical Classes to Convey Information","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Digital library; Field (mathematics); Information retrieval; World Wide Web; Linguistics","score_opus":0.019211746900202824,"score_gpt":0.29090359449865594,"score_spread":0.2716918475984531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593294079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017470053,0.00008998226,0.99625933,0.00068694865,0.0005038095,0.0004611709,0.000002177038,0.00037311277,0.0014487819],"genre_scores_gemma":[0.06766686,0.000018586972,0.92810017,0.0037870763,0.0003097984,0.00000868737,0.0000041651656,0.000021667662,0.00008302148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611145,0.00003881127,0.00082064455,0.0010753804,0.0012522818,0.0007014222],"domain_scores_gemma":[0.997401,0.00029624664,0.00038198513,0.001351136,0.00036687191,0.0002027337],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00095058593,0.0005414015,0.0005912004,0.0014903054,0.00027397243,0.0011745434,0.0023778738,0.0002905473,0.000017440616],"category_scores_gemma":[0.00015867464,0.0005192726,0.00015663808,0.0009905975,0.00034394552,0.0034460754,0.0018208714,0.00065665034,0.00007399504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046015493,0.000012172315,0.00002112039,0.00001790035,0.000010586333,0.000016193375,0.00053283235,0.10964973,0.00039917853,0.03326285,0.00002672374,0.8560461],"study_design_scores_gemma":[0.00021009335,0.00017077108,0.000052728854,0.00055185874,0.000018720371,0.00010897592,3.0019413e-7,0.82724667,0.005932338,0.1453058,0.019202696,0.0011990756],"about_ca_topic_score_codex":0.00003475306,"about_ca_topic_score_gemma":0.00006628852,"teacher_disagreement_score":0.854847,"about_ca_system_score_codex":0.0009759003,"about_ca_system_score_gemma":0.0005217614,"threshold_uncertainty_score":0.9998623},"labels":[],"label_agreement":null},{"id":"W1598898694","doi":"","title":"Can Human Assistance Improve a Computational Poet","year":2015,"lang":"en","type":"article","venue":"Proceedings of Bridges 2015: Mathematics, Music, Art, Architecture, Culture","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phrase; Metric (unit); Computer science; Poetry; Set (abstract data type); Artificial intelligence; Natural language processing; Linguistics; Engineering","score_opus":0.022145023727516006,"score_gpt":0.2754080413410924,"score_spread":0.2532630176135764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1598898694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047774043,0.00050627475,0.91183937,0.0031253714,0.0003661516,0.0014221995,0.00011438315,0.001732317,0.03311989],"genre_scores_gemma":[0.32725376,0.000007631235,0.6698217,0.00048900605,0.0002789974,0.00007932445,0.000037350088,0.000062158404,0.0019700879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99657154,0.000017966342,0.0008491653,0.0008415555,0.0011398537,0.00057990046],"domain_scores_gemma":[0.99666476,0.00008413969,0.0009907045,0.0004947823,0.001410378,0.00035521536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063655485,0.00053398655,0.00079944986,0.00033089772,0.00019782237,0.00030260853,0.001750797,0.0001864385,0.000013835036],"category_scores_gemma":[0.00043382045,0.0004522397,0.00026949015,0.0005953799,0.0002997836,0.0007020498,0.0005695564,0.00049847446,0.000027384902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046226705,0.0012142148,0.0006294711,0.0012904919,0.00046067772,0.000019562829,0.045789503,0.0011566328,0.051529586,0.53340054,0.35842776,0.0060353493],"study_design_scores_gemma":[0.0012875787,0.00052449503,0.0004831742,0.0004205662,0.00013944256,0.00015669601,0.0013093443,0.021694101,0.024485825,0.9297721,0.018392026,0.0013346459],"about_ca_topic_score_codex":0.00001586135,"about_ca_topic_score_gemma":0.000033356555,"teacher_disagreement_score":0.39637157,"about_ca_system_score_codex":0.0001581369,"about_ca_system_score_gemma":0.000102420454,"threshold_uncertainty_score":0.99979293},"labels":[],"label_agreement":null},{"id":"W166693255","doi":"10.4018/978-1-60566-172-8.ch009","title":"A Model for Estimating the Savings from Dimensional vs. Keyword Search","year":2009,"lang":"en","type":"book-chapter","venue":"Advances in database research (ADR) book series/Advances in database research series","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Zipf's law; Computer science; Metadata; Keyword search; Process (computing); Information retrieval; Search cost; Search engine; Keyword density; Data mining; Data science; World Wide Web; Economics; Statistics; Mathematics; Microeconomics","score_opus":0.08805243973955451,"score_gpt":0.41779534693456,"score_spread":0.3297429071950055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W166693255","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001690082,0.21973377,0.6466018,0.01455561,0.0011713365,0.018407196,0.023803266,0.0014148196,0.07414317],"genre_scores_gemma":[0.0003652359,0.19074804,0.7422893,0.00052402826,0.00095337466,0.0029048568,0.0067591383,0.00042198156,0.055034008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.971175,0.0026940813,0.0039518853,0.006130604,0.010761181,0.0052872086],"domain_scores_gemma":[0.9702609,0.013050611,0.0010403258,0.010966749,0.003716971,0.0009644102],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"category_scores_codex":[0.027336234,0.0020894099,0.0030230435,0.0043864185,0.0026586463,0.0013932952,0.01340431,0.0007535286,0.00036640212],"category_scores_gemma":[0.009146239,0.0017696135,0.00064146187,0.003180877,0.006147305,0.044846386,0.013750122,0.010033339,0.00017700957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039622104,0.0006779551,0.00008463355,0.0017512761,0.00021684077,0.0021530637,0.0014019788,0.028038558,0.0015302894,0.7382082,0.015578602,0.20639642],"study_design_scores_gemma":[0.0009715652,0.00068263756,0.0000060209654,0.0036789277,0.000023059582,0.000059768572,0.00021670414,0.16291673,0.0016695018,0.26462862,0.5636482,0.0014982308],"about_ca_topic_score_codex":0.00047372113,"about_ca_topic_score_gemma":0.01134853,"teacher_disagreement_score":0.5480696,"about_ca_system_score_codex":0.002437383,"about_ca_system_score_gemma":0.00298479,"threshold_uncertainty_score":0.9996433},"labels":[],"label_agreement":null},{"id":"W1728627389","doi":"","title":"Design and Considerations of a Searching Software","year":2015,"lang":"en","type":"article","venue":"Transactions on machine learning and data mining","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Order (exchange); Computer science; Software; Data science; Business; Finance","score_opus":0.0924846284533971,"score_gpt":0.35050625767348115,"score_spread":0.25802162922008404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1728627389","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024647012,0.00025146612,0.99668354,0.00025836524,0.000013284682,0.00006668335,0.000007803211,0.00020346006,0.000050721414],"genre_scores_gemma":[0.42630166,0.000038178558,0.5735763,0.000025699941,0.000003176798,0.000002808646,0.0000072402368,0.0000051416037,0.00003978537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905896,0.00018401476,0.00016081127,0.00032967137,0.00014938525,0.00011714645],"domain_scores_gemma":[0.9988105,0.0005933449,0.00006715249,0.00039096453,0.0000478682,0.00009015565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000707584,0.000093253846,0.00015066769,0.00017665236,0.00024239256,0.00009312894,0.00020504513,0.000030035602,0.000005845207],"category_scores_gemma":[0.00024685307,0.000088701294,0.000012653219,0.00017807775,0.000060571074,0.0005896082,0.000051655494,0.0002462881,0.0000011231841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003922752,0.000114145965,0.0024038337,0.000040635692,0.00011612477,0.000022628381,0.006688712,0.059398796,0.0009666197,0.0019552144,0.00014484936,0.9281092],"study_design_scores_gemma":[0.00034593817,0.00022739563,0.00006887402,0.000048682905,0.00003199502,0.00006100262,0.00021411973,0.99538636,0.00078547065,0.0021375392,0.0005396976,0.0001529354],"about_ca_topic_score_codex":0.0000566535,"about_ca_topic_score_gemma":0.000013950859,"teacher_disagreement_score":0.93598753,"about_ca_system_score_codex":0.000008582714,"about_ca_system_score_gemma":0.00004756485,"threshold_uncertainty_score":0.36171338},"labels":[],"label_agreement":null},{"id":"W1777978449","doi":"","title":"Topical Segmentation: a Study of Human Performance and a New Measure of Quality.","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metric (unit); Segmentation; Computer science; Measure (data warehouse); Quality (philosophy); Simple (philosophy); Scale (ratio); Agreement; Artificial intelligence; Natural language processing; Machine learning; Data mining; Linguistics; Epistemology","score_opus":0.07960152078766151,"score_gpt":0.3763586674321693,"score_spread":0.29675714664450775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1777978449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76867604,0.000034439334,0.23023894,0.000042896634,0.000008311929,0.00009438675,4.040286e-8,0.000036173587,0.00086875434],"genre_scores_gemma":[0.9386261,0.000002294096,0.06112221,0.000023855786,0.0000144797,0.0000035758453,1.3054988e-7,0.0000015611422,0.00020577817],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99934226,0.000042132335,0.00022303918,0.00010192302,0.00020870387,0.00008196135],"domain_scores_gemma":[0.99952507,0.000022351369,0.00009454193,0.00026266163,0.00004854755,0.000046848472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022763736,0.000051271283,0.00014659314,0.000051840947,0.000026592485,0.000007278524,0.00019399422,0.000017141716,0.000012460098],"category_scores_gemma":[0.00001002017,0.000041523905,0.00001926476,0.00017305602,0.000020036108,0.0004252523,0.000113007205,0.000034492008,5.1543617e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008335828,0.0008069017,0.76626086,0.000049066337,0.00006656453,2.7881103e-7,0.01248837,0.000005189277,0.02571872,0.07616823,0.00019661881,0.118230864],"study_design_scores_gemma":[0.0012577502,0.0013919321,0.8387823,0.000029386572,0.000045588502,0.0000041493686,0.0016279554,0.0007980704,0.15301704,0.0026479515,0.00011422139,0.00028364416],"about_ca_topic_score_codex":0.00009364867,"about_ca_topic_score_gemma":0.000036966132,"teacher_disagreement_score":0.16995007,"about_ca_system_score_codex":0.000008466006,"about_ca_system_score_gemma":0.000009181145,"threshold_uncertainty_score":0.16932957},"labels":[],"label_agreement":null},{"id":"W178949263","doi":"10.1007/978-3-319-12024-9_14","title":"Semantic Facets for Scientific Information Retrieval","year":2014,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Information retrieval; Sentence; Ontology; Semantic search; Semantics (computer science); Filter (signal processing); Natural language processing; World Wide Web; Semantic Web","score_opus":0.03733782229050642,"score_gpt":0.3114533557815188,"score_spread":0.27411553349101236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W178949263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018186567,0.00010134642,0.95982915,0.00078233035,0.00029450766,0.0006631511,0.000014110225,0.00021228346,0.03808493],"genre_scores_gemma":[0.0696274,0.0008449687,0.92466205,0.0015860113,0.00005527193,0.00007784481,0.0003331897,0.000016459591,0.0027967775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977029,0.000025723548,0.0009873537,0.00033166842,0.00064252183,0.00030982945],"domain_scores_gemma":[0.99482375,0.00027387118,0.00066681276,0.0030267283,0.0010954055,0.00011344703],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0023081894,0.00026125586,0.00033342637,0.0021237272,0.0009245599,0.0020112458,0.0045282394,0.0001604167,0.0000033457434],"category_scores_gemma":[0.00017766704,0.00026619373,0.00008808271,0.0008081273,0.0011410431,0.015845485,0.0023513264,0.00034332284,0.00008158564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002008438,0.0000048290417,0.000004898019,0.000036640053,0.00000400875,2.7496215e-8,0.0007585644,0.00014584266,0.0000072498065,0.7892476,0.0005015564,0.20928684],"study_design_scores_gemma":[0.00020467598,0.00004873429,0.000081897604,0.00011898198,0.000007185568,0.0000075598077,0.0000064855135,0.5346768,0.000074728196,0.035560515,0.4289209,0.00029157795],"about_ca_topic_score_codex":0.0000027570316,"about_ca_topic_score_gemma":0.0000057659504,"teacher_disagreement_score":0.753687,"about_ca_system_score_codex":0.00020436292,"about_ca_system_score_gemma":0.0003159217,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W1809680580","doi":"10.1111/j.1365-2575.2010.00368.x","title":"Using decision tree modelling to support Peircian abduction in IS research: a systematic approach for generating and evaluating hypotheses for systematic theory development","year":2011,"lang":"en","type":"article","venue":"Information Systems Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Virginia Commonwealth University","keywords":"Computer science; Data science; Management science; Development (topology); Empirical research; Decision tree; Development theory; Tree (set theory); Knowledge management; Data mining; Epistemology; Mathematics; Engineering","score_opus":0.46641362650993345,"score_gpt":0.4305231638408666,"score_spread":0.03589046266906687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1809680580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017654357,0.00014416345,0.9778088,0.000004583391,0.00012100929,0.0041039363,0.0000015522816,0.000058223948,0.0001033889],"genre_scores_gemma":[0.38953406,0.0000023169243,0.6096919,0.000024334002,0.000041306233,0.00068142184,0.0000013637417,0.000010905773,0.000012398949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956416,0.0005335798,0.0022212595,0.00025231487,0.000917112,0.00043414667],"domain_scores_gemma":[0.996485,0.00072220806,0.0010453427,0.00036062064,0.001242655,0.00014418029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021012936,0.00020755002,0.000594912,0.0014980938,0.0007026994,0.00086849154,0.0005455319,0.00009859205,6.9240616e-7],"category_scores_gemma":[0.0011462519,0.00016618552,0.00009322692,0.0005763021,0.000019108385,0.0033101763,0.00012175005,0.00018910237,0.000003386889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020617031,0.00013924816,0.00014574523,0.18177722,0.00031866392,0.000004586223,0.20959264,0.54945505,0.0012523901,0.02521799,0.0000917242,0.031798556],"study_design_scores_gemma":[0.00032509223,0.0001344158,0.000004341103,0.013971773,0.000026175721,0.00027630883,0.006456154,0.97529924,0.00048974564,0.002821058,0.0000043962136,0.00019132873],"about_ca_topic_score_codex":0.000009867943,"about_ca_topic_score_gemma":0.0000025854745,"teacher_disagreement_score":0.42584413,"about_ca_system_score_codex":0.0005096144,"about_ca_system_score_gemma":0.00022441531,"threshold_uncertainty_score":0.83748835},"labels":[],"label_agreement":null},{"id":"W18253573","doi":"","title":"Linked Opinions: Describing Sentiments on the Structured Web of Data.","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Semantic Web; World Wide Web; Sentiment analysis; Ontology; Data science; Process (computing); Publishing; Information retrieval; Artificial intelligence; Political science; Epistemology","score_opus":0.16491186477849681,"score_gpt":0.32247194816388364,"score_spread":0.15756008338538682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18253573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006656489,0.000022971853,0.98242635,0.00028207985,0.00008610035,0.0001931559,0.000007264882,0.00028639642,0.010039202],"genre_scores_gemma":[0.6468472,0.000007123522,0.35284916,0.00018202359,0.000009363701,0.000003523232,0.0000069074963,0.000003982313,0.00009074423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991002,0.000053129294,0.00020070684,0.0002992884,0.00021280926,0.0001338445],"domain_scores_gemma":[0.9979588,0.00007086455,0.00011121198,0.001779822,0.000050203646,0.000029091598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024134121,0.000089732304,0.000115225965,0.00008202482,0.00006469279,0.000026321692,0.0022366487,0.000031233954,0.00008671165],"category_scores_gemma":[0.000042365496,0.0000545693,0.000038990274,0.00031681743,0.00004528859,0.0005383438,0.0007583071,0.00008921496,0.000017454438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009577446,0.0001528978,0.0022006563,0.0000069178654,0.00014550115,0.0000047381054,0.00070343394,0.00000903863,0.0075694304,0.8870674,0.0061143474,0.096016094],"study_design_scores_gemma":[0.0007915668,0.00033995011,0.010453918,0.00020456947,0.00007853476,0.000011744657,0.00025340248,0.3646213,0.40849507,0.20495903,0.00891256,0.0008783457],"about_ca_topic_score_codex":0.000026868749,"about_ca_topic_score_gemma":0.000012753332,"teacher_disagreement_score":0.68210834,"about_ca_system_score_codex":0.000009603444,"about_ca_system_score_gemma":0.000031191074,"threshold_uncertainty_score":0.4156287},"labels":[],"label_agreement":null},{"id":"W1910591194","doi":"10.1109/fuzzy.1997.619736","title":"Elicitation of membership functions: how far can theory take us?","year":2002,"lang":"en","type":"article","venue":"Proceedings of 6th International Fuzzy Systems Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Management science; Cognitive science; Psychology; Engineering","score_opus":0.03719236577059323,"score_gpt":0.2486746373106849,"score_spread":0.21148227154009167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1910591194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113782376,0.00078484137,0.7353632,0.0039262944,0.0013358907,0.0010078845,0.00007011825,0.0007227526,0.14300665],"genre_scores_gemma":[0.98788154,0.00006894057,0.009282695,0.00004101728,0.00007518134,0.00007103209,0.000005178993,0.000011972099,0.0025624328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811345,0.000023554458,0.0005210735,0.000409164,0.0007358096,0.00019691867],"domain_scores_gemma":[0.9964567,0.00013374387,0.0008167862,0.00019991235,0.0023206305,0.00007222326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005236301,0.00018919437,0.00032040753,0.0004486098,0.000059912127,0.00019462437,0.0012672165,0.00008834534,0.00003852925],"category_scores_gemma":[0.00045559672,0.00018192604,0.00010923977,0.00048422307,0.00011256281,0.0009373859,0.00015181354,0.0001430445,0.000009097426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009952787,0.000072115836,0.004946653,0.00011152758,0.00012023103,6.95393e-7,0.00091174047,0.000045979607,0.018512083,0.9650813,0.00058474566,0.009602991],"study_design_scores_gemma":[0.0024794405,0.0012003582,0.0096336985,0.0028423788,0.00028466614,0.00019757342,0.010403616,0.44893196,0.16680309,0.32770652,0.026949136,0.0025675688],"about_ca_topic_score_codex":0.000067748,"about_ca_topic_score_gemma":0.000009199898,"teacher_disagreement_score":0.8740992,"about_ca_system_score_codex":0.00009563268,"about_ca_system_score_gemma":0.000029812223,"threshold_uncertainty_score":0.74187285},"labels":[],"label_agreement":null},{"id":"W193970460","doi":"10.1007/978-3-642-34752-8_11","title":"Improving Supervised Keyphrase Indexer Classification of Keyphrases with Text Denoising","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Information retrieval; Pattern recognition (psychology)","score_opus":0.018745757084550643,"score_gpt":0.25325356572081503,"score_spread":0.2345078086362644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193970460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013693954,0.00075224775,0.9961672,0.00014881293,0.00020224634,0.000412218,0.000003467739,0.00026599257,0.00067841774],"genre_scores_gemma":[0.5133864,0.000030192195,0.48618552,0.0001628903,0.00013809778,0.00000974813,0.000004915952,0.000035466466,0.000046731275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580014,0.000046468176,0.00073529343,0.0014588811,0.0012459493,0.0007132819],"domain_scores_gemma":[0.9960128,0.00045698596,0.00078184163,0.0020564923,0.00049509335,0.00019676857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008414372,0.0006104237,0.0007396308,0.0013680795,0.00021868432,0.00028995515,0.0030464258,0.00033097356,0.000021331243],"category_scores_gemma":[0.00010738892,0.0005120454,0.00015020902,0.001131269,0.00093908305,0.0016163674,0.0010148559,0.00071843393,0.000012549412],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013256894,0.000060462142,0.0007392203,0.00007374192,0.000020934649,0.000023133895,0.00055859785,0.0041462975,0.00942197,0.014132647,0.000003148178,0.9708066],"study_design_scores_gemma":[0.0010594134,0.00062970794,0.0020914108,0.0017229391,0.0001331025,0.00015636334,0.0000025087488,0.7863518,0.119976394,0.0846947,0.00050129066,0.0026803976],"about_ca_topic_score_codex":0.000053688953,"about_ca_topic_score_gemma":0.00011067152,"teacher_disagreement_score":0.9681262,"about_ca_system_score_codex":0.00037269297,"about_ca_system_score_gemma":0.00050650333,"threshold_uncertainty_score":0.9997331},"labels":[],"label_agreement":null},{"id":"W1966427115","doi":"10.1145/2232817.2232866","title":"Investigating keyphrase indexing with text denoising","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Search engine indexing; Computer science; Benchmark (surveying); Noise reduction; Artificial intelligence; Natural language processing; Noise (video); Energy (signal processing); Pattern recognition (psychology); Information retrieval; Image (mathematics); Mathematics","score_opus":0.01774092605419382,"score_gpt":0.26945065966914467,"score_spread":0.25170973361495086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966427115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055926595,0.000078201934,0.932631,0.00014477629,0.000021184538,0.000060558268,5.254345e-8,0.00066069904,0.0104769245],"genre_scores_gemma":[0.53559774,8.016883e-7,0.46391806,0.00032401533,0.00003370598,0.0000045301736,2.743462e-7,0.0000064104884,0.00011449701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897265,0.000033849985,0.00015988409,0.00022244496,0.000245019,0.00036612898],"domain_scores_gemma":[0.99916357,0.000073708026,0.00009400461,0.0004580383,0.000049888018,0.00016080387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028540555,0.00012409188,0.00012780346,0.00012390604,0.00014319182,0.0001110755,0.00045274838,0.00003526845,0.000012296764],"category_scores_gemma":[0.000057428042,0.00009382829,0.000029935905,0.0006175645,0.000052200558,0.0018589053,0.0002238242,0.00012925666,0.0000268383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016523578,0.00011006229,0.24439132,0.000020401,0.000059377577,0.000010752005,0.0029854197,0.00031919978,0.036835276,0.5977782,0.00055763125,0.11693068],"study_design_scores_gemma":[0.0010826496,0.00029819613,0.034754857,0.00042287784,0.00009766457,0.0003055605,0.00094562006,0.0739328,0.8193192,0.054891285,0.011043244,0.0029060505],"about_ca_topic_score_codex":0.0000324771,"about_ca_topic_score_gemma":0.00001372878,"teacher_disagreement_score":0.78248394,"about_ca_system_score_codex":0.000047754984,"about_ca_system_score_gemma":0.000033566954,"threshold_uncertainty_score":0.38262066},"labels":[],"label_agreement":null},{"id":"W1967235662","doi":"10.1038/nmeth.2490","title":"Plotting symbols","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Ambiguity; Computer science; Computational biology; Artificial intelligence; Biology; Programming language","score_opus":0.009798851858909177,"score_gpt":0.39838186598130454,"score_spread":0.3885830141223954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967235662","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005694547,0.0005918749,0.9879549,0.0009028681,0.00017952189,0.00015396447,1.14677775e-7,0.00081496703,0.008832293],"genre_scores_gemma":[0.05288033,0.0000072997095,0.9453846,0.0010881239,0.00007703961,0.00004052897,5.239006e-7,0.000011258359,0.0005102933],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987067,0.00027454423,0.00018551924,0.0003699979,0.00020615771,0.0002571064],"domain_scores_gemma":[0.9985376,0.00036952063,0.00009379552,0.0007710882,0.00015232584,0.00007567261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008277199,0.00013053481,0.00019854013,0.00014420597,0.00008309715,0.00014222992,0.0010408792,0.00022560725,0.000047396854],"category_scores_gemma":[0.00051669177,0.00010652981,0.00009590651,0.0006910667,0.000024912584,0.0007191873,0.0002979861,0.0006259635,0.00007325825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.3999766e-7,0.000013975967,0.00013251307,0.00000487119,0.00001622963,0.0000024742546,0.000101518344,0.000005422259,0.03700477,0.084266245,0.0022609576,0.8761908],"study_design_scores_gemma":[0.0001464566,0.00004676863,0.002597475,0.000028891915,0.000017817507,0.000021204492,0.0000257683,0.043313656,0.4715263,0.4291361,0.052621335,0.0005182139],"about_ca_topic_score_codex":0.000008966215,"about_ca_topic_score_gemma":5.7363854e-7,"teacher_disagreement_score":0.8756726,"about_ca_system_score_codex":0.000036099693,"about_ca_system_score_gemma":0.00001711537,"threshold_uncertainty_score":0.43441597},"labels":[],"label_agreement":null},{"id":"W1968731131","doi":"10.1145/2505515.2507854","title":"Modeling latent topic interactions using quantum interference for information retrieval","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinterpretation; Probabilistic logic; Computer science; Quantum; Quantum interference; Interference (communication); Information retrieval; Theoretical computer science; Artificial intelligence; Quantum mechanics; Physics; Telecommunications","score_opus":0.05218644465248692,"score_gpt":0.31901374649699377,"score_spread":0.26682730184450687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968731131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047966912,0.000005007235,0.95081145,0.0002549832,0.00012704126,0.00023101283,3.6868065e-7,0.000266106,0.00033714928],"genre_scores_gemma":[0.68746,0.000002361218,0.3123097,0.0001351571,0.000014109816,0.0000150851065,0.0000020544135,0.000002233688,0.000059286995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993128,0.000011259437,0.00027980813,0.00013807545,0.00010162478,0.00015639604],"domain_scores_gemma":[0.99928445,0.000035662964,0.00006533773,0.00028968535,0.00028417326,0.000040701427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089442336,0.000083142164,0.00010087093,0.0001629439,0.00009092389,0.00023259094,0.0003693374,0.000029548984,0.000025730056],"category_scores_gemma":[0.000056570923,0.000071517476,0.0000638638,0.00022106362,0.000008950203,0.004158858,0.00015180645,0.00007915983,0.000043063774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030734966,0.00018015763,0.00047456272,0.000092064874,0.00013182044,8.3760756e-7,0.0037693596,0.14909364,0.039971847,0.5978397,0.00106474,0.20735054],"study_design_scores_gemma":[0.000058188427,0.000024518216,0.000024175095,0.000014160557,0.000004274658,0.000002480372,0.000034958106,0.97279245,0.004854486,0.021960948,0.00013859828,0.00009074002],"about_ca_topic_score_codex":0.00018715282,"about_ca_topic_score_gemma":0.000009836037,"teacher_disagreement_score":0.8236988,"about_ca_system_score_codex":0.00007653573,"about_ca_system_score_gemma":0.000020386902,"threshold_uncertainty_score":0.30150717},"labels":[],"label_agreement":null},{"id":"W1969838600","doi":"10.3166/isi.11.4.81-97","title":"Réduction de l'espace de recherche par les techniques d'élagage","year":2006,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Art","score_opus":0.0592299782641279,"score_gpt":0.317243919151696,"score_spread":0.25801394088756807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969838600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017304651,0.0013706711,0.95294374,0.001160772,0.00024728433,0.00043250545,0.000012112886,0.001569149,0.024959106],"genre_scores_gemma":[0.38418317,0.0005537063,0.6121179,0.00032014298,0.00034122518,0.00013420497,0.000051187122,0.000028941431,0.00226956],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99652874,0.0009394301,0.0009808269,0.00031678623,0.0004020541,0.00083213643],"domain_scores_gemma":[0.997561,0.00026712992,0.00073901325,0.0006953555,0.0005962251,0.00014130054],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036945017,0.000406455,0.00038476707,0.0005395757,0.0006019497,0.00088359957,0.00074459566,0.00083332177,0.000051848914],"category_scores_gemma":[0.0008537575,0.00046515596,0.00021230268,0.0014484241,0.00044723623,0.009348142,0.00021707619,0.0008026625,0.00009114124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024564642,0.000088760404,0.0017309642,0.00044510665,0.00004027876,0.000013903112,0.006420488,0.0011439724,0.00591453,0.12307022,0.007807093,0.8533001],"study_design_scores_gemma":[0.00028157386,0.00025126638,0.0053618797,0.0008864618,0.000114887094,0.00046512822,0.0009393816,0.05477684,0.3238861,0.39963862,0.21235585,0.0010419919],"about_ca_topic_score_codex":0.0023309044,"about_ca_topic_score_gemma":0.00019553567,"teacher_disagreement_score":0.85225815,"about_ca_system_score_codex":0.0036652018,"about_ca_system_score_gemma":0.00045472203,"threshold_uncertainty_score":0.99978},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.006675345525235707,"score_gpt":0.262146813315761,"score_spread":0.2554714677905253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970043789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047847547,0.000207644,0.94790274,0.00041764195,0.000068328016,0.00005906055,4.7755407e-8,0.00034612283,0.0031508796],"genre_scores_gemma":[0.8388192,0.00000131365,0.1603789,0.00009707922,0.00001551372,0.0000018890244,4.3906232e-7,0.0000011486286,0.00068447477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923885,0.000024049255,0.00013088669,0.00029534457,0.00014196812,0.0001688751],"domain_scores_gemma":[0.9994776,0.000015123425,0.00003226987,0.0003941212,0.000054322412,0.00002652169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023683348,0.00006376281,0.000075478725,0.00030104115,0.00008206994,0.00026777128,0.00041126518,0.000040211147,0.0000038601065],"category_scores_gemma":[0.00004548704,0.000055741457,0.00003481483,0.0015572351,0.000013560902,0.00080269546,0.000055193945,0.00011330707,0.000009899591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016609673,0.00007905807,0.003108842,0.0000049954465,0.0000026129862,0.00003044942,0.00096657657,0.0001716749,0.055952154,0.4716208,0.0002304384,0.46783075],"study_design_scores_gemma":[0.00027471952,0.00012575873,0.07230069,0.000120887045,0.0000034209952,0.00002419438,0.00003660046,0.12641953,0.071666785,0.7265724,0.0020029543,0.00045207381],"about_ca_topic_score_codex":0.000004640381,"about_ca_topic_score_gemma":0.000038474835,"teacher_disagreement_score":0.7909717,"about_ca_system_score_codex":0.00008328947,"about_ca_system_score_gemma":0.000015799766,"threshold_uncertainty_score":0.25821245},"labels":[],"label_agreement":null},{"id":"W1970294714","doi":"10.3115/1614049.1614094","title":"Lycos Retriever","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Labrador Retriever; Information retrieval; World Wide Web; Medicine","score_opus":0.0035388341363369272,"score_gpt":0.21494187018193442,"score_spread":0.2114030360455975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970294714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011059444,0.00002367911,0.9202662,0.00035934872,0.000019777526,0.000030232595,6.6770795e-8,0.0006793813,0.07751538],"genre_scores_gemma":[0.58045053,0.0000015447941,0.41258594,0.00023671034,0.00002562076,0.000001429921,5.154983e-7,0.0000026012924,0.0066950666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99946684,0.000008771875,0.00009887194,0.00017551777,0.00013135282,0.00011862282],"domain_scores_gemma":[0.999504,0.000018799836,0.000026410928,0.00039630872,0.000035495785,0.000018927129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006575444,0.000052642183,0.00006398462,0.00005878298,0.000032765474,0.000046931185,0.0004305133,0.000023458393,0.000044571952],"category_scores_gemma":[0.000007811799,0.000043466516,0.00003883953,0.00038650542,0.0000138659625,0.00037459016,0.00010694431,0.00003757373,0.00011119701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.818115e-7,0.00002426599,0.0007530206,6.5779744e-7,0.0000027654646,0.000007864967,0.000008032578,0.000018559105,0.0026592587,0.95498437,0.024820084,0.016720733],"study_design_scores_gemma":[0.00017681695,0.00003985146,0.006550105,0.000004297765,0.000005430534,0.000012585421,0.0000036376862,0.026684256,0.23132153,0.5785748,0.15625745,0.00036926445],"about_ca_topic_score_codex":0.000047458845,"about_ca_topic_score_gemma":0.000013364143,"teacher_disagreement_score":0.57934463,"about_ca_system_score_codex":0.000020303749,"about_ca_system_score_gemma":0.000008240202,"threshold_uncertainty_score":0.17725131},"labels":[],"label_agreement":null},{"id":"W1971022461","doi":"10.1145/1810617.1810648","title":"The impact of resource title on tags in collaborative tagging systems","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Folksonomy; Tag system; Computer science; Resource (disambiguation); World Wide Web; Set (abstract data type); Consistency (knowledge bases); Process (computing); Information retrieval","score_opus":0.005319121494490606,"score_gpt":0.2990915330229232,"score_spread":0.2937724115284326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971022461","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053979307,0.00013919853,0.28268123,0.00044701382,0.00017477745,0.00036401048,0.0000026940031,0.00030849778,0.66190326],"genre_scores_gemma":[0.9941772,0.0000023974305,0.004394182,0.000013719043,0.000009051602,0.0000042264337,1.5871025e-7,0.0000024648075,0.0013965716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996767,0.000021823927,0.00007945219,0.000076737015,0.000077852696,0.00006740445],"domain_scores_gemma":[0.9995108,0.00011951666,0.000045480527,0.00027516394,0.000035993675,0.000012997155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016902146,0.000036028538,0.00006073679,0.00005020691,0.000024141018,0.000030519983,0.00027313066,0.000018807385,0.000012892401],"category_scores_gemma":[0.000046519664,0.000020034184,0.000021937145,0.00031944472,0.000021613887,0.000058373596,0.000040151564,0.000079210775,0.000022623706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004515891,0.00003445888,0.00042419755,0.0000023969558,0.000017467928,0.0000030733493,0.00026025565,0.00087623735,0.010712074,0.9426724,0.031687967,0.013304987],"study_design_scores_gemma":[0.00067967136,0.0006657214,0.006561389,0.00014617399,0.000010645612,0.000012030598,0.0005530906,0.6130253,0.077145144,0.07675947,0.22362074,0.00082057546],"about_ca_topic_score_codex":0.00006107601,"about_ca_topic_score_gemma":0.000031176376,"teacher_disagreement_score":0.94019794,"about_ca_system_score_codex":0.000018817189,"about_ca_system_score_gemma":0.000025465339,"threshold_uncertainty_score":0.08169703},"labels":[],"label_agreement":null},{"id":"W1977474781","doi":"10.1155/2014/920892","title":"Mental Mechanisms for Topics Identification","year":2014,"lang":"en","type":"article","venue":"Computational Intelligence and Neuroscience","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Identification (biology); Quality (philosophy); Statistic; Baseline (sea); Process (computing); Term (time); Focus (optics); Artificial neural network; Artificial intelligence; Cognitive psychology; Psychology; Statistics; Mathematics; Physics","score_opus":0.04112137919388175,"score_gpt":0.3281550001725835,"score_spread":0.2870336209787017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977474781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005473748,0.000017444912,0.9978148,0.0010490149,0.00022245609,0.00015411475,0.0000016991228,0.000117198484,0.0000759464],"genre_scores_gemma":[0.7777791,0.000015466085,0.22107892,0.0009253081,0.000021920536,0.000024005947,0.0000029218345,0.0000034340765,0.00014891222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989694,0.00002641307,0.00020452267,0.00042917742,0.00022187034,0.00014862535],"domain_scores_gemma":[0.9994149,0.00013012491,0.00009068663,0.00019810474,0.000107144115,0.000059044767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025759067,0.000087364264,0.00008633125,0.00009813709,0.00025070677,0.00018207513,0.0005657497,0.000022658924,0.0000013049533],"category_scores_gemma":[0.0001421622,0.000084973806,0.000036724556,0.00030093384,0.000099523335,0.00056334375,0.00013347017,0.000045278,0.000005049438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001165939,0.000020871901,0.000022580753,0.000004463507,7.2976707e-7,2.2504184e-7,0.000090359325,0.012015129,0.005778907,0.8905689,0.00009000897,0.09140663],"study_design_scores_gemma":[0.000016182243,0.000055364657,0.0004121609,0.0000028332695,0.0000013088518,0.0000058737382,0.0000046019854,0.56367564,0.027660856,0.40638277,0.001714405,0.00006799301],"about_ca_topic_score_codex":0.0000012547707,"about_ca_topic_score_gemma":7.560572e-7,"teacher_disagreement_score":0.77723175,"about_ca_system_score_codex":0.00001444665,"about_ca_system_score_gemma":0.000014532382,"threshold_uncertainty_score":0.34651312},"labels":[],"label_agreement":null},{"id":"W1977563360","doi":"10.1145/1088463.1088490","title":"Augmenting conversational dialogue by means of latent semantic googling","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Conversation; Semantics (computer science); Search engine indexing; Closeness; Information retrieval; World Wide Web; Probabilistic latent semantic analysis; Natural language processing; Latent semantic analysis; Semantic computing; Artificial intelligence; Semantic Web; Linguistics","score_opus":0.012057681514900432,"score_gpt":0.24926304285076042,"score_spread":0.23720536133585998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977563360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011615887,0.00005101243,0.9856227,0.00077174534,0.00002477139,0.000059447833,0.0000010726008,0.00020039534,0.0016529565],"genre_scores_gemma":[0.7390271,0.000009479962,0.26044914,0.00016074763,0.000019324643,0.0000028970087,0.000004448084,0.0000034279697,0.0003234379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991413,0.000020819363,0.0002496193,0.00020785167,0.00023188899,0.0001485668],"domain_scores_gemma":[0.9994665,0.00006398499,0.000116371295,0.00024661914,0.00007155346,0.000035015997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020436362,0.00007760084,0.00012964265,0.000077967634,0.000044908455,0.000026175916,0.0003748158,0.000027817052,0.000053066946],"category_scores_gemma":[0.00002327254,0.00007076465,0.00006346943,0.00020735625,0.000029130435,0.0004321221,0.00013124413,0.00005253079,0.000022773951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076237225,0.0005384465,0.026376927,0.00006132853,0.00031006327,0.000007817577,0.0024587212,0.012192701,0.22481172,0.4890867,0.012602023,0.23154594],"study_design_scores_gemma":[0.0002767943,0.00003099133,0.0006296494,0.000022318423,0.000020569392,0.0000029480973,0.000018418197,0.67361593,0.3155417,0.0062454524,0.0033586745,0.00023652466],"about_ca_topic_score_codex":0.000030379373,"about_ca_topic_score_gemma":0.00002406385,"teacher_disagreement_score":0.7274112,"about_ca_system_score_codex":0.000040448198,"about_ca_system_score_gemma":0.00001798694,"threshold_uncertainty_score":0.28856987},"labels":[],"label_agreement":null},{"id":"W1978022428","doi":"10.1109/icdm.2014.120","title":"Mining Contentious Documents Using an Unsupervised Topic Model Based Approach","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Viewpoints; Artificial intelligence; Probabilistic logic; Cluster analysis; Expression (computer science); Domain (mathematical analysis); Natural language processing; Information retrieval; Machine learning; Mathematics","score_opus":0.04839903355945884,"score_gpt":0.30069312434877,"score_spread":0.25229409078931114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978022428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05163695,0.0000067623096,0.94160056,0.00004275056,0.00002415919,0.00010601431,1.535625e-7,0.00046428444,0.006118347],"genre_scores_gemma":[0.5007099,2.506379e-7,0.49869192,0.0003789147,0.000010670814,0.000006208974,0.000002195117,0.000006002144,0.0001939389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872744,0.00007944107,0.0002236088,0.00045665624,0.00025616554,0.00025667803],"domain_scores_gemma":[0.9989296,0.000027033642,0.00007191657,0.0007841353,0.000087196,0.00010007098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027561752,0.00014575708,0.00019799864,0.00014362126,0.000118808784,0.00016040493,0.0007965114,0.000055070705,0.00000888607],"category_scores_gemma":[0.000020751082,0.00013074133,0.00007582046,0.00026299123,0.000027878203,0.0009437298,0.00013921483,0.000068437344,0.0000029157368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013870362,0.001003091,0.0061805025,0.00006175836,0.00009725667,0.000008140372,0.0011131173,0.4838303,0.039750997,0.26390693,0.00023102132,0.203803],"study_design_scores_gemma":[0.0002799297,0.00003350154,0.00004173962,0.000006043085,0.000009716824,0.0000014336505,0.000017270304,0.9903551,0.0036355485,0.0053843693,0.00006311224,0.00017225348],"about_ca_topic_score_codex":0.000042268875,"about_ca_topic_score_gemma":0.00000737659,"teacher_disagreement_score":0.5065248,"about_ca_system_score_codex":0.00004636437,"about_ca_system_score_gemma":0.000029263905,"threshold_uncertainty_score":0.5331477},"labels":[],"label_agreement":null},{"id":"W1978265849","doi":"10.1108/00220410610688750","title":"Aggregation consistency and frequency of Chinese words and characters","year":2006,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Zipf's law; Consistency (knowledge bases); Syllable; Romanization; Vernacular; Distribution (mathematics); Frequency distribution; Set (abstract data type); Mathematics; Computer science; Econometrics; Natural language processing; Data set; Statistics; Linguistics; Artificial intelligence; Speech recognition","score_opus":0.004694726306288027,"score_gpt":0.2702126740971309,"score_spread":0.26551794779084287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978265849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79407704,0.000387229,0.20506339,0.00026321303,0.00003291442,0.000041168518,2.6605588e-7,0.000009367539,0.00012544186],"genre_scores_gemma":[0.91280293,0.00011339748,0.08700774,0.00002658239,0.000028065015,8.085792e-7,9.824826e-7,0.0000023055143,0.000017210266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993049,0.000031764266,0.00035798707,0.00007692782,0.00017547433,0.00005294403],"domain_scores_gemma":[0.99914324,0.00004396682,0.00059330097,0.000077979894,0.000116883835,0.000024637135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001999274,0.000059241986,0.00013508413,0.00017969651,0.00003074992,0.00005458682,0.00009164113,0.000020657424,0.0000028768836],"category_scores_gemma":[0.000027665697,0.000048084923,0.00003222767,0.0001866994,0.00003850261,0.0015629521,0.000021202266,0.000051976873,2.0374405e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002684843,0.00014886707,0.49358463,0.000071165305,0.00009765866,0.000028075827,0.0025158292,0.00006309533,0.25053832,0.06395222,0.00007573554,0.18889754],"study_design_scores_gemma":[0.0009830666,0.00028765338,0.5857285,0.00010870947,0.00005335081,0.00018270565,0.00011031689,0.0012170881,0.027381184,0.38374528,0.000025205987,0.00017691929],"about_ca_topic_score_codex":0.00003124856,"about_ca_topic_score_gemma":0.000012448112,"teacher_disagreement_score":0.31979305,"about_ca_system_score_codex":0.000026071548,"about_ca_system_score_gemma":0.000016917487,"threshold_uncertainty_score":0.19608462},"labels":[],"label_agreement":null},{"id":"W1978406346","doi":"10.3758/bf03192769","title":"Anagram software for cognitive research that enables specification of psycholinguistic variables","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Anagram; Anagrams; Computer science; Task (project management); Software; Cognition; Natural language processing; Artificial intelligence; Programming language; Psychology","score_opus":0.46341037151236264,"score_gpt":0.6295342610735168,"score_spread":0.1661238895611542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978406346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044763708,0.00041181175,0.9913002,0.00006957409,0.000085671505,0.0016075938,0.000024881607,0.00022629916,0.0017975902],"genre_scores_gemma":[0.15379846,0.000041381896,0.8442465,0.0000056672297,0.00013982403,0.0008988001,0.000034522087,0.000032546108,0.00080231635],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99360484,0.0022799922,0.00055362674,0.0009086851,0.0016322499,0.0010206262],"domain_scores_gemma":[0.9851628,0.008107356,0.00018048474,0.0011840253,0.0052194726,0.00014586317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02460257,0.00018947509,0.00038095718,0.0016489251,0.00048975326,0.00022491552,0.0017074965,0.00018684324,0.000020933761],"category_scores_gemma":[0.0068289055,0.00018082578,0.0001453061,0.003752361,0.0006454664,0.00028718635,0.0004902678,0.0006617593,0.0000070577917],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085284046,0.0008725308,0.004839277,0.000109803834,0.000027109792,0.000022381297,0.00028068337,0.000008447486,0.060662087,0.11304372,0.0013664918,0.8186822],"study_design_scores_gemma":[0.00062507595,0.00050488324,0.022315005,0.00016973449,0.00004463153,0.000009022475,0.00044576457,0.0012486696,0.628731,0.3318826,0.01360737,0.00041622767],"about_ca_topic_score_codex":0.0005146527,"about_ca_topic_score_gemma":0.00006442081,"teacher_disagreement_score":0.818266,"about_ca_system_score_codex":0.00020234908,"about_ca_system_score_gemma":0.00021964885,"threshold_uncertainty_score":0.8526809},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01471340560740698,"score_gpt":0.2846390009863392,"score_spread":0.26992559537893224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978683092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.626125,0.0007933382,0.3712466,0.0007279652,0.00008047781,0.00016424713,7.951227e-7,0.00060776493,0.00025383555],"genre_scores_gemma":[0.7922873,0.00002250821,0.20750253,0.000120045705,0.000012921767,0.00002082255,3.1982438e-7,0.0000064022925,0.000027190534],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980142,0.00004446759,0.0003580406,0.00083999947,0.00032910562,0.0004141851],"domain_scores_gemma":[0.998672,0.00006300657,0.00019507614,0.00082702585,0.00017204606,0.000070838374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032182585,0.00018424155,0.00031671012,0.0021208024,0.0003809619,0.00009016663,0.0021925848,0.00011046953,0.000016202608],"category_scores_gemma":[0.00019357819,0.00017353825,0.000049063692,0.002884495,0.0022625679,0.00071955257,0.00091061566,0.00023779557,0.000012790807],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036851875,0.00008400834,0.0021351725,0.000009715753,0.000039001912,0.000013637099,0.019922175,0.00011667165,0.61944324,0.086355485,0.000067578396,0.2718096],"study_design_scores_gemma":[0.00018723775,0.0005522243,0.005057841,0.00006060524,0.0000265681,0.000018754985,0.0011946899,0.032263953,0.13531196,0.8248989,0.000043335996,0.00038393025],"about_ca_topic_score_codex":0.00003924225,"about_ca_topic_score_gemma":0.000012421256,"teacher_disagreement_score":0.7385434,"about_ca_system_score_codex":0.00007610271,"about_ca_system_score_gemma":0.000021675862,"threshold_uncertainty_score":0.83365256},"labels":[],"label_agreement":null},{"id":"W1979229208","doi":"10.5555/2025756.2025769","title":"Multimodal representations, indexing, unexpectedness and proteins","year":2011,"lang":"en","type":"article","venue":"International Conference Industrial, Engineering & Other Applications Applied Intelligent Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Modalities; Computer science; Search engine indexing; Human–computer interaction; Topology (electrical circuits); Artificial intelligence; Computational biology; Biology; Engineering","score_opus":0.07768854023297872,"score_gpt":0.2903790542009867,"score_spread":0.21269051396800798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979229208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012092165,0.00006935482,0.9824765,0.00007278228,0.0002269897,0.0014122039,0.000015374704,0.0006849066,0.0138326865],"genre_scores_gemma":[0.95351696,0.000028218512,0.04268522,0.000026892767,0.00022567171,0.0031790303,0.000019007008,0.000039542043,0.00027944995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979228,0.00003194016,0.00066806265,0.0006900124,0.00040697193,0.00028024212],"domain_scores_gemma":[0.99843943,0.00007678162,0.00030627887,0.00076729804,0.00026976198,0.00014046623],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029231538,0.00029759813,0.00028972572,0.00045330997,0.00010926085,0.0003059998,0.0013103656,0.00019636819,0.00007153707],"category_scores_gemma":[0.00004247036,0.0003078126,0.00006256769,0.000526353,0.00007491474,0.0003798574,0.00024737482,0.00033777807,0.000055180786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008599841,0.0001442372,0.00066499284,0.000013080615,0.00014849694,0.000001807329,0.00075290375,0.0008114665,0.007687234,0.9778133,0.00009897797,0.011854895],"study_design_scores_gemma":[0.0021490487,0.00017454685,0.0010505085,0.0004923756,0.00012966932,0.000115379145,0.0025074612,0.56917804,0.20894596,0.028952673,0.1831923,0.0031120318],"about_ca_topic_score_codex":0.00033706953,"about_ca_topic_score_gemma":0.0000064871833,"teacher_disagreement_score":0.95230776,"about_ca_system_score_codex":0.0001506577,"about_ca_system_score_gemma":0.000075284275,"threshold_uncertainty_score":0.9999374},"labels":[],"label_agreement":null},{"id":"W1986494226","doi":"10.1109/services.2013.62","title":"PALTask Chat: A Personalized Automated Context Aware Web Resources Listing Tool","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; University of Victoria","keywords":"Computer science; World Wide Web; Task (project management); The Internet; Context (archaeology); Listing (finance); Domain (mathematical analysis); User profile; Multimedia; Information retrieval; Human–computer interaction","score_opus":0.01204970316159229,"score_gpt":0.2599368146437869,"score_spread":0.24788711148219458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986494226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13515687,0.0003090242,0.8376588,0.0026959088,0.000090697074,0.0006534989,0.0000036524127,0.01365579,0.009775722],"genre_scores_gemma":[0.8805217,0.000011787875,0.11439075,0.0011858387,0.000044442717,0.00009874389,0.0000035983644,0.00001681436,0.0037263047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823004,0.00009120731,0.0003647965,0.00053407013,0.00036611687,0.00041375062],"domain_scores_gemma":[0.9985998,0.00017175631,0.00017024101,0.00069784216,0.0002481842,0.000112140486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023373294,0.00022380806,0.00031313047,0.00017890293,0.00020898604,0.00040404752,0.0010336847,0.00008599016,0.00047435457],"category_scores_gemma":[0.0001393021,0.00018260733,0.00013497149,0.0006312861,0.000092050424,0.000977738,0.00037502157,0.00014935667,0.00041866678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022291097,0.00039875173,0.0077103754,0.0001327347,0.00039955703,0.0001274988,0.011040013,0.00011016327,0.053659707,0.19236392,0.15097947,0.5830555],"study_design_scores_gemma":[0.00043090386,0.000062108884,0.0011649707,0.000057320554,0.000012848234,0.000017444,0.00041059297,0.95868427,0.0030074327,0.002985411,0.032695137,0.00047156998],"about_ca_topic_score_codex":0.00031257153,"about_ca_topic_score_gemma":0.000051657702,"teacher_disagreement_score":0.9585741,"about_ca_system_score_codex":0.000060882565,"about_ca_system_score_gemma":0.00004555499,"threshold_uncertainty_score":0.7446511},"labels":[],"label_agreement":null},{"id":"W1988834855","doi":"10.1002/meet.1450420170","title":"MARTT: Using induced knowledge base to automatically mark up plant taxonomic descriptions with XML","year":2005,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Markup language; XML; Computer science; RuleML; Domain (mathematical analysis); Knowledge base; XHTML; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Mathematics","score_opus":0.02088201374965352,"score_gpt":0.2770650099305437,"score_spread":0.2561829961808902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988834855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7829086,0.0000056982162,0.21186946,0.0039035077,0.000025285848,0.0005159961,0.0000059150952,0.00029404447,0.00047147635],"genre_scores_gemma":[0.5979272,0.000004422439,0.4015416,0.00045649655,0.000006062389,0.000053692824,1.922253e-7,0.000002710752,0.000007634672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988389,0.0000015872866,0.0003110335,0.00022179159,0.00027563158,0.0003510299],"domain_scores_gemma":[0.99830884,0.000029015775,0.00045495387,0.00022396573,0.0009016332,0.00008161959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072810863,0.00012246809,0.00021031125,0.00042806627,0.00042584972,0.00014858943,0.0012200304,0.00004300634,3.6420013e-7],"category_scores_gemma":[0.00023544324,0.00008729369,0.00007031582,0.004080038,0.0010150161,0.003078069,0.00053831615,0.00011609595,0.000002415434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002992484,0.00008291585,0.0024905314,0.00008970338,0.00007177407,3.0911544e-8,0.005310924,0.000055484616,0.22278453,0.32773402,0.0041804137,0.43716973],"study_design_scores_gemma":[0.0007834823,0.0008772993,0.0023005882,0.00017140356,0.00009126925,0.00009569027,0.009438846,0.6324581,0.30235103,0.006211834,0.044434216,0.00078625896],"about_ca_topic_score_codex":0.0000085069405,"about_ca_topic_score_gemma":0.0000031783172,"teacher_disagreement_score":0.6324026,"about_ca_system_score_codex":0.0002191705,"about_ca_system_score_gemma":0.00023942333,"threshold_uncertainty_score":0.3739869},"labels":[],"label_agreement":null},{"id":"W1989265129","doi":"10.1108/17440081011090220","title":"Topic‐based web site summarization","year":2010,"lang":"en","type":"article","venue":"International Journal of Web Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Automatic summarization; Computer science; Multi-document summarization; Information retrieval; Cluster analysis; Web page; Set (abstract data type); Web modeling; World Wide Web; Artificial intelligence","score_opus":0.006202646875641511,"score_gpt":0.26099236416118304,"score_spread":0.2547897172855415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989265129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027852368,0.00001726739,0.9628506,0.00096376264,0.0036494706,0.00009805126,0.000008973365,0.000103477076,0.0044560838],"genre_scores_gemma":[0.97352594,0.000011490544,0.025666887,0.00033972866,0.0003564776,0.0000047128146,0.000016182912,0.000003832481,0.00007477289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803287,0.000037796955,0.00086961134,0.000071058144,0.0008834262,0.00010521639],"domain_scores_gemma":[0.99672604,0.00007225327,0.0010829046,0.00023999914,0.0018067154,0.00007209402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006305644,0.00010008653,0.00016069983,0.0006900312,0.000045321776,0.00051576504,0.0010794715,0.00007766631,0.000020025207],"category_scores_gemma":[0.00018931561,0.00008652479,0.0001168076,0.00025757763,0.000022228764,0.0047418,0.00007832653,0.00024793905,0.00006771509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013676115,0.0003191156,0.048014496,0.00011403137,0.0006047512,0.000091367445,0.002780234,0.035543412,0.1251068,0.5873153,0.024722828,0.1752509],"study_design_scores_gemma":[0.00092340476,0.000065010085,0.0012033106,0.00008253694,0.000011748325,0.00021995399,0.000050965722,0.5631406,0.005108007,0.00057613925,0.42841354,0.00020481739],"about_ca_topic_score_codex":0.000009963441,"about_ca_topic_score_gemma":0.000009080598,"teacher_disagreement_score":0.9456735,"about_ca_system_score_codex":0.00008702617,"about_ca_system_score_gemma":0.00021693167,"threshold_uncertainty_score":0.4973534},"labels":[],"label_agreement":null},{"id":"W1989573439","doi":"10.1109/icassp.2014.6853571","title":"Improving dialogue classification using a topic space representation and a Gaussian classifier based on the decision rule","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Decision rule; Gaussian; Representation (politics); Space (punctuation); Natural language processing; Machine learning; Pattern recognition (psychology)","score_opus":0.053622232715271494,"score_gpt":0.3238928781536958,"score_spread":0.2702706454384243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989573439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022247648,0.000021153459,0.9727996,0.0025014577,0.00019857645,0.0004972041,0.0000012977499,0.00030067167,0.0014323815],"genre_scores_gemma":[0.65417475,0.000009813576,0.34523967,0.00034750238,0.00006646367,0.00005586524,0.000008718268,0.000014116996,0.00008308211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976028,0.0002723641,0.00039741298,0.0010292095,0.00046230902,0.00023589247],"domain_scores_gemma":[0.9966747,0.0006400652,0.0004719551,0.00200496,0.00012951596,0.00007880024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000708262,0.00028446873,0.0003097663,0.00030348846,0.00024286748,0.0005379073,0.0008978598,0.00025597657,0.00001116327],"category_scores_gemma":[0.00042116336,0.0001980926,0.00013809235,0.0003286051,0.000080556114,0.0002660982,0.0008526471,0.00048219375,0.000007209475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005864048,0.00020815752,0.0044784457,0.0001525646,0.00008287171,0.000017659131,0.00069533114,0.014699687,0.029600507,0.28503406,0.00077427446,0.6641978],"study_design_scores_gemma":[0.000107883694,0.000023671679,0.0037946687,0.000106542284,0.000025302654,0.0000019840977,0.000021808279,0.9397618,0.0034508677,0.052356787,0.00012292064,0.00022572985],"about_ca_topic_score_codex":0.0002825555,"about_ca_topic_score_gemma":0.000057190606,"teacher_disagreement_score":0.9250621,"about_ca_system_score_codex":0.0001793579,"about_ca_system_score_gemma":0.00010759798,"threshold_uncertainty_score":0.80779815},"labels":[],"label_agreement":null},{"id":"W1989994111","doi":"10.1145/1502650.1502696","title":"A multimedia interface for facilitating comparisons of opinions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Interface (matter); Visualization; Set (abstract data type); Information visualization; Multimedia; Baseline (sea); User interface; Human–computer interaction; Information retrieval; World Wide Web; Artificial intelligence","score_opus":0.033660982285267906,"score_gpt":0.3613166909410079,"score_spread":0.32765570865573995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989994111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008960951,0.00003113088,0.99703145,0.0005559005,0.000024473418,0.00016235195,0.0000043937634,0.0002566024,0.0010376115],"genre_scores_gemma":[0.45001948,8.08267e-7,0.54982597,0.000043520246,0.000003913257,0.000006755267,0.0000017647282,0.000001226056,0.000096572505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931765,0.000015210538,0.0002349885,0.00019292247,0.000096474876,0.00014278258],"domain_scores_gemma":[0.99918985,0.00025017097,0.0000843203,0.00033937494,0.0000966888,0.00003959605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012526757,0.00007446335,0.00017338697,0.00008548314,0.00004170518,0.000017409973,0.0005042686,0.000025466969,0.000005088403],"category_scores_gemma":[0.00012573773,0.00006577552,0.00008460618,0.00022638432,0.000026068265,0.0002416008,0.00006630041,0.00004861189,0.0000043396726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013674935,0.00040545137,0.0008186093,0.000028979724,0.00006032613,6.386602e-7,0.003297797,0.0016864699,0.05067737,0.30212575,0.017532472,0.62335247],"study_design_scores_gemma":[0.0003194355,0.00031817696,0.0011436197,0.0000280383,0.000007777446,0.000001272238,0.00017690203,0.8451972,0.12878859,0.018179001,0.0056388387,0.00020114271],"about_ca_topic_score_codex":0.000013167805,"about_ca_topic_score_gemma":0.000016379418,"teacher_disagreement_score":0.84351075,"about_ca_system_score_codex":0.000014641984,"about_ca_system_score_gemma":0.000014863305,"threshold_uncertainty_score":0.26822478},"labels":[],"label_agreement":null},{"id":"W1991664945","doi":"10.3166/ria.24.97-120","title":"Centering Information Retrieval to the User","year":2010,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Terminology; Domain (mathematical analysis); Humanities; Information retrieval; Artificial intelligence; Linguistics; Philosophy; Mathematics","score_opus":0.031751355571021996,"score_gpt":0.293792729742198,"score_spread":0.262041374171176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991664945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008221202,0.00027351355,0.9563635,0.027130822,0.0033572987,0.0004902203,0.000008949412,0.00021849337,0.0039359964],"genre_scores_gemma":[0.8763059,0.00026463272,0.09929989,0.0026360503,0.0007978999,0.000040471747,0.000009856329,0.00003358252,0.020611709],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977129,0.00008229402,0.0007628792,0.00044083744,0.00037337487,0.00062771345],"domain_scores_gemma":[0.99729514,0.00019414083,0.00023640673,0.0016365148,0.00041837728,0.00021943494],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010704002,0.00026744435,0.00024297694,0.00021094552,0.00046596245,0.00071501866,0.0019351458,0.00017326955,0.00046294727],"category_scores_gemma":[0.00067140925,0.00023427272,0.00018785764,0.0017134537,0.00018324668,0.0022851932,0.0007292985,0.0007725893,0.0055728285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026036103,0.0001279535,0.00016455469,0.00007183866,0.000033354194,0.000014927335,0.008778442,0.03428293,0.015156922,0.31416833,0.009272145,0.6179026],"study_design_scores_gemma":[0.000011616796,0.000064816755,0.000051271734,0.000075492346,0.000013192218,0.000042013053,0.00021518553,0.2906883,0.11450791,0.0027046003,0.59140605,0.00021952094],"about_ca_topic_score_codex":0.00011322749,"about_ca_topic_score_gemma":0.00017320269,"teacher_disagreement_score":0.8680847,"about_ca_system_score_codex":0.000082248895,"about_ca_system_score_gemma":0.000075301716,"threshold_uncertainty_score":0.99520147},"labels":[],"label_agreement":null},{"id":"W1992760963","doi":"10.1109/bibm.2013.6732593","title":"Innovative navigation of health discussion forums based on relationship extraction and medical ontologies","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Ontology; Computer science; Unified Medical Language System; Interface (matter); Natural language; Information extraction; World Wide Web; Information retrieval; Open Biomedical Ontologies; Data science; Natural language processing; Upper ontology; Semantic Web; Ontology alignment","score_opus":0.02783934920412459,"score_gpt":0.3511083292126822,"score_spread":0.32326898000855764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992760963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0153218685,0.00001269339,0.96850544,0.015081313,0.000022738957,0.00017271237,1.6951896e-7,0.0001723716,0.0007106878],"genre_scores_gemma":[0.8487467,0.0000037148898,0.15087146,0.00028662925,0.0000040734126,0.000021467875,0.000006070612,0.0000023587759,0.000057501955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989758,0.00010798394,0.00029668125,0.00019482603,0.00031909658,0.00010559723],"domain_scores_gemma":[0.99912727,0.00025323505,0.00021277837,0.00023258716,0.00013314417,0.000040966956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047982155,0.000069945665,0.0001339049,0.00014582966,0.00008946769,0.000024403791,0.00016208977,0.00006290413,0.000017423507],"category_scores_gemma":[0.00032130766,0.000041127045,0.000018352319,0.00052535307,0.000058740825,0.0006824373,0.000053448566,0.00012763403,0.0000044],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004473346,0.000108430584,0.037496258,0.000022667045,0.000005610409,5.9139586e-7,0.00026744686,0.00008395723,0.00040283505,0.2119229,0.00089804945,0.7487868],"study_design_scores_gemma":[0.00034477218,0.0004664441,0.42376253,0.00023476465,0.0000025193533,0.0000042392944,0.00024370346,0.42376828,0.008449366,0.14234214,0.00018564246,0.00019559675],"about_ca_topic_score_codex":0.00012033115,"about_ca_topic_score_gemma":0.000020024987,"teacher_disagreement_score":0.83342487,"about_ca_system_score_codex":0.000050129114,"about_ca_system_score_gemma":0.00006390935,"threshold_uncertainty_score":0.16771121},"labels":[],"label_agreement":null},{"id":"W1996606535","doi":"10.1037/0278-7393.32.6.1244","title":"Linking associative and serial list memory: Pairs versus triples.","year":2006,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"Canadian Institutes of Health Research","keywords":"Dissociation (chemistry); Computer science; Associative property; Content-addressable memory; Isolation (microbiology); Arithmetic; Artificial intelligence; Mathematics; Biology; Pure mathematics; Chemistry; Artificial neural network","score_opus":0.022152592808653507,"score_gpt":0.3259258794838167,"score_spread":0.3037732866751632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996606535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9215675,0.0020771897,0.06729163,0.0004320035,0.0007096116,0.00011537145,8.211665e-7,0.000103634484,0.0077022095],"genre_scores_gemma":[0.9887364,0.00008865274,0.010590514,0.00017010006,0.00031164376,0.0000042539714,0.0000046974897,0.000009396217,0.00008436746],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99877983,0.00025481585,0.0003558431,0.00024527655,0.00019361025,0.0001706046],"domain_scores_gemma":[0.9990471,0.0001455814,0.00055092515,0.00008772649,0.00010782535,0.00006083598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005265393,0.00014051187,0.00026370827,0.0001815935,0.0002286764,0.00008939784,0.0001587769,0.000115243245,0.000017994325],"category_scores_gemma":[0.00006273081,0.00013641543,0.00008081053,0.0001608716,0.00013349131,0.00064417924,0.00007312778,0.00040225455,0.0000019683405],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003065562,0.0012517943,0.0054922993,0.000029926834,0.0005672746,0.0004688301,0.0076239402,0.00022154457,0.81485,0.0040173368,0.0021205798,0.16029096],"study_design_scores_gemma":[0.041199397,0.0145317055,0.033645086,0.00067844114,0.0006112018,0.002238466,0.013011687,0.0051039043,0.83021784,0.05109943,0.0052843885,0.0023784786],"about_ca_topic_score_codex":0.0000047666053,"about_ca_topic_score_gemma":0.0000028474262,"teacher_disagreement_score":0.15791248,"about_ca_system_score_codex":0.000049659287,"about_ca_system_score_gemma":0.000016006503,"threshold_uncertainty_score":0.556286},"labels":[],"label_agreement":null},{"id":"W2001124886","doi":"10.1300/j104v28n04_05","title":"The Essential Elements of Faceted Thesauri","year":2000,"lang":"en","type":"article","venue":"Cataloging & Classification Quarterly","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Information retrieval; Facet (psychology); Construct (python library); Search engine indexing; Selection (genetic algorithm); Homogeneous; Artificial intelligence; Mathematics","score_opus":0.01282327803168236,"score_gpt":0.2720939766783442,"score_spread":0.2592706986466618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001124886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09851279,0.00014808441,0.8963817,0.0015868639,0.00010742112,0.00030318802,0.000006576975,0.0005197824,0.0024336246],"genre_scores_gemma":[0.98664147,0.00003252093,0.012672726,0.00004748173,0.000027390264,0.000045420453,0.000028259308,0.000008295258,0.00049641036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985869,0.00009034034,0.00046807108,0.00033309293,0.00028707366,0.00023455828],"domain_scores_gemma":[0.9983966,0.00011653883,0.00025386276,0.0010769172,0.000110229616,0.000045864148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036255855,0.0001239227,0.00014120799,0.00007830191,0.00024440157,0.00013262955,0.0012120126,0.000048063437,0.000025729414],"category_scores_gemma":[0.000021174175,0.00009314203,0.00008658935,0.00045684355,0.00014183471,0.00045667688,0.00002342123,0.000106068255,0.00009388143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006223958,0.00005877353,0.0002828433,0.0000048881043,0.000030301815,9.970611e-7,0.0009887997,0.000009979224,0.02754638,0.047708165,0.0005516336,0.92281103],"study_design_scores_gemma":[0.0023438756,0.0015475464,0.12632112,0.00018996626,0.00019832348,0.00004694926,0.0030505618,0.34328452,0.14912964,0.17817792,0.19332626,0.0023833227],"about_ca_topic_score_codex":0.000012616546,"about_ca_topic_score_gemma":0.000010585607,"teacher_disagreement_score":0.9204277,"about_ca_system_score_codex":0.00004232047,"about_ca_system_score_gemma":0.00003897834,"threshold_uncertainty_score":0.3798222},"labels":[],"label_agreement":null},{"id":"W2002945463","doi":"10.1145/2682571.2797083","title":"Enhancing Exploration with a Faceted Browser through Summarization","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Automatic summarization; Computer science; Information retrieval; Set (abstract data type); Centroid; Multi-document summarization; World Wide Web; Thesaurus; Natural language processing; Artificial intelligence; Programming language","score_opus":0.04618328961949001,"score_gpt":0.2866778724386565,"score_spread":0.2404945828191665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002945463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015786799,0.000014605492,0.9906736,0.00049082586,0.000025710644,0.00011656535,9.36661e-8,0.00074998016,0.006349927],"genre_scores_gemma":[0.42082617,0.000003769611,0.5783815,0.00021123013,0.000015415091,0.00001899747,0.000005418006,0.0000060317025,0.00053151086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991766,0.000033880744,0.00014271952,0.0002519789,0.0002612045,0.00013359722],"domain_scores_gemma":[0.99926805,0.000016708294,0.00007423201,0.00037413588,0.0002180019,0.00004886944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013154453,0.00009109033,0.00010150453,0.00006228615,0.000047633344,0.000105881314,0.0002742889,0.00003339003,0.0000057574016],"category_scores_gemma":[0.000037242695,0.00006901703,0.000017611559,0.00063678034,0.000016944403,0.0032436354,0.000086178814,0.000050427487,0.00003462259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005349588,0.00026933607,0.0028849486,0.00002397669,0.00011668418,0.00003005695,0.017176675,0.0108243525,0.06566618,0.8424633,0.006995516,0.05349548],"study_design_scores_gemma":[0.0006410285,0.00034842748,0.00011394892,0.0000378577,0.000019030615,0.000009226215,0.0005851599,0.10025098,0.7794313,0.109771274,0.0082727205,0.0005190536],"about_ca_topic_score_codex":0.000047850186,"about_ca_topic_score_gemma":0.00021552463,"teacher_disagreement_score":0.732692,"about_ca_system_score_codex":0.000055963876,"about_ca_system_score_gemma":0.00005229316,"threshold_uncertainty_score":0.28144327},"labels":[],"label_agreement":null},{"id":"W2004269233","doi":"10.5210/fm.v18i5.4529","title":"Navigating an imagined Middle–earth: Finding and analyzing text–based and film–based mental images of Middle–earth through TheOneRing.net online fan community","year":2013,"lang":"en","type":"article","venue":"First Monday","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Point (geometry); Adaptation (eye); Mental image; Dissemination; Social media; World Wide Web; Computer science; Sociology; Psychology; Cognition; Media studies; Mathematics","score_opus":0.054980428905124085,"score_gpt":0.3176600709940333,"score_spread":0.26267964208890926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004269233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78216934,0.00079428963,0.2134752,0.001142946,0.00014094582,0.00090680417,0.00034242132,0.0008946864,0.00013334212],"genre_scores_gemma":[0.63332975,0.00010345981,0.3646922,0.00046461218,0.00009172198,0.000083355895,0.0007917541,0.00011645877,0.00032671026],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99274373,0.0010113067,0.0017586688,0.0017418792,0.0011933817,0.0015510151],"domain_scores_gemma":[0.99232775,0.0012763251,0.0012787405,0.003867038,0.0006085666,0.00064160954],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0016775435,0.0013286044,0.0016668661,0.0005643981,0.0020065228,0.0010094941,0.002721326,0.00039740824,0.00031629694],"category_scores_gemma":[0.00074189005,0.0012972748,0.00044882047,0.001857549,0.0011494282,0.0034514265,0.002035607,0.0020136621,0.000072009105],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004963774,0.0064108777,0.12134756,0.0032112235,0.0015686366,0.000089077424,0.15445304,0.00882854,0.5880804,0.000867213,0.00673103,0.107916035],"study_design_scores_gemma":[0.017985424,0.0030846675,0.1199663,0.011599914,0.0014495607,0.00041527674,0.004151739,0.36052954,0.20046416,0.0150811765,0.24995732,0.01531491],"about_ca_topic_score_codex":0.0036822646,"about_ca_topic_score_gemma":0.0032049874,"teacher_disagreement_score":0.38761622,"about_ca_system_score_codex":0.00018335062,"about_ca_system_score_gemma":0.00016790828,"threshold_uncertainty_score":0.99994653},"labels":[],"label_agreement":null},{"id":"W2005025726","doi":"10.5539/ells.v1n2p129","title":"An Innovative Way of Finding Best or Least Matching Pairs and Groups","year":2011,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Rank (graph theory); Pairing; Mathematics; Group (periodic table); Variable (mathematics); Computer science; Combinatorics; Statistics; Physics; Mathematical analysis","score_opus":0.0213697606517436,"score_gpt":0.29725035190274685,"score_spread":0.2758805912510032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005025726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9705927,0.0115798125,0.016416794,0.00002104638,0.00008754795,0.00010613693,0.000009465003,0.00018129712,0.0010051985],"genre_scores_gemma":[0.9405825,0.00027979698,0.058887195,0.00004793709,0.00008840067,0.000009452974,0.0000038800695,0.000007650161,0.0000931572],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99917936,0.000053375534,0.00020406712,0.00030241083,0.00010647804,0.00015431567],"domain_scores_gemma":[0.9992531,0.000078761834,0.00011513779,0.00025664738,0.00025888864,0.00003745052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023235634,0.00015763423,0.00027422686,0.00016132495,0.0001209713,0.00008342741,0.0002109677,0.000051798113,0.0000032516932],"category_scores_gemma":[0.00016794892,0.000107812724,0.000022458218,0.00062122673,0.00010223435,0.00095877855,0.00022651268,0.00017017892,1.711643e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012422269,0.000049193524,0.0008282645,0.00006407619,0.00009232306,0.000095296025,0.9605604,2.3371223e-7,0.0008817075,0.0176917,0.0000430243,0.019681351],"study_design_scores_gemma":[0.0014160625,0.0019620124,0.007526842,0.0022394017,0.00015025902,0.000099144025,0.9167288,0.00029130786,0.046435546,0.019917842,0.0015756608,0.0016571207],"about_ca_topic_score_codex":0.000012782216,"about_ca_topic_score_gemma":0.000030851446,"teacher_disagreement_score":0.04555384,"about_ca_system_score_codex":0.0000086131095,"about_ca_system_score_gemma":0.0000056393674,"threshold_uncertainty_score":0.43964753},"labels":[],"label_agreement":null},{"id":"W2007176642","doi":"10.1002/meet.14504701334","title":"Newsblog relevance: Applying relevance criteria to news‐related blogs","year":2010,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Relevance (law); Ranking (information retrieval); Quality (philosophy); Psychology; Computer science; Information retrieval; Political science; Epistemology","score_opus":0.007204722471592029,"score_gpt":0.2823218099709089,"score_spread":0.27511708749931685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007176642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8957345,0.000019533287,0.08644125,0.014525006,0.00019502017,0.0011114279,0.0000050992894,0.0007427392,0.0012254316],"genre_scores_gemma":[0.6949583,0.000056763038,0.30347353,0.0013091292,0.0000102903505,0.00016285438,2.8294997e-7,0.000005037523,0.000023770428],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983087,0.0000013479884,0.00044444384,0.00034453475,0.0004637496,0.00043718365],"domain_scores_gemma":[0.9972218,0.00007033735,0.0007464532,0.00038537447,0.0014888082,0.00008718362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096886186,0.0001534009,0.00027365432,0.00039892626,0.0005112977,0.00018272155,0.0022895185,0.000089601635,6.8482353e-7],"category_scores_gemma":[0.0017883613,0.00011992717,0.00011816018,0.006905179,0.0021133446,0.003607157,0.00089632906,0.00030819495,0.0000034442317],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060621796,0.000015279873,0.001603303,0.00003181352,0.000015648602,1.7545474e-8,0.0012481497,0.0000040789378,0.45476657,0.22345403,0.002615017,0.31624004],"study_design_scores_gemma":[0.0007290318,0.00063876127,0.0024636667,0.00009261034,0.00005406534,0.00008274885,0.006754295,0.045191765,0.5095648,0.18661197,0.24688843,0.00092784],"about_ca_topic_score_codex":0.000013677384,"about_ca_topic_score_gemma":0.0000017608231,"teacher_disagreement_score":0.3153122,"about_ca_system_score_codex":0.000063209605,"about_ca_system_score_gemma":0.00011943656,"threshold_uncertainty_score":0.7786706},"labels":[],"label_agreement":null},{"id":"W2010118061","doi":"10.3758/s13420-013-0112-z","title":"An elemental model of retrospective revaluation without within-compound associations","year":2013,"lang":"en","type":"article","venue":"Learning & Behavior","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Psychology; Stimulus (psychology); Striatum; Neuroscience; Chemistry; Developmental psychology; Cognitive psychology","score_opus":0.02592354657919084,"score_gpt":0.3318573211196088,"score_spread":0.305933774540418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010118061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62544435,0.000003880631,0.3739177,0.000026831296,0.00002071723,0.00022290627,0.0000015595618,0.00022668354,0.00013537022],"genre_scores_gemma":[0.77155066,0.0000012200467,0.22805163,0.00001944596,0.00001394156,0.00010153145,0.000017722203,0.000012176084,0.00023164944],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985246,0.00013011103,0.00033901818,0.00035076385,0.0004700887,0.00018542037],"domain_scores_gemma":[0.99871415,0.000022156813,0.00043731745,0.00043841652,0.000328552,0.00005941116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004365997,0.00012580138,0.00021764287,0.00013650743,0.0001825796,0.000106762745,0.00045513772,0.0000578363,0.000035841313],"category_scores_gemma":[0.00006176445,0.00012916666,0.00007248103,0.00031598558,0.000042483156,0.0012551144,0.00008983185,0.0002577798,0.000021834472],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018239169,0.0002395782,0.51333445,0.000002024641,0.00002030709,7.7260825e-7,0.0021676754,0.015793776,0.45722774,0.004936632,0.000028821596,0.006246373],"study_design_scores_gemma":[0.00019284699,0.00015183023,0.312215,0.000012180587,0.00007028819,0.0000016266309,0.00010054877,0.6620015,0.022183187,0.002856019,0.0000028415616,0.0002121585],"about_ca_topic_score_codex":0.00013452554,"about_ca_topic_score_gemma":0.000033302294,"teacher_disagreement_score":0.6462077,"about_ca_system_score_codex":0.00023119093,"about_ca_system_score_gemma":0.0000424999,"threshold_uncertainty_score":0.5267263},"labels":[],"label_agreement":null},{"id":"W2013295704","doi":"10.1016/s0278-2626(02)00506-7","title":"The referencing of internet web sites in medical and scientific publications","year":2002,"lang":"en","type":"article","venue":"Brain and Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Search engine; Information retrieval; Set (abstract data type); Ranking (information retrieval); Computer science; The Internet; Similarity (geometry); Measure (data warehouse); Web search engine; Webometrics; Web search query; Spamdexing; Data mining; World Wide Web; Artificial intelligence","score_opus":0.031863293453405044,"score_gpt":0.2794154786655812,"score_spread":0.24755218521217615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013295704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7886877,0.0018099117,0.18226379,0.018401496,0.000048661503,0.00022623845,0.000003041893,0.00019170571,0.008367438],"genre_scores_gemma":[0.99741304,0.00011574625,0.001980268,0.000103460814,0.0000050537183,0.000010388129,0.00000308584,0.0000012816248,0.00036769055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999499,0.00003778264,0.00011826854,0.00014109483,0.0001362423,0.00006761145],"domain_scores_gemma":[0.9995718,0.0001848739,0.000042124844,0.000117758245,0.000053618747,0.000029836096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036637764,0.000033416003,0.000048707137,0.00011221251,0.00007229473,0.00011920872,0.0001511587,0.000024694249,0.00001808941],"category_scores_gemma":[0.00030964805,0.000024889609,0.000009333743,0.00032928732,0.0001322823,0.00022435674,0.0000919627,0.00005617461,0.0000019283473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020289847,0.00008355743,0.0018893857,0.00001853256,0.000011077945,0.0000031401748,0.0011448988,1.7660591e-7,0.009913619,0.21078126,0.00569382,0.7704585],"study_design_scores_gemma":[0.0008768239,0.0001270337,0.02067702,0.00028428977,0.000016021795,0.00008226248,0.0003541802,0.7450162,0.0095537165,0.20387755,0.018802114,0.0003327402],"about_ca_topic_score_codex":0.0000037644177,"about_ca_topic_score_gemma":0.00021704355,"teacher_disagreement_score":0.77012575,"about_ca_system_score_codex":0.000005147635,"about_ca_system_score_gemma":0.000009818349,"threshold_uncertainty_score":0.11495324},"labels":[],"label_agreement":null},{"id":"W2015225850","doi":"10.1108/00220411311295315","title":"Nodes and arcs: concept map, semiotics, and knowledge organization","year":2013,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Semiotics; Terminology; Meaning (existential); Knowledge organization; Domain (mathematical analysis); Perspective (graphical); Computer science; Knowledge management; Epistemology; Sociology; Linguistics; Data science; Artificial intelligence; Mathematics","score_opus":0.0049372449305333365,"score_gpt":0.2683386110452432,"score_spread":0.2634013661147099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015225850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15689738,0.00059314695,0.8413934,0.000874431,0.00006522681,0.0000769853,1.5215801e-7,0.00002816159,0.00007112004],"genre_scores_gemma":[0.87828034,0.00019061861,0.12130265,0.00008509101,0.000044718276,6.780864e-7,0.0000010004992,0.000004493737,0.00009040069],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944896,0.00004129045,0.00023953995,0.00008914868,0.00011485913,0.00006619936],"domain_scores_gemma":[0.9992379,0.000054134307,0.00025355394,0.000077277786,0.00032431044,0.000052799707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013012823,0.000060596518,0.00010812352,0.00011754119,0.00005113161,0.0002152506,0.0001240844,0.000024612298,0.000027738219],"category_scores_gemma":[0.00005227593,0.000051324325,0.000014369821,0.00017326762,0.000034330467,0.0021058517,0.00006204796,0.00006258244,0.0000067421197],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010383669,0.000262754,0.09736857,0.00012561948,0.00025596598,0.000017193985,0.021586828,0.00030945035,0.12369576,0.069153845,0.017798891,0.66941476],"study_design_scores_gemma":[0.0043473244,0.0011731246,0.23645137,0.00046595358,0.00028499583,0.0006113698,0.003267264,0.04612682,0.3853924,0.31691766,0.0038224093,0.0011393102],"about_ca_topic_score_codex":0.0000076059428,"about_ca_topic_score_gemma":0.000001437328,"teacher_disagreement_score":0.721383,"about_ca_system_score_codex":0.000038074064,"about_ca_system_score_gemma":0.000020235908,"threshold_uncertainty_score":0.20929451},"labels":[],"label_agreement":null},{"id":"W2017155419","doi":"10.1016/j.procs.2011.09.050","title":"Quantum Theory-Inspired Search","year":2011,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Engineering and Physical Sciences Research Council; European Commission","keywords":"Computer science; Quantum; Theoretical computer science; Quantum mechanics; Physics","score_opus":0.035995282752279215,"score_gpt":0.28006056234070886,"score_spread":0.24406527958842966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017155419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012666522,0.000059065016,0.9829612,0.000118786986,0.00033256822,0.00020516105,3.9377858e-7,0.0010938229,0.0025624973],"genre_scores_gemma":[0.5464943,0.0000075488747,0.45308462,0.00030019594,0.000057083576,0.000016745103,2.0748378e-7,0.000007744754,0.000031570795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968649,0.00006765932,0.00031866637,0.0010933856,0.00088567066,0.0007696925],"domain_scores_gemma":[0.997771,0.00008680651,0.00011326406,0.0012792265,0.00045962402,0.00029006522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017832007,0.00023108991,0.00023396971,0.0005412095,0.00040489543,0.0003108816,0.0051779696,0.00005346705,0.000019332423],"category_scores_gemma":[0.00008330181,0.00019984602,0.00008920392,0.0029777645,0.0007134526,0.002604512,0.0016870393,0.00022071219,0.0001656461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005893922,0.00011949175,0.001210327,0.000011997636,0.000009225364,0.000024757946,0.0036889527,0.000023351378,0.0024349038,0.80389047,0.00012527304,0.18845537],"study_design_scores_gemma":[0.00022898367,0.00032628677,0.00863046,0.00003711252,0.000008979979,0.000073007475,0.000024211313,0.58254474,0.11793148,0.28908142,0.0004481928,0.00066511263],"about_ca_topic_score_codex":0.000015121589,"about_ca_topic_score_gemma":0.0000017314371,"teacher_disagreement_score":0.5825214,"about_ca_system_score_codex":0.00008747352,"about_ca_system_score_gemma":0.00034474224,"threshold_uncertainty_score":0.9622042},"labels":[],"label_agreement":null},{"id":"W2018222148","doi":"10.1145/1860559.1860615","title":"Structure-aware topic clustering in social media","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Conversation; Meaning (existential); Social media; Variety (cybernetics); Set (abstract data type); Cluster analysis; Software; Data science; World Wide Web; Scale (ratio); Artificial intelligence; Sociology; Communication; Psychology","score_opus":0.011197016894605682,"score_gpt":0.27793588576744316,"score_spread":0.2667388688728375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018222148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09706293,0.00000329882,0.8993022,0.00048090942,0.00022951206,0.00005172607,5.153556e-7,0.00033523163,0.0025336682],"genre_scores_gemma":[0.86115766,6.536901e-7,0.13853805,0.0001222452,0.0001073351,0.0000029911898,8.889387e-7,0.000003575198,0.00006661679],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993488,0.0000129763885,0.00013314644,0.00020905872,0.0001336405,0.00016235851],"domain_scores_gemma":[0.99960494,0.000042745436,0.000032528376,0.00026435198,0.000025613113,0.00002981483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068830595,0.00007510309,0.00011131142,0.000115019706,0.000049256872,0.000051857256,0.00058465195,0.00006854413,0.00008992341],"category_scores_gemma":[0.000030420351,0.000066006556,0.000032421864,0.00028308528,0.000023048367,0.00032118623,0.00024561156,0.00021427091,0.000005986108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028377328,0.000045999215,0.007842816,0.00001435996,0.0000135165365,0.000042601005,0.0035395545,0.00004533237,0.06990242,0.35487074,0.0009545698,0.56272525],"study_design_scores_gemma":[0.0009713568,0.000040319297,0.113337025,0.000018030905,0.000011608975,0.000033006363,0.00018759219,0.17137907,0.14203548,0.5618187,0.008912696,0.0012551111],"about_ca_topic_score_codex":0.000016820499,"about_ca_topic_score_gemma":0.0039912052,"teacher_disagreement_score":0.7640947,"about_ca_system_score_codex":0.00001837476,"about_ca_system_score_gemma":0.00001521351,"threshold_uncertainty_score":0.26916692},"labels":[],"label_agreement":null},{"id":"W2020664340","doi":"10.1353/lib.2012.0022","title":"Capitalizing on Information Organization and Information Visualization for a New-Generation Catalogue","year":2012,"lang":"en","type":"article","venue":"Library trends","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre for Interdisciplinary Research in Music Media and Technology; McGill University; University of Wisconsin-Milwaukee","keywords":"Computer science; Subject (documents); World Wide Web; Information retrieval; USable; Subject access; Digital library; Library catalog; Leverage (statistics); Controlled vocabulary; Vocabulary; Artificial intelligence","score_opus":0.012152060795173256,"score_gpt":0.24596519278730852,"score_spread":0.23381313199213527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020664340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005391162,0.000035213674,0.9922482,0.00044426386,0.00014265924,0.00011859202,0.000013103765,0.00052232126,0.0010845183],"genre_scores_gemma":[0.9045224,0.000043359356,0.08757558,0.0013567712,0.0002542659,0.000029701476,0.0059850966,0.000013775984,0.0002190451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993123,0.000021938169,0.00026477932,0.00009740151,0.00014299064,0.00016063808],"domain_scores_gemma":[0.9994598,0.000027605776,0.00017446783,0.00020483814,0.000047513462,0.00008578618],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00007755943,0.00011526053,0.00009345551,0.00047832297,0.00013433893,0.00034186666,0.00016156632,0.00007245924,0.000013085213],"category_scores_gemma":[0.000054179684,0.000112871174,0.000023412935,0.0008530024,0.000009263376,0.04407611,0.00007627658,0.00003802039,0.000015670219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005760677,0.00002687869,0.0019777657,0.000017776087,0.0000122089805,4.44603e-8,0.0033391877,0.0002736797,0.0002967062,0.75868165,0.01599012,0.2193782],"study_design_scores_gemma":[0.0018260858,0.00053986115,0.02128258,0.000052029965,0.00006834675,0.000027358172,0.0001653358,0.41033125,0.15274659,0.007721316,0.4040267,0.001212578],"about_ca_topic_score_codex":0.0000045504394,"about_ca_topic_score_gemma":7.263233e-7,"teacher_disagreement_score":0.90467256,"about_ca_system_score_codex":0.00002548089,"about_ca_system_score_gemma":0.000025848904,"threshold_uncertainty_score":0.9692939},"labels":[],"label_agreement":null},{"id":"W2021285674","doi":"10.1109/icalt.2013.158","title":"Knowledge Representation for Context and Sentiment Analysis","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Alberta Innovates - Technology Futures","keywords":"Computer science; Representation (politics); Context (archaeology); Knowledge acquisition; Knowledge representation and reasoning; Artificial intelligence; Knowledge extraction; Information extraction; Natural language; Sentiment analysis; Natural language processing; Mechanism (biology); Human–computer interaction","score_opus":0.02252660654375636,"score_gpt":0.3323195221343422,"score_spread":0.3097929155905858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021285674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008217946,0.00009724043,0.9884484,0.00053037645,0.000015145252,0.00027747688,3.029589e-7,0.0001872728,0.0022258745],"genre_scores_gemma":[0.7696835,0.0000071467825,0.22728147,0.000119623226,0.000009651744,0.000118949,0.0000025604693,0.0000027088856,0.0027744079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993421,0.000021457236,0.00015444675,0.00029375413,0.0000730392,0.000115209376],"domain_scores_gemma":[0.99929357,0.00010067302,0.000055242013,0.00035250472,0.00014766725,0.000050372288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009661963,0.00006945181,0.00015051173,0.00020231643,0.000059623962,0.00012717156,0.00020248366,0.00002279865,0.000051005136],"category_scores_gemma":[0.000020554944,0.000057837704,0.00009499947,0.00061416003,0.000021189107,0.00055157446,0.00012021098,0.000021297463,0.000029419289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024919964,0.00012659791,0.013273333,0.000012226109,0.00080569263,5.786287e-7,0.0010104062,0.00005597347,0.005724051,0.24673535,0.013204959,0.7190483],"study_design_scores_gemma":[0.00038152793,0.000073069685,0.013539332,0.0000041853896,0.00028024142,0.0000014230061,0.00020594208,0.855819,0.06278544,0.06096954,0.005636758,0.000303536],"about_ca_topic_score_codex":0.000089438785,"about_ca_topic_score_gemma":0.00006615983,"teacher_disagreement_score":0.855763,"about_ca_system_score_codex":0.000018695686,"about_ca_system_score_gemma":0.000005929109,"threshold_uncertainty_score":0.23585531},"labels":[],"label_agreement":null},{"id":"W2023370053","doi":"10.1109/ds-rt.2010.28","title":"Location Aware Question Answering Based Product Searching in Mobile Handheld Devices","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Ask price; Conversation; Mobile device; Markup language; Question answering; Global Positioning System; Information retrieval; Product (mathematics); World Wide Web; Human–computer interaction; Word (group theory); Telecommunications; XML","score_opus":0.009268044008883362,"score_gpt":0.30447045181436044,"score_spread":0.2952024078054771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023370053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1052531,0.00004184348,0.8934103,0.0002655231,0.00005647168,0.00020192606,8.611109e-8,0.00042225997,0.00034847652],"genre_scores_gemma":[0.7796641,0.0000029217754,0.22012323,0.00006359907,0.0000279596,0.00005546317,0.00000210168,0.0000051930656,0.00005541391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905837,0.00004956435,0.00017090894,0.00035863125,0.00018634685,0.00017617016],"domain_scores_gemma":[0.9992329,0.00006867417,0.000054806304,0.0004934292,0.000109812965,0.000040367584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005497876,0.00009070957,0.00009981917,0.00032482352,0.000081657265,0.00011619959,0.00044717046,0.000035558598,0.00001091148],"category_scores_gemma":[0.00009067364,0.00008272216,0.000023453787,0.0008668758,0.000022562519,0.0009451305,0.0000910522,0.0002201275,0.000011565092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009044695,0.00027920125,0.07540415,0.00019761089,0.000011541949,0.00001579086,0.0008306618,0.02260045,0.18553644,0.034581155,0.00006845883,0.6804655],"study_design_scores_gemma":[0.00014321449,0.0000506728,0.013352168,0.00010215184,0.0000030806923,0.0000033052502,0.000029704817,0.6624678,0.3201096,0.002151703,0.0013261038,0.00026051907],"about_ca_topic_score_codex":0.00019702398,"about_ca_topic_score_gemma":0.0034832351,"teacher_disagreement_score":0.680205,"about_ca_system_score_codex":0.000035208974,"about_ca_system_score_gemma":0.000058653237,"threshold_uncertainty_score":0.33733118},"labels":[],"label_agreement":null},{"id":"W2023684799","doi":"10.3758/bf03196096","title":"Estimating the frequency of events from unnatural categories","year":2003,"lang":"en","type":"article","venue":"Memory & Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Spinach; Property (philosophy); Event (particle physics); Cognitive psychology; Social psychology; Natural language processing; Computer science; Chemistry; Astrophysics; Epistemology","score_opus":0.01693046206502992,"score_gpt":0.272789210497638,"score_spread":0.2558587484326081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023684799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19350813,0.00015901898,0.8035201,0.00011957622,0.0001782153,0.00011769625,0.0000032964585,0.00014414084,0.002249864],"genre_scores_gemma":[0.7961266,0.0000024667395,0.20369501,0.000090330344,0.00002681004,0.000014890492,0.000011125825,0.0000046717587,0.000028112947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991128,0.00011579161,0.00021277493,0.00020668049,0.00022315819,0.00012882915],"domain_scores_gemma":[0.9991929,0.0001133435,0.00016788696,0.0003592062,0.00014416937,0.000022525528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021691012,0.00009548386,0.00012265822,0.000053440646,0.00012101629,0.00002678146,0.00036181865,0.000037242487,0.000029391185],"category_scores_gemma":[0.00019970702,0.000071239614,0.000060455768,0.00031657136,0.000054469954,0.0004776594,0.000048422793,0.0001166057,0.000015739617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020557483,0.00057497685,0.009344725,0.00011115728,0.0004825349,0.000056690762,0.009864318,0.0015025884,0.3341091,0.19105904,0.00096758595,0.45190674],"study_design_scores_gemma":[0.00017718994,0.00002861858,0.0036340302,0.000045499008,0.000047214944,0.0000062966255,0.000094370225,0.00869094,0.21424499,0.772834,0.000030454043,0.00016639495],"about_ca_topic_score_codex":0.00006459438,"about_ca_topic_score_gemma":0.000020342253,"teacher_disagreement_score":0.60261846,"about_ca_system_score_codex":0.000022883638,"about_ca_system_score_gemma":0.000028734983,"threshold_uncertainty_score":0.2905067},"labels":[],"label_agreement":null},{"id":"W2029491700","doi":"10.2307/3315991","title":"Authors' addendum to: “A generalized‐moments specification test for the logistic link”","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Addendum; Link (geometry); Test (biology); Logistic regression; Econometrics; Mathematics; Computer science; Statistics; Political science; Combinatorics; Law; Geology","score_opus":0.05017725175222088,"score_gpt":0.29923536935334927,"score_spread":0.2490581176011284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029491700","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000097667384,0.00016307409,0.9954784,0.003398239,0.00026954262,0.00017106665,0.00018721088,0.000014108025,0.00022070605],"genre_scores_gemma":[0.13803938,0.0000923619,0.8581246,0.00081526063,0.0005746603,0.000013564013,0.000009674075,0.000017656272,0.0023128358],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998917,0.000031439533,0.00042022712,0.00015174196,0.00020201373,0.00027760395],"domain_scores_gemma":[0.9981751,0.00041779,0.00020526556,0.00036725696,0.00037498458,0.00045964116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036653117,0.00011113782,0.00016839181,0.00019171533,0.00023323698,0.00019582153,0.0009934243,0.00004242743,0.00015903139],"category_scores_gemma":[0.0006117011,0.000087143526,0.000057410532,0.0003487683,0.000066588516,0.00016730367,0.000012702386,0.0001560962,0.000031108204],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000078720705,0.00002251028,0.00043656174,0.000009342703,0.000062944644,0.000103960345,0.0005003971,0.0029183957,0.00015769177,0.15902995,0.2677639,0.5689865],"study_design_scores_gemma":[0.00043164263,0.0004976075,0.005644726,0.00006050795,0.000119383716,0.000078842335,0.000047265217,0.041776326,0.0005921294,0.1270251,0.82333004,0.00039644682],"about_ca_topic_score_codex":0.00037163516,"about_ca_topic_score_gemma":0.0033497924,"teacher_disagreement_score":0.56859,"about_ca_system_score_codex":0.00020167285,"about_ca_system_score_gemma":0.00044982106,"threshold_uncertainty_score":0.35536098},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016025685924846902,"score_gpt":0.2950436954188471,"score_spread":0.27901800949400024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032328503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07608683,0.000021043123,0.922473,0.000101745376,0.00013843851,0.00015264824,0.0000011538779,0.00014536605,0.00087975606],"genre_scores_gemma":[0.8730282,0.0000017921966,0.12679331,0.00012733469,0.000009851551,6.3575385e-7,0.0000081043145,0.0000015262516,0.000029232839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873674,0.000023851091,0.0004896937,0.0001185582,0.00047968785,0.00015145414],"domain_scores_gemma":[0.9988553,0.000027921944,0.00036414934,0.0003516878,0.00035639273,0.000044568318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991781,0.000087954206,0.00013130238,0.00045049714,0.00012522656,0.00029144232,0.00038742763,0.000044833167,0.000008330959],"category_scores_gemma":[0.00011209011,0.00008700669,0.00005907105,0.0010127735,0.000042933214,0.0049297926,0.000076947246,0.00006564358,0.000018396873],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068013214,0.00006210744,0.00017887336,0.000058573954,0.00003056094,0.000002354211,0.0052327854,0.015389724,0.04377983,0.081656314,0.00030506754,0.8532358],"study_design_scores_gemma":[0.0007095921,0.00027348706,0.0042520007,0.00010702849,0.000018363162,0.000017211005,0.000086201384,0.7957874,0.16236202,0.032525443,0.0034892815,0.00037195513],"about_ca_topic_score_codex":0.0000032243572,"about_ca_topic_score_gemma":8.041845e-7,"teacher_disagreement_score":0.85286385,"about_ca_system_score_codex":0.00010212303,"about_ca_system_score_gemma":0.000056798282,"threshold_uncertainty_score":0.35739806},"labels":[],"label_agreement":null},{"id":"W2033153019","doi":"10.1207/s15327663jcp1502_5","title":"When Categorization Is Ambiguous: Factors That Facilitate the Use of a Multiple Category Inference Strategy","year":2005,"lang":"en","type":"article","venue":"Journal of Consumer Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Cued speech; Ambiguity; Inference; Psychology; Cognitive psychology; Product category; Concept learning; Perception; Product (mathematics); Artificial intelligence; Computer science; Mathematics","score_opus":0.14715482868470045,"score_gpt":0.3529718958089943,"score_spread":0.20581706712429385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033153019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20276915,0.0005550287,0.79475725,0.0015089611,0.00015838382,0.00011292052,0.000005613585,0.00003896869,0.00009375062],"genre_scores_gemma":[0.97125745,0.00048340062,0.027380094,0.00070703594,0.000022908145,0.0000032548307,0.0000015292223,0.000009863837,0.00013444455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815136,0.0002488336,0.0007460398,0.00025163763,0.00034506127,0.0002570832],"domain_scores_gemma":[0.9973906,0.00038692105,0.0009878444,0.00067616464,0.00046922502,0.00008919295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036787603,0.0001926344,0.00040100812,0.0003159324,0.00007465689,0.00007781144,0.0010808021,0.000121214354,0.000057378224],"category_scores_gemma":[0.00018116305,0.00012830878,0.00018264093,0.00031346525,0.0002386311,0.0013243795,0.00009118434,0.00037057788,0.000012720532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020504967,0.00089731393,0.24633284,0.000043053427,0.0009911698,0.000053071017,0.01866339,0.003995233,0.029304702,0.0067336746,0.02888595,0.66389453],"study_design_scores_gemma":[0.0053242734,0.0022332568,0.3760942,0.00017282854,0.0005147676,0.0006780905,0.0010023145,0.035325777,0.08483753,0.09209806,0.3997776,0.0019413066],"about_ca_topic_score_codex":0.00018272562,"about_ca_topic_score_gemma":0.00011701117,"teacher_disagreement_score":0.76848835,"about_ca_system_score_codex":0.000042551866,"about_ca_system_score_gemma":0.000105282095,"threshold_uncertainty_score":0.52322805},"labels":[],"label_agreement":null},{"id":"W2033962915","doi":"10.1145/900051.900086","title":"User-controlled link adaptation","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Adaptive hypermedia; Computer science; Adaptation (eye); Annotation; Hypermedia; Focus (optics); Task (project management); Human–computer interaction; Link (geometry); Adaptive system; User modeling; Architecture; Control (management); Information retrieval; World Wide Web; User interface; Artificial intelligence","score_opus":0.013951534834722477,"score_gpt":0.2638670876887624,"score_spread":0.2499155528540399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033962915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027342807,0.00004042651,0.9462328,0.00034114806,0.000039962168,0.00011715014,3.331553e-8,0.00048219715,0.052472845],"genre_scores_gemma":[0.44818166,0.000006653573,0.549124,0.00025478413,0.000010504082,0.000018335868,2.449299e-7,0.000003081096,0.0024007116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992967,0.00005491218,0.00016538953,0.00020503256,0.0001466532,0.00013129292],"domain_scores_gemma":[0.9993761,0.00006903038,0.000059280166,0.00038357484,0.000072397015,0.000039613344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021343297,0.000074543525,0.00014821668,0.00009052625,0.000049531616,0.00006298904,0.0003099456,0.000032587654,0.00005672412],"category_scores_gemma":[0.00011183951,0.000059268943,0.0000756439,0.00031601096,0.000009967158,0.00046719305,0.000029992108,0.000052850184,0.00007474696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024693204,0.000015931502,0.00005939157,5.867111e-7,0.000012328629,0.0000021478447,0.00006585017,0.0002770615,0.0006404086,0.958935,0.0003132963,0.03967552],"study_design_scores_gemma":[0.00374577,0.00014804522,0.00032399732,0.000009929326,0.000033418517,0.0000126312525,0.000077082084,0.49232724,0.063613586,0.34693408,0.09217797,0.00059624686],"about_ca_topic_score_codex":0.0000055422584,"about_ca_topic_score_gemma":0.000014461947,"teacher_disagreement_score":0.61200094,"about_ca_system_score_codex":0.000023487297,"about_ca_system_score_gemma":0.000029112003,"threshold_uncertainty_score":0.24169174},"labels":[],"label_agreement":null},{"id":"W2035069493","doi":"10.1109/ichit.2006.165","title":"Keyword Extraction from Documents Using a Neural Network Model","year":2006,"lang":"en","type":"article","venue":"International Conference on Hybrid Information Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial neural network; Backpropagation; Keyword extraction; Selection (genetic algorithm); Word (group theory); Artificial intelligence; tf–idf; Feature selection; Natural language processing; Feature (linguistics); Feature extraction; Information retrieval; Term (time); Mathematics","score_opus":0.02295526057919053,"score_gpt":0.30580536325677865,"score_spread":0.28285010267758814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035069493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07170182,0.000009112874,0.91670674,0.001516969,0.00032498233,0.00013684315,0.00001523059,0.00079476245,0.008793559],"genre_scores_gemma":[0.84182703,0.000015839672,0.15751089,0.00035963434,0.000068176414,0.00003165515,0.00009710667,0.00000577701,0.000083863204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984858,0.000018634608,0.0005473827,0.0002659368,0.00042340724,0.0002588318],"domain_scores_gemma":[0.998671,0.000027006425,0.0004501541,0.00045076816,0.0003692593,0.00003181091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107049746,0.00018874963,0.0001700585,0.00063042715,0.00012613524,0.00028243524,0.0011707658,0.000105060084,0.00006499794],"category_scores_gemma":[0.000036879326,0.00019730015,0.00006721483,0.00036527935,0.00006515782,0.0037946827,0.00025925483,0.00027607533,0.000100212856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018698183,0.000043299544,0.0005668772,0.0000015379296,0.000030805186,0.0000061991145,0.000021860917,0.15678251,0.0011752845,0.7612448,0.0012025768,0.0789056],"study_design_scores_gemma":[0.00015262651,0.000021054084,0.00009354809,0.00001564622,0.0000039009265,0.000014527142,0.000008362368,0.6990044,0.005369073,0.29395375,0.00122905,0.00013403692],"about_ca_topic_score_codex":0.00013165819,"about_ca_topic_score_gemma":0.000013165436,"teacher_disagreement_score":0.7701252,"about_ca_system_score_codex":0.00022516506,"about_ca_system_score_gemma":0.00006107917,"threshold_uncertainty_score":0.8045666},"labels":[],"label_agreement":null},{"id":"W2037337707","doi":"10.1145/1458082.1458140","title":"Relating dependent indexes using dempster-shafer theory","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Search engine indexing; Dempster–Shafer theory; Computer science; Term (time); Information retrieval; Artificial intelligence; Index (typography); Data mining; World Wide Web","score_opus":0.036428326711995765,"score_gpt":0.2891301163310142,"score_spread":0.25270178961901846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037337707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10524161,0.00007692293,0.8862321,0.000035887762,0.00003726652,0.00006370505,1.15368955e-7,0.0005314658,0.0077809165],"genre_scores_gemma":[0.6414752,0.000007123479,0.3573451,0.00020383511,0.000020661862,0.0000029156724,2.173729e-7,0.0000072287025,0.0009377008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881876,0.00008662767,0.0002417619,0.0003380076,0.00027338607,0.00024143627],"domain_scores_gemma":[0.99909794,0.00012008646,0.00009625549,0.00056605716,0.00005910546,0.00006052467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031641257,0.00012707444,0.00015503759,0.00014419165,0.00023670818,0.00004395916,0.0006300428,0.000062945765,0.00004244733],"category_scores_gemma":[0.000059125956,0.00010768088,0.00007518976,0.0003464034,0.000051692037,0.000836944,0.00038763357,0.00014956544,0.000034371355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013259195,0.00018648678,0.0680783,0.000014635326,0.00014860534,0.00032714912,0.00356342,0.004498623,0.044354007,0.78008115,0.00042025046,0.09831413],"study_design_scores_gemma":[0.0007026303,0.00012906213,0.0075545837,0.000089376415,0.00005529103,0.00085324195,0.00018897711,0.39841524,0.21836866,0.37109205,0.0010070433,0.001543858],"about_ca_topic_score_codex":0.000021913895,"about_ca_topic_score_gemma":0.000007960434,"teacher_disagreement_score":0.5362336,"about_ca_system_score_codex":0.000063679996,"about_ca_system_score_gemma":0.000036117377,"threshold_uncertainty_score":0.43910986},"labels":[],"label_agreement":null},{"id":"W2037847309","doi":"10.1109/hicss.2014.228","title":"Introduction to Text Analytics Minitrack","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Analytics; Data science","score_opus":0.009641329039161796,"score_gpt":0.2665987821706924,"score_spread":0.25695745313153057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037847309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011548329,0.0000027463993,0.9789301,0.008966248,0.00008147406,0.00005306183,6.485404e-8,0.00045515105,0.010356307],"genre_scores_gemma":[0.30557263,0.0000017639866,0.68896115,0.001094466,0.00039180624,0.0000053095364,7.3780575e-7,0.000005057349,0.003967077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991709,0.000026282542,0.00014947752,0.00033185098,0.00016445165,0.0001570416],"domain_scores_gemma":[0.99901724,0.000036218335,0.00003720899,0.00073527807,0.00009261312,0.000081469894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023075489,0.00007999832,0.00011280078,0.00016554874,0.00004516567,0.00007598056,0.0005289682,0.0000279484,0.00006125278],"category_scores_gemma":[0.00013036253,0.00006973625,0.00004406617,0.00067327544,0.00001398361,0.00033385606,0.00014522002,0.00005775501,0.0004852508],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019802776,0.000053696407,0.00022626239,0.0000032846208,0.000016944326,9.764206e-7,0.00011762025,0.0009464267,0.0068699373,0.47503853,0.114734195,0.40199015],"study_design_scores_gemma":[0.00009450579,0.0001752711,0.0011034855,0.0000038895673,0.000014083669,0.0000080882955,0.0000149372345,0.15147346,0.08211715,0.041158166,0.7234811,0.00035583545],"about_ca_topic_score_codex":0.0000062506415,"about_ca_topic_score_gemma":0.000014411576,"teacher_disagreement_score":0.60874695,"about_ca_system_score_codex":0.000030057678,"about_ca_system_score_gemma":0.0000074935024,"threshold_uncertainty_score":0.62370795},"labels":[],"label_agreement":null},{"id":"W2039979754","doi":"10.1109/isspa.2012.6310552","title":"Automatic Document Topic Identification using Wikipedia Hierarchical Ontology","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ontology; Information retrieval; Identification (biology); Document clustering; Cluster analysis; Construct (python library); Hierarchical clustering; Data mining; Artificial intelligence","score_opus":0.02265378680570878,"score_gpt":0.3276773295832177,"score_spread":0.3050235427775089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039979754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12261613,0.00007008545,0.8752747,0.00038022423,0.0001615534,0.000090081616,6.0353955e-8,0.00040369356,0.0010034809],"genre_scores_gemma":[0.6414125,0.0000031817813,0.3581572,0.00014229267,0.00005244753,0.0000094387215,7.4979613e-7,0.0000030390113,0.00021919272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989858,0.0000738668,0.00026531957,0.0002057489,0.0001885632,0.00028069897],"domain_scores_gemma":[0.9991941,0.00006060729,0.00008983034,0.00053239084,0.000034141638,0.00008896469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029108897,0.00008955315,0.0001347884,0.00012498663,0.00007405057,0.00006489854,0.00046017746,0.000050313673,0.00008026506],"category_scores_gemma":[0.00003912534,0.00007785698,0.000051854895,0.00025567983,0.000036735226,0.0009955928,0.0001768216,0.00008370664,0.00006755705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.565606e-7,0.00014224394,0.006025184,0.000013416733,0.000028179102,0.0000026187163,0.00072399736,0.00001613339,0.007986967,0.7411171,0.00028445787,0.24365902],"study_design_scores_gemma":[0.00047136712,0.00007805788,0.062482167,0.000027242506,0.0000866536,0.00011222755,0.000060450482,0.5938627,0.05722787,0.2782495,0.006512328,0.00082940335],"about_ca_topic_score_codex":0.00002530421,"about_ca_topic_score_gemma":0.000009232007,"teacher_disagreement_score":0.5938466,"about_ca_system_score_codex":0.00009562404,"about_ca_system_score_gemma":0.000020088648,"threshold_uncertainty_score":0.31749156},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08088215470050462,"score_gpt":0.36584288331871384,"score_spread":0.2849607286182092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040027527","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.3314673e-9,0.6479406,0.34883615,0.00015716025,0.00009351386,0.00054759847,0.000002946581,0.00013989606,0.0022821645],"genre_scores_gemma":[1.7794851e-7,0.9207743,0.07724998,0.00023911189,0.00008276767,0.0002968891,0.000053217023,0.000040508938,0.0012630399],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968276,0.00036439032,0.0014194575,0.0007963431,0.00033936123,0.00025285516],"domain_scores_gemma":[0.99679935,0.00011879975,0.0015773184,0.0011658932,0.00022504436,0.00011357312],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014664526,0.00046673228,0.0025473596,0.00022766525,0.00005702496,0.00004240735,0.0014143612,0.0001851197,0.00015247292],"category_scores_gemma":[0.00011803115,0.00040027403,0.0008945009,0.00051701255,0.000049719885,0.00013135163,0.000273744,0.0005404102,0.0007190124],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.280056e-7,0.000025165278,5.708684e-8,0.014428656,0.000067743335,2.9613742e-7,0.0000036691147,0.000059188595,1.2546853e-7,0.0035328714,0.035036724,0.94684476],"study_design_scores_gemma":[0.000056278717,0.000036886435,1.9545308e-8,0.030853558,0.00050215446,0.000011474563,2.8739066e-7,0.0013376077,9.783754e-8,0.0012944211,0.9655828,0.0003244215],"about_ca_topic_score_codex":0.0000021744518,"about_ca_topic_score_gemma":2.5210625e-7,"teacher_disagreement_score":0.9465203,"about_ca_system_score_codex":0.00018048375,"about_ca_system_score_gemma":0.00034585578,"threshold_uncertainty_score":0.9998449},"labels":[],"label_agreement":null},{"id":"W2052799227","doi":"10.1109/3pgcic.2013.68","title":"Principal Component Analysis in Business Intelligence Applications","year":2013,"lang":"en","type":"article","venue":"2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Competitor analysis; Business intelligence; Context (archaeology); Identification (biology); Task (project management); Principal component analysis; Component (thermodynamics); Domain (mathematical analysis); Data science; Principal (computer security); Big data; Market intelligence; Business information; Chart; Competitive intelligence; Information retrieval; Artificial intelligence; Data mining; Knowledge management; Engineering; Marketing; Business; Computer security","score_opus":0.029996336928425234,"score_gpt":0.29628025998283475,"score_spread":0.2662839230544095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052799227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04606933,0.00008849644,0.94374704,0.0022198132,0.00038046026,0.00050159014,0.000006446699,0.00023788733,0.006748902],"genre_scores_gemma":[0.9463087,0.00025766093,0.05208072,0.0003937854,0.00024081209,0.00013533451,0.00007118072,0.000016117117,0.000495687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694896,0.00011413502,0.00090117846,0.0010205493,0.0005484217,0.00046677084],"domain_scores_gemma":[0.9979083,0.00017823132,0.00043379777,0.0006426218,0.0006548384,0.00018220303],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034252007,0.00041110447,0.00054448406,0.0008571179,0.00011184743,0.0006126615,0.002046668,0.00012347469,0.00035923012],"category_scores_gemma":[0.000045366476,0.0003646102,0.00015764798,0.0011598179,0.00015523216,0.00069721957,0.00091126165,0.000415711,0.0002709693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002203414,0.0003944257,0.010882966,0.000024773537,0.00045938054,0.00001630709,0.0006781399,0.012711502,0.0002998579,0.9260477,0.0011913137,0.04727164],"study_design_scores_gemma":[0.00021840804,0.00006299213,0.029110944,0.00010245633,0.000032308704,0.000012508319,0.00007132944,0.9505674,0.00024212066,0.014306126,0.0048028505,0.0004705383],"about_ca_topic_score_codex":0.0010484761,"about_ca_topic_score_gemma":0.00017479519,"teacher_disagreement_score":0.9378559,"about_ca_system_score_codex":0.00016715584,"about_ca_system_score_gemma":0.000052754396,"threshold_uncertainty_score":0.9998806},"labels":[],"label_agreement":null},{"id":"W2053624351","doi":"10.1111/j.0037-976x.2003.00263.x","title":"III. Study 2: Rule Complexity and Stimulus Characteristics in Executive Function","year":2003,"lang":"en","type":"article","venue":"Monographs of the Society for Research in Child Development","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Toronto","funders":"","keywords":"Psychology; Executive functions; Cognitive psychology; Stimulus (psychology); Cognition; Developmental psychology; Neuroscience","score_opus":0.08148596802906449,"score_gpt":0.36731655988695855,"score_spread":0.28583059185789406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053624351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9213206,0.0001522769,0.07591232,0.0003669657,0.0000662573,0.0018548805,0.0000039703027,0.000044189408,0.0002785259],"genre_scores_gemma":[0.9178023,0.000047952402,0.08188126,0.00003523067,0.0000040223367,0.00019706888,0.0000024663693,0.0000075694106,0.000022150927],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980368,0.00020485444,0.00042544503,0.00040124578,0.0005301695,0.0004014635],"domain_scores_gemma":[0.9990212,0.00018634254,0.00011346639,0.00044524777,0.00017899547,0.000054757955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032242036,0.00013127213,0.00026402005,0.00024177639,0.00033432234,0.000053680065,0.00065344834,0.000056519817,0.0000010487365],"category_scores_gemma":[0.000089974106,0.00010525523,0.00017619968,0.0015751026,0.00024104211,0.0001826885,0.0004910814,0.00037019016,3.1055674e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001745143,0.0035946954,0.87182206,0.00022127602,0.0005851754,0.0000049808345,0.04835718,0.00009830542,0.0003002994,0.033788327,0.0009237506,0.040129434],"study_design_scores_gemma":[0.002348928,0.000314705,0.89021784,0.00021458363,0.000014666138,0.0000029020262,0.0038999273,0.0036017757,0.004524861,0.09279211,0.0016839671,0.00038371736],"about_ca_topic_score_codex":0.000056211906,"about_ca_topic_score_gemma":0.00012768846,"teacher_disagreement_score":0.059003778,"about_ca_system_score_codex":0.00017422857,"about_ca_system_score_gemma":0.00011041138,"threshold_uncertainty_score":0.42921838},"labels":[],"label_agreement":null},{"id":"W2056425533","doi":"10.1167/8.6.628","title":"Visual spread reading: Noisy letters in their natural context","year":2010,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Legibility; Noise (video); Computer science; Context (archaeology); Artificial intelligence; Reading (process); Natural language processing; Natural (archaeology); Stimulus (psychology); Speech recognition; Pattern recognition (psychology); Psychology; Cognitive psychology; Computer vision; Communication; Image (mathematics); Linguistics; Geography; Art; Visual arts","score_opus":0.007233417522279048,"score_gpt":0.30445572434014584,"score_spread":0.29722230681786677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056425533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84948283,0.000099511475,0.14773631,0.001964152,0.00052797433,0.000050116014,1.455514e-7,0.0000395434,0.00009940143],"genre_scores_gemma":[0.95440245,0.000019319225,0.044927463,0.00049203634,0.0001290794,5.3856934e-7,2.476828e-7,0.0000072736293,0.00002159391],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998827,0.00005485865,0.00044785423,0.00016459625,0.00032089802,0.00018482575],"domain_scores_gemma":[0.9989863,0.00013966225,0.00039421045,0.00026457006,0.00013897193,0.00007629939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063280587,0.00012095551,0.0002611018,0.00040293534,0.000044146742,0.00009968027,0.0007853835,0.000060050173,0.000007402927],"category_scores_gemma":[0.00013308346,0.00008559478,0.00014557992,0.0003612499,0.000043242504,0.0011759826,0.00014280534,0.00069258583,0.0000073672604],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021292699,0.000080247635,0.0013843216,0.0000023236225,0.000011032439,0.00007549704,0.00034091683,0.00001543633,0.8260246,0.0014644021,0.0010009009,0.16957906],"study_design_scores_gemma":[0.003596697,0.0018241334,0.18231747,0.00084959104,0.000046376,0.0014243986,0.00031895496,0.10412968,0.6470588,0.022144126,0.03494737,0.00134243],"about_ca_topic_score_codex":0.00000928243,"about_ca_topic_score_gemma":0.000040236722,"teacher_disagreement_score":0.18093315,"about_ca_system_score_codex":0.000055113003,"about_ca_system_score_gemma":0.0000300675,"threshold_uncertainty_score":0.3490454},"labels":[],"label_agreement":null},{"id":"W2057505677","doi":"10.1111/j.1467-8640.2007.00293.x","title":"KEYWORD EXTRACTION STRATEGY FOR ITEM BANKS TEXT CATEGORIZATION","year":2007,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Selection (genetic algorithm); Keyword extraction; Natural language processing; Phrase; Sentence; Artificial intelligence; Text categorization; Feature selection; Information retrieval","score_opus":0.04857456591788745,"score_gpt":0.37604187604377143,"score_spread":0.327467310125884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057505677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082633295,0.00010701224,0.99676096,0.00017207551,0.00020078213,0.00029741708,0.000002284321,0.00038142572,0.001251718],"genre_scores_gemma":[0.65529704,0.000009138666,0.3442036,0.00012633449,0.0000829675,0.000021627302,0.000036149726,0.000010068839,0.00021309136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983733,0.00002657408,0.00048551863,0.00047760282,0.00034127722,0.0002957224],"domain_scores_gemma":[0.99794143,0.0008921009,0.00022389686,0.00028069303,0.0005703491,0.00009151287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005329649,0.0001692565,0.00015398463,0.0002734088,0.00019236907,0.00015108768,0.00060722156,0.00008990734,0.000022320797],"category_scores_gemma":[0.00014634241,0.00017870052,0.00009842662,0.0007608148,0.000056086737,0.00091546064,0.000072726834,0.0001362026,0.000053912387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009914154,0.000052109634,0.000106858424,0.00000863338,0.000012607507,0.0000034213333,0.00010608244,0.16017292,0.0003826218,0.42684302,0.000186924,0.4121149],"study_design_scores_gemma":[0.000047363294,0.00009253085,0.0020149392,0.000011315576,0.000007120181,0.000016390579,0.000035588288,0.63742447,0.018835446,0.33936512,0.0019324603,0.00021724723],"about_ca_topic_score_codex":0.000011786195,"about_ca_topic_score_gemma":0.000017272541,"teacher_disagreement_score":0.6544707,"about_ca_system_score_codex":0.00013515953,"about_ca_system_score_gemma":0.00008251334,"threshold_uncertainty_score":0.7287196},"labels":[],"label_agreement":null},{"id":"W2061449990","doi":"10.1002/asi.1101.abs","title":"User preferences in the classification of electronic bookmarks: Implications for a shared system","year":2001,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Computer science; Context (archaeology); World Wide Web; The Internet; Documentation; Information retrieval; Artificial intelligence","score_opus":0.018552468412853438,"score_gpt":0.3082505032618173,"score_spread":0.28969803484896384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061449990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17791995,0.00005601559,0.80867296,0.012696781,0.000024778123,0.00047287604,0.000004369089,0.000034453904,0.00011780318],"genre_scores_gemma":[0.96336144,0.00011006216,0.03613846,0.0003049411,0.000006946927,0.000073181734,4.3849374e-7,0.0000013133555,0.0000031860084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999044,0.0000138509,0.00043183097,0.000084594954,0.00024567812,0.00018003561],"domain_scores_gemma":[0.997446,0.00011912138,0.0012147164,0.0003331152,0.00087174634,0.000015306294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016086387,0.000058846992,0.0001595543,0.00028976912,0.00022335062,0.00007698849,0.0016685091,0.00003203092,8.974283e-8],"category_scores_gemma":[0.0002454409,0.00003348912,0.00011972439,0.0031025612,0.0006270936,0.0018078381,0.000087661916,0.00011824067,1.0957451e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017597818,0.000039048784,0.0060972753,0.00002987664,0.000035623347,2.0157676e-8,0.0017264881,0.000050818675,0.008576924,0.8146317,0.0015503954,0.16724423],"study_design_scores_gemma":[0.002442497,0.0029977523,0.27451155,0.00028797274,0.00022963776,0.00066929974,0.06411948,0.2036648,0.01195646,0.2614478,0.17691655,0.00075619214],"about_ca_topic_score_codex":0.0000042274432,"about_ca_topic_score_gemma":0.000004426876,"teacher_disagreement_score":0.7854415,"about_ca_system_score_codex":0.000142846,"about_ca_system_score_gemma":0.00027969322,"threshold_uncertainty_score":0.31005326},"labels":[],"label_agreement":null},{"id":"W2061552568","doi":"10.1037/0278-7393.32.6.1431","title":"Relation availability was not confounded with familiarity or plausibility in Gagné and Shoben (1997): Comment on Wisniewski and Murphy (2005).","year":2006,"lang":"en","type":"letter","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of Mental Health","keywords":"Relation (database); Phrase; Psychology; Artificial intelligence; Computer science; Data mining","score_opus":0.03262812095320073,"score_gpt":0.32581819497411074,"score_spread":0.29319007402091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061552568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88908225,0.0010617228,0.021600313,0.08530705,0.00035013453,0.0008710294,0.000009509648,0.00011742423,0.0016005909],"genre_scores_gemma":[0.90030503,0.00021290628,0.0074504325,0.09153166,0.0002203689,0.000027572654,0.000060182087,0.000026771924,0.00016509891],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99720776,0.00071490294,0.00073220767,0.0006856482,0.0003713642,0.00028811436],"domain_scores_gemma":[0.9983281,0.00037658142,0.00081108534,0.00029134806,0.00011070183,0.00008218361],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010964661,0.0003504127,0.0006321542,0.00035024426,0.00019161888,0.00010123724,0.00020612247,0.00047697002,0.000030005236],"category_scores_gemma":[0.00006067179,0.0002810703,0.0000663209,0.00016621812,0.00039688626,0.0005848799,0.00010198825,0.0024790678,0.0000021684841],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029684134,0.010909838,0.09670938,0.0015016525,0.0020920767,0.009737854,0.015805287,0.00041908943,0.06569163,0.0014583875,0.6430989,0.12289177],"study_design_scores_gemma":[0.05858054,0.05321343,0.43969354,0.0068913773,0.0016114386,0.011158505,0.0046586925,0.008820625,0.07187363,0.050985925,0.2834216,0.009090716],"about_ca_topic_score_codex":0.000023048431,"about_ca_topic_score_gemma":0.000025725461,"teacher_disagreement_score":0.3596773,"about_ca_system_score_codex":0.00016742607,"about_ca_system_score_gemma":0.00004700301,"threshold_uncertainty_score":0.9999641},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031040022811816538,"score_gpt":0.23764317546717234,"score_spread":0.2066031526553558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066433987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863021,0.000096751464,0.010634359,0.0009924609,0.000011798441,0.00036561355,6.5421665e-7,0.0002956671,0.0013006154],"genre_scores_gemma":[0.92420083,0.00019141538,0.07513737,0.00017539503,0.000016224625,0.00010102229,0.000001897622,0.000012780699,0.00016304702],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823636,0.000097768396,0.0004031876,0.000560119,0.0002993475,0.0004032095],"domain_scores_gemma":[0.9989112,0.00027136455,0.0001305144,0.00046867566,0.00012420377,0.000094036805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017755352,0.00019416823,0.00042136037,0.0005102419,0.00006201693,0.00014524518,0.00056109764,0.00010000035,0.000030364066],"category_scores_gemma":[0.00043200995,0.00018425942,0.000027008433,0.0009894958,0.000083057086,0.0011053854,0.00019998237,0.00027150987,0.000043140997],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000175741,0.0015221629,0.65343034,0.00026489058,0.00016565305,0.000070461465,0.011783822,0.0000067399956,0.24123436,0.034681413,0.00025299683,0.05656956],"study_design_scores_gemma":[0.0019755068,0.0004834536,0.51091087,0.004273822,0.00008991396,0.000014830413,0.002193634,0.23085266,0.14891575,0.098190874,0.000017883185,0.0020807788],"about_ca_topic_score_codex":0.0007826106,"about_ca_topic_score_gemma":0.00025489173,"teacher_disagreement_score":0.23084591,"about_ca_system_score_codex":0.000095725205,"about_ca_system_score_gemma":0.00002108881,"threshold_uncertainty_score":0.7513881},"labels":[],"label_agreement":null},{"id":"W206788155","doi":"10.4018/978-1-60566-904-5.ch015","title":"Using Graphics to Improve Understanding of Conceptual Models","year":2010,"lang":"en","type":"book-chapter","venue":"Advances in database research (ADR) book series/Advances in database research series","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Graphics; Cognitive load; Computer science; Comprehension; Cognition; Domain (mathematical analysis); Human–computer interaction; Computer graphics; Multimedia; Artificial intelligence; Computer graphics (images); Programming language; Psychology","score_opus":0.20224303746265215,"score_gpt":0.4459812781824064,"score_spread":0.24373824071975425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W206788155","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022638615,0.10903624,0.7111667,0.0014767823,0.0014434407,0.010381593,0.0130688,0.00070971786,0.15249038],"genre_scores_gemma":[0.0036127623,0.47826532,0.49467656,0.00019808879,0.0006695579,0.0012221792,0.0021983702,0.0006032609,0.0185539],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.973793,0.002249825,0.0043706507,0.005220634,0.009910887,0.004454944],"domain_scores_gemma":[0.97851825,0.0052597933,0.0013768038,0.010233444,0.003390286,0.0012214062],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","sts","open_science"],"category_scores_codex":[0.022906851,0.0018502082,0.00341936,0.009508311,0.0013206773,0.0006057193,0.00958489,0.0009805689,0.00036222895],"category_scores_gemma":[0.0059455605,0.001882313,0.00051552925,0.005193987,0.0125402985,0.05727638,0.014820343,0.010660112,0.000062094514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008507558,0.0002292952,0.000034924433,0.0011485643,0.00008441931,0.0011372783,0.00076023664,0.0012474151,0.008902994,0.9809061,0.0004490806,0.004248928],"study_design_scores_gemma":[0.0008736091,0.00097509025,0.0000010069356,0.003937058,0.000022408154,0.00008051613,0.0019019288,0.0034137056,0.0227094,0.44931984,0.5149832,0.0017822634],"about_ca_topic_score_codex":0.00048609133,"about_ca_topic_score_gemma":0.01334915,"teacher_disagreement_score":0.5315862,"about_ca_system_score_codex":0.0029091847,"about_ca_system_score_gemma":0.0026714648,"threshold_uncertainty_score":0.9999795},"labels":[],"label_agreement":null},{"id":"W2071049913","doi":"10.3390/informatics1010032","title":"Using Collaborative Tagging for Text Classification: From Text Classification to Opinion Mining","year":2013,"lang":"en","type":"article","venue":"Informatics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Polytechnique Montréal","funders":"Génome Québec; Genome Canada","keywords":"Ranking (information retrieval); Computer science; Task (project management); Context (archaeology); Information retrieval; Document classification; Natural language processing; Artificial intelligence; World Wide Web; Engineering; Geography","score_opus":0.07513631016913433,"score_gpt":0.34807593113271956,"score_spread":0.27293962096358526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071049913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010656506,0.00002776086,0.98491865,0.0011110678,0.0001756188,0.00082470966,0.000013131688,0.00030472118,0.0019678376],"genre_scores_gemma":[0.22860485,0.000009338258,0.7703224,0.000700673,0.00007992594,0.00019368732,0.000036601912,0.000011868338,0.00004065643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844784,0.000031618387,0.0007164687,0.00022008416,0.0003003951,0.0002835925],"domain_scores_gemma":[0.99778014,0.00025956714,0.0005098493,0.0007046988,0.00062538753,0.00012034501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022912337,0.00018646306,0.0002361088,0.00026126264,0.0002548661,0.00047394264,0.0007458944,0.00009986546,0.00001452274],"category_scores_gemma":[0.00019772773,0.0001824801,0.000060390943,0.0009595027,0.000038723607,0.002659753,0.00017249775,0.00009392015,0.00012818945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001977913,0.00014006355,0.0011872005,0.00012630958,0.000160863,4.6785695e-7,0.048455283,0.005329021,0.03457863,0.12197671,0.040785182,0.7472405],"study_design_scores_gemma":[0.0001756449,0.00004776348,0.0011489103,0.000074304815,0.000010694674,0.0000011416425,0.0034747939,0.9616846,0.0034413994,0.0036797537,0.025984745,0.00027628767],"about_ca_topic_score_codex":0.000021342556,"about_ca_topic_score_gemma":0.000006096379,"teacher_disagreement_score":0.9563555,"about_ca_system_score_codex":0.00020807257,"about_ca_system_score_gemma":0.000113558104,"threshold_uncertainty_score":0.7441322},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04250187749906544,"score_gpt":0.3179108858070179,"score_spread":0.27540900830795245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072435181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40383947,0.00006399833,0.5915224,0.00019986315,0.000109045825,0.00006596902,1.5161137e-7,0.000104150924,0.0040949658],"genre_scores_gemma":[0.972892,0.00007372345,0.026875567,0.000090993795,0.00004454733,0.0000049541327,0.0000015982296,0.0000026669666,0.000013966712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991961,0.000019677163,0.00016216775,0.0002709548,0.00018550397,0.00016557038],"domain_scores_gemma":[0.99975103,0.0000115862,0.00006200401,0.00010245922,0.00005331017,0.000019634963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017525947,0.000069335445,0.000097215416,0.00021906197,0.00019634803,0.000107176704,0.00016844021,0.00003871259,0.000002058132],"category_scores_gemma":[0.000018960953,0.00007494411,0.000014977896,0.00047863543,0.00013906769,0.0012136919,0.00007660504,0.00008737662,8.795813e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008116258,0.00007723346,0.00524651,0.00002470962,0.000009151458,0.000014128741,0.0043909857,0.00012641963,0.008563037,0.5915635,0.000008676211,0.3899675],"study_design_scores_gemma":[0.002089723,0.00013825425,0.069294274,0.00021295318,0.000019307396,0.00018297146,0.004709634,0.029715812,0.023088148,0.86919373,0.0008030568,0.0005521354],"about_ca_topic_score_codex":0.000027881719,"about_ca_topic_score_gemma":0.00008739248,"teacher_disagreement_score":0.5690525,"about_ca_system_score_codex":0.00008566287,"about_ca_system_score_gemma":0.0000214854,"threshold_uncertainty_score":0.30561322},"labels":[],"label_agreement":null},{"id":"W2073654225","doi":"10.5430/air.v4n1p1","title":"Using a predefined passphrase to evaluate a speaker verification system","year":2014,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speaker verification; Computer science; Biometrics; Variety (cybernetics); Process (computing); Feature (linguistics); Speaker recognition; Focus (optics); Speech recognition; Artificial intelligence; Natural language processing; Programming language; Linguistics","score_opus":0.32271136736696715,"score_gpt":0.4872202259271605,"score_spread":0.16450885856019337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073654225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0408391,0.000019535806,0.9554945,0.0007602272,0.00010169532,0.00052285945,9.741013e-7,0.00037901814,0.0018820479],"genre_scores_gemma":[0.85300106,0.000004097932,0.14666294,0.000046773494,0.000100675294,0.0000926092,0.0000015455862,0.000017373402,0.00007294782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959285,0.00076343707,0.00054008904,0.00081126805,0.0012340194,0.00072266854],"domain_scores_gemma":[0.9969169,0.0003910734,0.0000917971,0.0014313946,0.0009027053,0.00026613177],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051947227,0.0001702867,0.00024213022,0.0006320496,0.00041190657,0.000425825,0.0014935099,0.00008716393,0.000031071962],"category_scores_gemma":[0.0011467645,0.00016267144,0.00008775863,0.0027025715,0.00012298995,0.0004673873,0.00051444204,0.00030803285,0.001121125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002969708,0.00008753379,0.000074646865,0.000026597994,0.000015426389,0.0000072936864,0.0007207774,0.004441837,0.08555941,0.5798951,0.00014706323,0.32899463],"study_design_scores_gemma":[0.000012070049,0.00013052771,0.0000270601,0.00006317164,0.0000057653992,0.0000062520053,0.00021475031,0.74860215,0.19594483,0.053876087,0.00093967875,0.00017767394],"about_ca_topic_score_codex":0.00037770547,"about_ca_topic_score_gemma":0.00010156068,"teacher_disagreement_score":0.8121619,"about_ca_system_score_codex":0.00039136628,"about_ca_system_score_gemma":0.00013654341,"threshold_uncertainty_score":0.9996566},"labels":[],"label_agreement":null},{"id":"W2077409459","doi":"10.1504/ijamc.2008.018504","title":"Keyword extraction rules based on a part-of-speech hierarchy","year":2008,"lang":"en","type":"article","venue":"International Journal of Advanced Media and Communication","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hierarchy; Natural language processing; Artificial intelligence; Sentence; Domain (mathematical analysis); Set (abstract data type); Field (mathematics); Context (archaeology); Natural language; Keyword extraction; Natural language understanding","score_opus":0.021887724369164682,"score_gpt":0.3129724551895625,"score_spread":0.2910847308203978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077409459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18253961,0.001145182,0.80966544,0.004749931,0.00045038667,0.00010933592,0.000004259779,0.000064518,0.0012713531],"genre_scores_gemma":[0.72388995,0.003036904,0.27285847,0.00012043822,0.00006136544,0.000004453402,0.000006938882,0.000005076394,0.000016401153],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99867475,0.0000972006,0.00047001624,0.0001170267,0.0005560066,0.00008498044],"domain_scores_gemma":[0.9976513,0.0005198756,0.0006744244,0.00041686624,0.0006747012,0.000062833264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029280255,0.00009595665,0.00018223762,0.00035849583,0.00006992028,0.000023702398,0.0010432224,0.000042885906,0.000008023418],"category_scores_gemma":[0.0002812422,0.00008639808,0.000089718764,0.00016166165,0.000108472515,0.00079625606,0.0001009188,0.00024075857,0.000001789517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022176704,0.00029259146,0.0013007929,0.000005567266,0.00007422975,0.000047855472,0.00096952525,0.0019591074,0.008100069,0.017158244,0.00019224307,0.969678],"study_design_scores_gemma":[0.008421412,0.0020745455,0.06055212,0.0022158031,0.00013149757,0.0019689952,0.00054954266,0.12758298,0.32763687,0.3266389,0.14085191,0.0013753931],"about_ca_topic_score_codex":0.0000045668035,"about_ca_topic_score_gemma":0.000005358386,"teacher_disagreement_score":0.9683026,"about_ca_system_score_codex":0.0000714618,"about_ca_system_score_gemma":0.000070680486,"threshold_uncertainty_score":0.35232115},"labels":[],"label_agreement":null},{"id":"W2081510074","doi":"10.4028/www.scientific.net/amr.760-762.852","title":"Semantic Similarity Measure Based on Concreteness Degree of a Concept","year":2013,"lang":"en","type":"article","venue":"Advanced materials research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Transportation of Ontario","funders":"Division of Materials Research; Natural Science Foundation of Hebei Province","keywords":"Concreteness; Semantic similarity; Similarity (geometry); Process (computing); Measure (data warehouse); Task (project management); Degree (music); Computer science; Ontology; Semantics (computer science); Natural language processing; Artificial intelligence; Mathematics; Data mining; Image (mathematics); Cognitive psychology; Psychology; Engineering","score_opus":0.08846113571753662,"score_gpt":0.3716765264366494,"score_spread":0.2832153907191128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081510074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22364037,0.00016484114,0.7701391,0.0012017566,0.00022039755,0.0017424027,0.000028962611,0.0005190131,0.0023431873],"genre_scores_gemma":[0.92072195,0.000017245902,0.078698404,0.0001450784,0.000034004453,0.00024981974,0.000008917739,0.000025380035,0.0000991836],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99611133,0.00070600933,0.00051956135,0.0006810625,0.0012851222,0.00069692533],"domain_scores_gemma":[0.99607176,0.0007176861,0.00018717424,0.0015666487,0.0012988033,0.00015790462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015109717,0.00023556613,0.00055165164,0.00042100035,0.00018096835,0.00018336785,0.001695749,0.0001356743,0.0002896204],"category_scores_gemma":[0.00084228936,0.00020322997,0.00009063677,0.0009727374,0.00035322184,0.0008313541,0.00044100816,0.00027691337,0.000091433656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005935427,0.00008339251,0.000040903058,0.000079001235,0.000019437395,0.00001464463,0.000078661586,0.00062588445,0.95624167,0.01049012,0.00033771413,0.03192921],"study_design_scores_gemma":[0.00046539918,0.00036981367,0.00048003474,0.00014216028,0.0000043159002,0.0000016712679,0.000024746265,0.0065839305,0.97567797,0.015785053,0.00024678255,0.00021809604],"about_ca_topic_score_codex":0.00017587282,"about_ca_topic_score_gemma":0.000008575767,"teacher_disagreement_score":0.6970816,"about_ca_system_score_codex":0.000107958156,"about_ca_system_score_gemma":0.00015116073,"threshold_uncertainty_score":0.82874775},"labels":[],"label_agreement":null},{"id":"W2084026949","doi":"10.1109/cec.2013.6557603","title":"An evolutionary algorithm for Feature Selective Double Clustering of text documents","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Document clustering; Feature (linguistics); Artificial intelligence; Cluster (spacecraft); Data mining; Information retrieval; Algorithm; Pattern recognition (psychology)","score_opus":0.00884334672967403,"score_gpt":0.2884877279305971,"score_spread":0.2796443812009231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084026949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043601988,0.00003786745,0.9966302,0.00014213914,0.000038458355,0.0004328906,0.0000020818693,0.0002550577,0.0020252995],"genre_scores_gemma":[0.14336288,0.0000032679256,0.8552388,0.000079749865,0.000027255192,0.00011397324,0.000007178284,0.0000074484874,0.0011594449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913985,0.000016655045,0.00015629087,0.00031423548,0.00016816317,0.00020479897],"domain_scores_gemma":[0.99909997,0.000033319164,0.00009343058,0.00041714337,0.0002955921,0.000060525224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000807485,0.00010961143,0.00016352467,0.00011915379,0.000077784185,0.000040508825,0.00059569813,0.000060511713,0.000023458495],"category_scores_gemma":[0.0000043576943,0.00009405983,0.00006991471,0.0003388184,0.000026272877,0.0016851281,0.00015003576,0.00006746083,0.000010488718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016023636,0.00035465925,0.0008701137,0.000026029244,0.0001571713,0.0000015074576,0.00053670834,0.0009296762,0.02406122,0.021510256,0.019276926,0.9322597],"study_design_scores_gemma":[0.00043129874,0.00021699027,0.002363149,0.000009233762,0.000009172733,0.0000050220874,0.000031426196,0.9230421,0.0469766,0.026031218,0.00068617443,0.00019756622],"about_ca_topic_score_codex":0.00017764833,"about_ca_topic_score_gemma":0.000012840112,"teacher_disagreement_score":0.93206215,"about_ca_system_score_codex":0.000070074435,"about_ca_system_score_gemma":0.00002681386,"threshold_uncertainty_score":0.38356486},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.018819512951789196,"score_gpt":0.2764848424940115,"score_spread":0.2576653295422223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086368750","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014655105,0.00005177784,0.92937046,0.001281737,0.000028569832,0.000036677575,2.3925772e-8,0.0007393796,0.06702583],"genre_scores_gemma":[0.3102618,0.00003103647,0.67496437,0.0011944873,0.000036377565,0.000010677129,3.5662256e-7,0.0000048438515,0.013496049],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936664,0.000012823422,0.00010055497,0.00021939697,0.00014580105,0.00015478204],"domain_scores_gemma":[0.9992997,0.000021265161,0.000025670808,0.0005682178,0.00003557985,0.000049557224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000063409774,0.000067815905,0.000081167454,0.000072151146,0.000041363597,0.000056075973,0.0006714587,0.00002486071,0.0001767108],"category_scores_gemma":[0.000013165055,0.00005434506,0.000045638302,0.00021105596,0.000015511205,0.00051736156,0.00018385479,0.000030447964,0.0000979774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018375048,0.00007736084,0.0027044713,0.0000012545581,0.00001887845,0.00008648784,0.0007772437,0.000014241789,0.0044169333,0.317626,0.0660877,0.60818756],"study_design_scores_gemma":[0.00023947032,0.00008530289,0.0010322812,0.000010789636,0.000006025892,0.00008168467,0.00006770849,0.035926707,0.036894884,0.3967483,0.52836484,0.0005419954],"about_ca_topic_score_codex":0.000032679123,"about_ca_topic_score_gemma":0.000037156904,"teacher_disagreement_score":0.6076456,"about_ca_system_score_codex":0.000020358844,"about_ca_system_score_gemma":0.000007844028,"threshold_uncertainty_score":0.22161272},"labels":[],"label_agreement":null},{"id":"W2087006618","doi":"10.1002/meet.2008.1450450206","title":"Concept theory and the role of conceptual coherence in assessments of similarity","year":2008,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Coherence (philosophical gambling strategy); Similarity (geometry); Representation (politics); Computer science; Epistemology; Concept learning; Conceptual framework; Cognitive psychology; Cognitive science; Psychology; Artificial intelligence; Mathematics","score_opus":0.009150753586632495,"score_gpt":0.27932940321944766,"score_spread":0.2701786496328152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087006618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98049,0.000095405085,0.01791495,0.00058152067,0.000008552407,0.00037214585,0.000004495092,0.000039108156,0.00049379637],"genre_scores_gemma":[0.97046345,0.00010839909,0.029232452,0.0001630561,0.0000012284164,0.00002741765,1.1625936e-7,0.0000011975937,0.0000026622417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906963,0.000005754295,0.00033024934,0.00012592727,0.00031526724,0.00015317998],"domain_scores_gemma":[0.99809384,0.0001524161,0.0008285849,0.0001506174,0.00075774756,0.000016808443],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0013778809,0.0000707194,0.0002518805,0.00014178258,0.00015870623,0.000014172056,0.0010527102,0.000036328405,1.8780983e-7],"category_scores_gemma":[0.00052080216,0.000044008775,0.00006180298,0.0022975374,0.015741564,0.0014493014,0.00049543113,0.00010628606,3.2106012e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021320142,0.000016493135,0.012233714,0.000014580606,0.00001448686,4.7206012e-9,0.0074369237,0.0000025005359,0.013966989,0.9214388,0.000035635483,0.04481854],"study_design_scores_gemma":[0.0014692333,0.00047115065,0.009773089,0.000058681922,0.00003063462,0.000020722006,0.06862638,0.021653326,0.57951343,0.317068,0.001081167,0.00023416571],"about_ca_topic_score_codex":0.000021026734,"about_ca_topic_score_gemma":3.644304e-7,"teacher_disagreement_score":0.6043708,"about_ca_system_score_codex":0.000025455905,"about_ca_system_score_gemma":0.00011037042,"threshold_uncertainty_score":0.98693705},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0283444507547641,"score_gpt":0.3147546726853978,"score_spread":0.2864102219306337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089286873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8606627,0.011103723,0.06804077,0.041950416,0.003759834,0.000793481,0.0000168357,0.00010006459,0.013572172],"genre_scores_gemma":[0.94475704,0.00010422806,0.047260094,0.0071764207,0.00011686451,0.000043151576,0.0000012227237,0.000037233254,0.0005037285],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679637,0.00034784665,0.00054970686,0.00073085807,0.00013417575,0.0014410338],"domain_scores_gemma":[0.99601644,0.00016443408,0.00037576273,0.0011679182,0.00014896167,0.0021264753],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015371469,0.00038566574,0.00043773954,0.00056227995,0.000627517,0.0003408297,0.002164668,0.00018353431,0.000043041997],"category_scores_gemma":[0.00041419565,0.00034121837,0.00019600742,0.0006895017,0.00043968472,0.0005402764,0.00008446534,0.0005113573,0.000020063928],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015487183,0.00046006488,0.011244453,0.00002115098,0.0006356601,0.003519077,0.022750149,0.00008447829,0.3154028,0.2798843,0.33913332,0.026709687],"study_design_scores_gemma":[0.0039321855,0.0040577287,0.008758072,0.00024061448,0.00007664855,0.013705551,0.01869086,0.00016739579,0.14495543,0.03148971,0.771781,0.0021447672],"about_ca_topic_score_codex":0.0006983363,"about_ca_topic_score_gemma":0.01722547,"teacher_disagreement_score":0.43264773,"about_ca_system_score_codex":0.0009917932,"about_ca_system_score_gemma":0.00039675552,"threshold_uncertainty_score":0.999904},"labels":[],"label_agreement":null},{"id":"W2089787183","doi":"10.1109/cse.2014.69","title":"Automatic Twitter Topic Summarization","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Automatic summarization; Computer science; Ranking (information retrieval); Hidden Markov model; Multi-document summarization; Information retrieval; Social media; Bayesian probability; Parametric statistics; Artificial intelligence; Data mining; World Wide Web; Mathematics","score_opus":0.009246781099650433,"score_gpt":0.25368207453427477,"score_spread":0.24443529343462433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089787183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005247337,0.0000030223232,0.9756933,0.00067255076,0.000037601694,0.000040807903,1.2028069e-8,0.0007322776,0.017573085],"genre_scores_gemma":[0.6259701,8.6440434e-7,0.37179083,0.00084894674,0.000021079833,0.0000056598715,7.2260417e-7,0.0000026616515,0.001359144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994801,0.000029681232,0.00011199336,0.00016074818,0.000115642935,0.000101821555],"domain_scores_gemma":[0.9994483,0.000035981007,0.00003569348,0.0004217942,0.00003096474,0.000027283899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000111677946,0.000055550136,0.00007673034,0.00006923806,0.000035768455,0.00006275611,0.0003771272,0.000023723838,0.00007323396],"category_scores_gemma":[0.000033030767,0.000045077286,0.000029076882,0.00022115523,0.000010418708,0.00032812657,0.00009996923,0.000033065084,0.00009615794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.13903276e-7,0.00002170608,0.003273217,0.000007024316,0.000007396882,7.4796674e-7,0.00012719353,0.00002781275,0.0010542907,0.5059079,0.0028618753,0.48671076],"study_design_scores_gemma":[0.00007831114,0.000029079962,0.0050035957,0.0000062302584,0.000004237798,0.0000017756505,0.0000024368292,0.8624446,0.010798234,0.1075573,0.013933625,0.00014057527],"about_ca_topic_score_codex":0.0000059543677,"about_ca_topic_score_gemma":0.000004228676,"teacher_disagreement_score":0.8624168,"about_ca_system_score_codex":0.0000150933665,"about_ca_system_score_gemma":0.000005335191,"threshold_uncertainty_score":0.18381983},"labels":[],"label_agreement":null},{"id":"W2091303901","doi":"10.1016/j.fss.2012.03.011","title":"Fuzzy logic and semiotic methods in modeling of medical concepts","year":2012,"lang":"en","type":"article","venue":"Fuzzy Sets and Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Computer science; Representation (politics); Context (archaeology); Semiotics; Knowledge representation and reasoning; Ambiguity; Field (mathematics); Process (computing); Artificial intelligence; Data science; Theoretical computer science; Management science; Cognitive science; Epistemology; Mathematics; Programming language; Psychology","score_opus":0.06177873447235941,"score_gpt":0.4079266917271283,"score_spread":0.3461479572547689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091303901","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050682765,0.010526416,0.9362621,0.00018330321,0.00018483539,0.00016883838,0.0000011386823,0.000078502526,0.0019121403],"genre_scores_gemma":[0.90188456,0.0001995337,0.09779335,0.000051585426,0.000039911392,0.000009135867,7.816177e-7,0.0000051893435,0.000015951604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985272,0.00027677687,0.00038956525,0.00023401722,0.00032292053,0.00024949084],"domain_scores_gemma":[0.9992431,0.00017541839,0.000106930194,0.00027747752,0.00004112419,0.00015597485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021896476,0.00011397397,0.00037379842,0.00012755612,0.00003641944,0.00004208104,0.00030419946,0.0001245483,0.0000015134013],"category_scores_gemma":[0.00012264571,0.00008819566,0.00003017158,0.00022878686,0.00006090117,0.0003386291,0.000233537,0.00013244383,9.310935e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010207215,0.00021507952,0.04158862,0.00067805604,0.00010485189,0.000035538407,0.008373341,0.0030322252,0.0027095736,0.7917834,0.00029163493,0.15117745],"study_design_scores_gemma":[0.00025327236,0.0000437051,0.00071580085,0.0001966319,0.000011761579,0.00006678637,0.00032860338,0.9808554,0.00013834643,0.016920835,0.00027109176,0.00019773153],"about_ca_topic_score_codex":0.00016715683,"about_ca_topic_score_gemma":0.000008046915,"teacher_disagreement_score":0.9778232,"about_ca_system_score_codex":0.000019986446,"about_ca_system_score_gemma":0.000020657535,"threshold_uncertainty_score":0.35965145},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02404426383237939,"score_gpt":0.2786062161423486,"score_spread":0.2545619523099692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091597866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895038,0.002384622,0.002710968,0.000047749218,0.0024034095,0.0016015192,0.000020636928,0.00023269505,0.0010945785],"genre_scores_gemma":[0.9892875,0.000005792036,0.0064478964,0.0000104951205,0.000039572664,0.00006278135,0.000008735263,0.000017132703,0.0041201166],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9951006,0.0004042723,0.0009191996,0.0014305171,0.0016195271,0.00052586076],"domain_scores_gemma":[0.993511,0.00014730389,0.00063548493,0.0039312267,0.0016460142,0.00012895405],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0026940021,0.00035954604,0.00051070884,0.00086624065,0.0013527607,0.0020461814,0.004328735,0.00011750573,0.000012605225],"category_scores_gemma":[0.00017925812,0.00023188791,0.00020151095,0.008470151,0.00060761767,0.0012738621,0.0010438355,0.00048940553,0.000008610586],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014535003,0.017035697,0.020217737,0.000118577795,0.00055238,0.0001762826,0.8815633,0.000028273123,0.017099531,0.023722524,0.012354781,0.026985582],"study_design_scores_gemma":[0.019371366,0.031250592,0.26967782,0.0044312687,0.0016273715,0.00023504219,0.1973215,0.009680705,0.19433215,0.18191089,0.08191078,0.008250518],"about_ca_topic_score_codex":0.00001679109,"about_ca_topic_score_gemma":0.00016493839,"teacher_disagreement_score":0.6842418,"about_ca_system_score_codex":0.00003326882,"about_ca_system_score_gemma":0.00008266947,"threshold_uncertainty_score":0.99994737},"labels":[],"label_agreement":null},{"id":"W2091855347","doi":"10.5539/cis.v7n4p123","title":"Ontology Based Data Mining Approach on Web Documents","year":2014,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Ontology; Information retrieval; Web mining; The Internet; World Wide Web; Data Web; Data mining; Web page","score_opus":0.02619256338547216,"score_gpt":0.2971963681470349,"score_spread":0.2710038047615627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091855347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026569376,0.000003634256,0.9829568,0.00023968157,0.00012461966,0.00008020471,0.0000011559272,0.00017774868,0.013759212],"genre_scores_gemma":[0.47286376,0.0000031118652,0.524805,0.0022884724,0.00001964956,0.0000035813623,0.000010358037,0.0000011343764,0.0000049379614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987313,0.000033901833,0.00025172907,0.0003439586,0.00041490508,0.0002241741],"domain_scores_gemma":[0.998499,0.00007896989,0.00013523622,0.0010761423,0.00011482674,0.00009582844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010801319,0.00010300278,0.00012680663,0.00041477298,0.00025134467,0.00051125337,0.0022045542,0.000029235818,0.0000018365465],"category_scores_gemma":[0.000075246804,0.000086071625,0.000014959572,0.00075956626,0.00019398612,0.01187658,0.0009070171,0.000073263356,0.00002219152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031796549,0.000031908803,0.00058689044,0.000014541881,0.0000036105507,2.4957512e-7,0.0004975685,0.0013868558,0.000068269364,0.11588865,0.0019752288,0.87954307],"study_design_scores_gemma":[0.00016995057,0.000069369155,0.0015453525,0.000008962843,0.00000142085,0.000004685102,0.0000054614484,0.97630596,0.00019545482,0.00033186917,0.021254374,0.00010714208],"about_ca_topic_score_codex":0.0000023478865,"about_ca_topic_score_gemma":4.1703407e-7,"teacher_disagreement_score":0.9749191,"about_ca_system_score_codex":0.0000265716,"about_ca_system_score_gemma":0.000075452175,"threshold_uncertainty_score":0.8610234},"labels":[],"label_agreement":null},{"id":"W2094256961","doi":"10.1145/2661829.2661963","title":"Succinct Queries for Linking and Tracking News in Social Media","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Social media; Set (abstract data type); Rank (graph theory); Key (lock); World Wide Web; Mathematics","score_opus":0.023657716101981644,"score_gpt":0.29482792920784595,"score_spread":0.2711702131058643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094256961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015967477,0.000024433226,0.9819817,0.00067731185,0.000032481377,0.000072919436,1.6282482e-7,0.00019887817,0.0010446361],"genre_scores_gemma":[0.71999735,0.000006251356,0.27968732,0.00017713902,0.00009023623,0.000012654926,8.919739e-7,0.000004692837,0.000023432878],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993282,0.00002816269,0.00015987318,0.00022869137,0.0000898871,0.00016516318],"domain_scores_gemma":[0.9994443,0.00030934048,0.000051368534,0.00013599145,0.000034595563,0.000024388097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029374022,0.000077418146,0.00015806223,0.00011173334,0.00009279033,0.00009476678,0.0002507978,0.000047457946,0.0000020295013],"category_scores_gemma":[0.00013050022,0.00006894114,0.000036511723,0.00018637872,0.00002871847,0.00046914758,0.00010316468,0.00006212936,7.597743e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025599065,0.000010982484,0.0052373568,0.000010566452,0.0000038420244,7.2792864e-7,0.0017507209,0.0000048317825,0.00079755514,0.41751492,0.00013227813,0.57453364],"study_design_scores_gemma":[0.0008115896,0.00008330493,0.021028588,0.000046756,0.000013575424,0.0000044395974,0.0002677487,0.08790894,0.020231562,0.8519528,0.017080192,0.00057049247],"about_ca_topic_score_codex":0.000020650994,"about_ca_topic_score_gemma":0.0012520751,"teacher_disagreement_score":0.7040299,"about_ca_system_score_codex":0.000018518815,"about_ca_system_score_gemma":0.000010276021,"threshold_uncertainty_score":0.2811338},"labels":[],"label_agreement":null},{"id":"W2096786223","doi":"10.1109/nafips.2004.1337433","title":"On the direct scaling approach of eliciting aggregated fuzzy information: the psychophysical view","year":2004,"lang":"en","type":"article","venue":"IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04.","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Scaling; Fuzzy logic; Operator (biology); Simple (philosophy); Computer science; Fuzzy set; Artificial intelligence; Mathematics","score_opus":0.010723362078098337,"score_gpt":0.2514054052676692,"score_spread":0.24068204318957084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096786223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20601241,0.0013386504,0.67504823,0.010550025,0.000999331,0.0031461923,0.00008488968,0.0016368836,0.10118341],"genre_scores_gemma":[0.9764609,0.000025094423,0.021876624,0.0014180251,0.00010797498,0.00006680582,0.000011151647,0.000016691067,0.000016752001],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99629587,0.00021006062,0.0015228465,0.0002443294,0.001251916,0.0004749755],"domain_scores_gemma":[0.9950208,0.00038199453,0.0022025038,0.0011096532,0.0012147229,0.00007030669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020506275,0.00037248203,0.0004653263,0.00026822547,0.0010348381,0.00037820314,0.0026758427,0.00013938399,0.000001150166],"category_scores_gemma":[0.0010224369,0.00020637692,0.00028046232,0.0026294128,0.00035768098,0.004857587,0.0002661582,0.00055054924,0.00002335937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013491308,0.00043827656,0.00015538254,0.0014964964,0.0003219056,8.427974e-7,0.08121504,0.44161415,0.0009856112,0.0756011,0.005145607,0.3928907],"study_design_scores_gemma":[0.0063982685,0.0010248126,0.0017424684,0.019520028,0.0008316784,0.00021717719,0.021518959,0.25730306,0.33647338,0.32874793,0.02159376,0.0046284976],"about_ca_topic_score_codex":0.00007654878,"about_ca_topic_score_gemma":0.0000024764981,"teacher_disagreement_score":0.77044845,"about_ca_system_score_codex":0.00013265121,"about_ca_system_score_gemma":0.00029388932,"threshold_uncertainty_score":0.8415806},"labels":[],"label_agreement":null},{"id":"W2097212070","doi":"10.3389/fpsyg.2015.01447","title":"Quantum structure of negation and conjunction in human thought","year":2015,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital","funders":"","keywords":"Conjunction (astronomy); Negation; Representation (politics); Set (abstract data type); Space (punctuation); Fuzzy set; Mathematics; Fuzzy logic; Computer science; Artificial intelligence; Theoretical computer science; Algebra over a field; Pure mathematics","score_opus":0.018490580233547427,"score_gpt":0.32598122085839437,"score_spread":0.30749064062484693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097212070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13250971,0.0003078903,0.86585534,0.00020022919,0.00045029714,0.00008126354,5.348986e-7,0.000036909973,0.0005578442],"genre_scores_gemma":[0.8083676,0.000023073673,0.19145711,0.000117821044,0.00001424582,0.0000029916232,0.0000025979962,0.0000036066822,0.000010979218],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923193,0.000090949514,0.00022094777,0.00025702585,0.00008317633,0.00011598114],"domain_scores_gemma":[0.9995361,0.000008795078,0.00010448761,0.00028604027,0.00003629892,0.00002826779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017365294,0.000070555914,0.00018607169,0.00038065593,0.000011863999,0.00000785973,0.00024073664,0.00009987596,0.0000011982175],"category_scores_gemma":[0.00002900975,0.00007028208,0.000014078965,0.0004588018,0.00008108869,0.00025682867,0.000046267847,0.00012532942,2.6748015e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011376533,0.00021851779,0.49149418,0.000027104492,0.000039395403,0.000021390813,0.0031812997,0.00021989059,0.033165712,0.14783742,0.049555775,0.27412555],"study_design_scores_gemma":[0.0010361832,0.00018024715,0.03574114,0.0000148522795,0.0000041287926,0.000009859835,0.00012476,0.010009917,0.0032255931,0.9469951,0.0025154625,0.00014279733],"about_ca_topic_score_codex":0.00002311422,"about_ca_topic_score_gemma":0.00005744162,"teacher_disagreement_score":0.7991577,"about_ca_system_score_codex":0.000036619997,"about_ca_system_score_gemma":0.000010626457,"threshold_uncertainty_score":0.28660202},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0271779675503826,"score_gpt":0.37800327637377823,"score_spread":0.35082530882339563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100784475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26870263,0.0029389346,0.6976633,0.014162864,0.00050089153,0.0009032972,0.000001962167,0.00089098344,0.014235108],"genre_scores_gemma":[0.9307705,0.00009638823,0.067732245,0.000067286135,0.000025731253,0.00014967973,8.590833e-7,0.0000051954594,0.0011520978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905175,0.00003691512,0.00023308801,0.00027253546,0.0001866706,0.00021903725],"domain_scores_gemma":[0.9993976,0.00008117341,0.00006297478,0.00033636967,0.000083513194,0.000038373622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010221081,0.00011210201,0.00018932314,0.00013679772,0.00009830178,0.000047554688,0.00035882974,0.000027090513,0.000019791107],"category_scores_gemma":[0.000107460444,0.0000895986,0.00005360205,0.00040672702,0.00008650868,0.0009947611,0.00030264698,0.00010899434,0.00022189251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005957179,0.0010627399,0.20043814,0.000029523073,0.00062515895,0.00007703651,0.020486306,0.0013858719,0.0014271026,0.49657866,0.057613634,0.22026987],"study_design_scores_gemma":[0.0017870147,0.0002249361,0.30807516,0.00021785055,0.000079107376,0.000009252465,0.007542364,0.0734346,0.0025380368,0.59842616,0.00597042,0.0016951088],"about_ca_topic_score_codex":0.00008388793,"about_ca_topic_score_gemma":0.00005312973,"teacher_disagreement_score":0.6620679,"about_ca_system_score_codex":0.00010100291,"about_ca_system_score_gemma":0.000013340317,"threshold_uncertainty_score":0.3653725},"labels":[],"label_agreement":null},{"id":"W2101145506","doi":"10.1002/meet.14504701412","title":"How hierarchical structures may influence the way that we think","year":2010,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hierarchy; Computer science; Task (project management); Hierarchical database model; Affect (linguistics); Hierarchical organization; Cognitive psychology; Psychology; Data mining; Communication; Engineering; Systems engineering; Political science","score_opus":0.008299225593631067,"score_gpt":0.261755658319421,"score_spread":0.25345643272578994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101145506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.878338,0.00002270524,0.03663254,0.08376792,0.00007699218,0.0005177923,0.0000041271833,0.00036452585,0.00027542582],"genre_scores_gemma":[0.8726134,0.00006586647,0.12619857,0.001052703,0.000010192909,0.000040670777,1.430744e-7,0.0000028126706,0.000015664435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986641,0.000001768574,0.0002024803,0.00022599507,0.0005736675,0.00033202305],"domain_scores_gemma":[0.9979421,0.00007558755,0.0006364587,0.000365538,0.00093381794,0.00004652863],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00088585826,0.00012753003,0.00018298524,0.00021086793,0.0007081079,0.000415561,0.0031497446,0.00007299661,2.2323276e-7],"category_scores_gemma":[0.0007192545,0.000069609494,0.00011935063,0.0033158306,0.0058844853,0.0041871313,0.0009380107,0.00040735368,3.7384586e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024766605,0.000005247199,0.0018424157,0.000017612923,0.000013121424,7.228336e-9,0.0018100176,0.0000012594917,0.06109738,0.7466041,0.0007199015,0.18788648],"study_design_scores_gemma":[0.0002706811,0.00022507067,0.008849455,0.00002296922,0.000032501048,0.00006566544,0.00943502,0.012877246,0.4223494,0.45403236,0.091442525,0.00039711266],"about_ca_topic_score_codex":0.000006124125,"about_ca_topic_score_gemma":0.0000010605448,"teacher_disagreement_score":0.361252,"about_ca_system_score_codex":0.000031317006,"about_ca_system_score_gemma":0.00009891068,"threshold_uncertainty_score":0.9968209},"labels":[],"label_agreement":null},{"id":"W2102724816","doi":"10.1109/kam.2009.191","title":"PH-SSBM: Phrase Semantic Similarity Based Model for Document Clustering","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"WordNet; Semantic similarity; Computer science; Natural language processing; Artificial intelligence; Document clustering; Explicit semantic analysis; Cluster analysis; Similarity (geometry); Phrase; Semantic computing; Representation (politics); tf–idf; Information retrieval; Semantic technology; Semantic Web; Term (time)","score_opus":0.024105504912120004,"score_gpt":0.3109896130239714,"score_spread":0.2868841081118514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102724816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000448107,0.000016806895,0.9949625,0.0025630556,0.000023835022,0.00030722507,9.954196e-7,0.0007347393,0.0009427223],"genre_scores_gemma":[0.51129574,0.000002204763,0.486501,0.0018479099,0.000012324228,0.00001858097,0.0000018179268,0.000004456565,0.00031592947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872625,0.00001902561,0.0002555507,0.00044776467,0.00022897153,0.0003224314],"domain_scores_gemma":[0.9989706,0.000048227284,0.000077497745,0.0007263096,0.00008496835,0.00009235198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027755834,0.00016720935,0.00021123822,0.00012806933,0.000119893855,0.00013215581,0.00071481266,0.000053003758,0.000010583292],"category_scores_gemma":[0.000031463445,0.00015065374,0.00014428288,0.00024428105,0.000015922606,0.0006437597,0.00012041277,0.0000803607,0.0000059710546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006392631,0.0006703825,0.00010820783,0.0000986631,0.000063575215,0.00003092124,0.0005396283,0.57760125,0.021630239,0.1614374,0.007136345,0.23061945],"study_design_scores_gemma":[0.00025629046,0.00006274786,0.000023181676,0.000010821347,0.000011715845,0.0000010008365,0.0000021185692,0.91308224,0.015620567,0.070536576,0.0002070255,0.00018569439],"about_ca_topic_score_codex":0.000007783573,"about_ca_topic_score_gemma":0.000058603124,"teacher_disagreement_score":0.5108476,"about_ca_system_score_codex":0.00008059021,"about_ca_system_score_gemma":0.000041803523,"threshold_uncertainty_score":0.6143481},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015531196943938437,"score_gpt":0.26695244195383044,"score_spread":0.251421245009892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106377293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018166952,0.00013518192,0.98350304,0.0003494426,0.000056039564,0.000036582,3.0155795e-7,0.00011192567,0.013990813],"genre_scores_gemma":[0.8916189,0.000031948228,0.105705194,0.00009513836,0.0000069757507,0.0000074363857,3.373897e-7,0.0000021292774,0.002531914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939847,0.000056598656,0.00014763781,0.00012585032,0.0001679679,0.00010348878],"domain_scores_gemma":[0.9991891,0.00014618796,0.000059469094,0.000477671,0.000105470135,0.000022149361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038670594,0.000046764042,0.000068750946,0.000021437427,0.000102225546,0.000021471871,0.0003883223,0.000016698868,0.000029658699],"category_scores_gemma":[0.00011731235,0.00002794542,0.00006023933,0.00031101366,0.00004614492,0.00016166984,0.000063380656,0.00003822061,0.000011605383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.890773e-7,0.000011750097,0.0017060657,5.537808e-7,0.000011632242,1.9868014e-7,0.000007995649,0.000019451192,0.0005170816,0.9907223,0.002194814,0.004807745],"study_design_scores_gemma":[0.0001474136,0.00005625165,0.014790717,0.0000038290846,0.000011638875,0.0000070989813,0.00004115133,0.0019244746,0.24560736,0.44287375,0.2943206,0.00021570829],"about_ca_topic_score_codex":0.000011006633,"about_ca_topic_score_gemma":0.000021523287,"teacher_disagreement_score":0.8898022,"about_ca_system_score_codex":0.000013659382,"about_ca_system_score_gemma":0.000023040056,"threshold_uncertainty_score":0.11395811},"labels":[],"label_agreement":null},{"id":"W2106900819","doi":"10.1109/hicss.2002.994040","title":"Adaptive user modeling for filtering electronic news","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Newspaper; Artificial neural network; User modeling; Task (project management); Quality (philosophy); User profile; Adaptive system; Test (biology); Information retrieval; Multimedia; Artificial intelligence; World Wide Web; User interface; Advertising; Engineering","score_opus":0.026812736624997772,"score_gpt":0.28011909598136164,"score_spread":0.25330635935636386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106900819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006622465,0.00006345292,0.9949962,0.00007421618,0.000021963637,0.00015672967,1.6048307e-7,0.00036902813,0.0036560223],"genre_scores_gemma":[0.42021814,0.000010628511,0.57902807,0.00015270499,0.000009038063,0.00003805868,2.8915008e-7,0.000006721077,0.00053637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909633,0.000019279472,0.00014569993,0.00030656872,0.00009573425,0.00033636342],"domain_scores_gemma":[0.9994424,0.000038815735,0.000035657038,0.0003774007,0.00006701935,0.000038730537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001416844,0.00010085636,0.000121871366,0.000076989985,0.0000739423,0.000054470256,0.0003853735,0.000031980315,0.000011812917],"category_scores_gemma":[0.000033090557,0.00009096665,0.000083902894,0.000217499,0.0000066194857,0.00051849784,0.000060292146,0.00007113471,0.0000079548345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021477927,0.000013865837,0.0000098211885,0.0000015817307,0.000016518727,4.7733636e-7,0.00004794556,0.012798211,0.0027967202,0.9750336,0.00017737548,0.009101765],"study_design_scores_gemma":[0.000094725554,0.0000589728,4.2411378e-7,0.0000033211768,0.0000045522615,0.0000022482416,0.000020192827,0.8310577,0.026669733,0.13643843,0.0055127414,0.00013691746],"about_ca_topic_score_codex":0.000014133307,"about_ca_topic_score_gemma":0.00004880556,"teacher_disagreement_score":0.83859515,"about_ca_system_score_codex":0.00007285502,"about_ca_system_score_gemma":0.000044871515,"threshold_uncertainty_score":0.37095124},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01949208080998927,"score_gpt":0.27803940768089846,"score_spread":0.2585473268709092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107363066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.784822,0.0001440299,0.18354918,0.029922642,0.0006996354,0.00035283488,0.0000059854715,0.00004813968,0.00045556534],"genre_scores_gemma":[0.99739075,0.000015768346,0.002541279,0.000024549698,0.0000042456913,0.0000035892117,2.7080142e-7,4.4591388e-7,0.000019118052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987477,0.000024588075,0.00043761253,0.000052274565,0.000612745,0.00012504458],"domain_scores_gemma":[0.99626356,0.00012025915,0.0010929886,0.00018267761,0.0023168528,0.000023656106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065061497,0.00003506287,0.000090461304,0.00038904438,0.00026987845,0.00022938687,0.00096509134,0.000044775676,4.6947626e-8],"category_scores_gemma":[0.00616389,0.000019142763,0.000024920848,0.0029343884,0.0003023293,0.0028773628,0.0001714522,0.00009491187,5.541735e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010107336,0.000024095885,0.024174416,0.0000038728367,0.000010502917,7.7285804e-8,0.0012214776,0.00012161344,0.0017037942,0.8908622,0.0013970718,0.08047076],"study_design_scores_gemma":[0.0010101944,0.0003006714,0.033652134,0.00005685765,0.000020785033,0.000025813362,0.0029722666,0.033906978,0.099305816,0.7704799,0.058117893,0.00015064597],"about_ca_topic_score_codex":0.000003212143,"about_ca_topic_score_gemma":0.000017314482,"teacher_disagreement_score":0.21256875,"about_ca_system_score_codex":0.00025753988,"about_ca_system_score_gemma":0.00035845127,"threshold_uncertainty_score":0.7379197},"labels":[],"label_agreement":null},{"id":"W2109753595","doi":"10.1109/lsp.2010.2048940","title":"Self-Organizing Maps for Topic Trend Discovery","year":2010,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Mitacs","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Visualization; Dimensionality reduction; Data mining; Information retrieval; Set (abstract data type); Data visualization; Process (computing); Latent semantic analysis; Curse of dimensionality; Artificial intelligence; Machine learning","score_opus":0.01012035866637828,"score_gpt":0.25203025302561993,"score_spread":0.24190989435924165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109753595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053148005,0.00003709009,0.94326615,0.002344093,0.00022556561,0.0001433171,0.0000020744305,0.00067933445,0.00015434872],"genre_scores_gemma":[0.6660002,0.00000102881,0.33184752,0.0017259719,0.0002903719,0.000028863582,0.000003062072,0.000020013244,0.00008298265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860483,0.000019406638,0.00025012827,0.0004999079,0.00024805524,0.00037769697],"domain_scores_gemma":[0.99925977,0.00008865373,0.0001610828,0.0003653646,0.00005454966,0.000070554626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021146804,0.00019689847,0.00020392865,0.00016666725,0.00026048426,0.00053151813,0.0008711763,0.00007259452,0.0000029303349],"category_scores_gemma":[0.00001591536,0.00018258556,0.0001084179,0.00040787188,0.000060139493,0.001759152,0.000074305375,0.0002756022,0.000005600524],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038041542,0.000045524124,0.00016137496,0.000075358774,0.000022297692,0.0000111540185,0.0004644052,0.000049252892,0.91510624,0.0015916142,0.0018072262,0.08066173],"study_design_scores_gemma":[0.00064286427,0.00009838337,0.00016692792,0.00008837896,0.00007847898,0.000044848934,0.000029551373,0.043949377,0.9122382,0.017262822,0.024397869,0.001002314],"about_ca_topic_score_codex":0.000003235865,"about_ca_topic_score_gemma":0.000009506071,"teacher_disagreement_score":0.6128522,"about_ca_system_score_codex":0.00004390914,"about_ca_system_score_gemma":0.000054679735,"threshold_uncertainty_score":0.7445623},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011818057569659177,"score_gpt":0.3080099634055263,"score_spread":0.2961919058358671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111310810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049689002,0.000008971912,0.98365414,0.000054825116,0.000023506134,0.0001228859,0.0000012388466,0.00011431187,0.011051208],"genre_scores_gemma":[0.58421797,0.000001050291,0.4157148,0.00001509806,0.0000059834565,0.000001907628,0.000013496626,8.2748204e-7,0.000028857268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989877,0.00004138542,0.00028357512,0.000088676665,0.0005252996,0.00007339815],"domain_scores_gemma":[0.99923396,0.00008570028,0.00011110817,0.00025749017,0.00029655086,0.000015201699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005499591,0.000045882483,0.00007830852,0.00012476921,0.000022396187,0.000034076067,0.00022250737,0.000029897861,0.000053527874],"category_scores_gemma":[0.00016884219,0.00003862924,0.000022257576,0.00034393714,0.000018462937,0.0012196783,0.00006668088,0.000033008986,0.000022991018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000945989,0.000036444264,0.00036239522,0.0000053138187,0.0000036632061,1.8996593e-7,0.000045344237,0.0008726837,0.002431027,0.7295376,0.002575831,0.26412],"study_design_scores_gemma":[0.00020611512,0.00007080677,0.015566173,0.0000063221414,0.000011023772,0.0000014246499,0.000005284544,0.5960891,0.069213584,0.31750527,0.0012333324,0.00009156233],"about_ca_topic_score_codex":0.000031093223,"about_ca_topic_score_gemma":0.0000044116036,"teacher_disagreement_score":0.5952164,"about_ca_system_score_codex":0.000043008444,"about_ca_system_score_gemma":0.00003480012,"threshold_uncertainty_score":0.15752546},"labels":[],"label_agreement":null},{"id":"W2111823757","doi":"10.1109/icccyb.2010.5491333","title":"A new search method for ranking short text messages using semantic features and cluster coherence","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Coherence (philosophical gambling strategy); Ranking (information retrieval); Information retrieval; Artificial intelligence; Semantic similarity; Measure (data warehouse); Natural language processing; Similarity (geometry); Non-negative matrix factorization; Cluster (spacecraft); Matrix decomposition; Data mining; Mathematics; Statistics; Image (mathematics)","score_opus":0.028520676570858695,"score_gpt":0.37075938864443203,"score_spread":0.3422387120735733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111823757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075958995,0.00008796517,0.9904669,0.00061029225,0.00006081059,0.00036661446,4.131659e-7,0.00025773194,0.00055340974],"genre_scores_gemma":[0.21003301,0.000005039096,0.78862846,0.00022404692,0.000052690742,0.000010602662,5.1169457e-7,0.0000114484565,0.0010341613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868405,0.000060121904,0.00018479559,0.00050927926,0.00024583598,0.00031589466],"domain_scores_gemma":[0.9988133,0.00039746944,0.000040668077,0.00052407733,0.00011285984,0.000111654444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000753819,0.000163789,0.0002483376,0.00016992739,0.00017442441,0.0003031698,0.0006419326,0.00009820306,0.00001936856],"category_scores_gemma":[0.00007442008,0.00013204978,0.00007565733,0.00033239662,0.000043169366,0.00060348434,0.0003986716,0.00025501117,0.0000012414993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014584491,0.000023851933,0.0015605298,0.000044829372,0.000065383916,0.0000058250107,0.00077121105,0.0001775188,0.27381754,0.044974867,0.0016145927,0.6769293],"study_design_scores_gemma":[0.00044497885,0.00007533915,0.0016871435,0.000053246982,0.00006827201,0.00016202992,0.00006442006,0.6814463,0.27167484,0.04254998,0.0012306338,0.0005428098],"about_ca_topic_score_codex":0.0002329595,"about_ca_topic_score_gemma":0.00038525966,"teacher_disagreement_score":0.68126875,"about_ca_system_score_codex":0.000015204976,"about_ca_system_score_gemma":0.00006575237,"threshold_uncertainty_score":0.5384834},"labels":[],"label_agreement":null},{"id":"W2114224956","doi":"10.1080/15326900701326600","title":"What Makes People Revise Their Beliefs Following Contradictory Anecdotal Evidence?: The Role of Systemic Variability and Direct Experience","year":2007,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomness; Element (criminal law); Generality; Psychology; Certainty; Action (physics); Social psychology; Cognitive psychology; Mathematics; Statistics","score_opus":0.014261907045873835,"score_gpt":0.29217931190000923,"score_spread":0.2779174048541354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114224956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79275537,0.0068813674,0.19844458,0.00007575218,0.0002367382,0.0005312778,0.000002245223,0.00015693913,0.0009157123],"genre_scores_gemma":[0.9967147,0.00039000966,0.002697519,0.000113596274,0.000029919123,0.00002877229,2.912292e-7,0.0000070589685,0.000018113491],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99718845,0.00022070392,0.00045274035,0.000894035,0.0007345537,0.0005095114],"domain_scores_gemma":[0.9956048,0.002693943,0.00028107475,0.0007533306,0.00050358835,0.00016324066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058795563,0.00022281075,0.000378723,0.00018686087,0.0005179728,0.0003565257,0.0015613579,0.000049727918,0.0000037575799],"category_scores_gemma":[0.002720674,0.00015319683,0.00012780902,0.0018554571,0.0014840806,0.0042290185,0.0005742333,0.00017150362,0.0000026455712],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039266786,0.00014907862,0.10479732,0.00007381719,0.00005526688,0.000028818276,0.08206338,0.000007583137,0.46178365,0.01223788,0.000004343826,0.3387596],"study_design_scores_gemma":[0.00045339126,0.00029159797,0.110747434,0.0044968026,0.000099804165,0.00014772006,0.041729685,0.012647501,0.8159996,0.012241347,0.00013521123,0.0010098676],"about_ca_topic_score_codex":0.000024957795,"about_ca_topic_score_gemma":0.000018448016,"teacher_disagreement_score":0.35421598,"about_ca_system_score_codex":0.00009875529,"about_ca_system_score_gemma":0.0001670604,"threshold_uncertainty_score":0.62471855},"labels":[],"label_agreement":null},{"id":"W2115756143","doi":"10.5430/ijhe.v2n4p172","title":"The Integrative Model of Behavior Prediction to Explain Technology Use in Post-graduate Teacher Education Programs in the Netherlands","year":2013,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Post graduate; Graduate education; Mathematics education; Graduate students; Psychology; Pedagogy; Medical education; Medicine","score_opus":0.03703895631413239,"score_gpt":0.3435336310024244,"score_spread":0.306494674688292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115756143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94951534,0.000119934724,0.034308206,0.014748227,0.0006520433,0.00048851065,9.950801e-7,0.00002050914,0.000146249],"genre_scores_gemma":[0.97538364,0.000031195763,0.023406094,0.0002498527,0.00010035323,0.00035077502,0.000006247168,0.0000069992184,0.0004648646],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985687,0.0001258389,0.00057571335,0.00015174267,0.00045505748,0.00012293241],"domain_scores_gemma":[0.9978025,0.00008261997,0.00044486418,0.0002744496,0.001363643,0.000031914504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004876705,0.00010946586,0.00012766791,0.0007125592,0.000034693676,0.00016764739,0.0012814637,0.000064160624,0.0000062828985],"category_scores_gemma":[0.0001286688,0.00006539822,0.00006339024,0.00060272013,0.000054741344,0.001154717,0.0000672524,0.0003207877,0.0000031832908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005467007,0.0030478465,0.14342165,0.0000033322967,0.000062487794,0.000002194534,0.010380539,0.0011268943,0.008105031,0.045097522,0.00406487,0.784633],"study_design_scores_gemma":[0.000664566,0.0007721731,0.83186376,0.0004660299,0.000054838165,0.00011745032,0.008350518,0.01726454,0.0038374541,0.13322599,0.003009073,0.00037358864],"about_ca_topic_score_codex":0.00024115767,"about_ca_topic_score_gemma":0.0001666753,"teacher_disagreement_score":0.7842594,"about_ca_system_score_codex":0.0002700153,"about_ca_system_score_gemma":0.00035842348,"threshold_uncertainty_score":0.2666862},"labels":[],"label_agreement":null},{"id":"W2116373577","doi":"10.1109/nafips.2004.1337356","title":"A fuzzy set approach to extracting keywords from abstracts","year":2004,"lang":"en","type":"article","venue":"IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04.","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Fuzzy set; Fuzzy logic; Relevance (law); Set (abstract data type); Vocabulary; Fuzzy clustering; Natural language processing; Data mining; Fuzzy classification; Natural language; Information retrieval; Cluster analysis; Linguistics","score_opus":0.01571152251035344,"score_gpt":0.2666254911786536,"score_spread":0.2509139686683001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116373577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2242788,0.00043089277,0.72123444,0.0018441621,0.0007382662,0.0010693752,0.00009954987,0.0014241991,0.04888035],"genre_scores_gemma":[0.74097407,0.0000046785112,0.25805795,0.000674674,0.00015378819,0.000039493607,0.00001765739,0.0000216336,0.000056082437],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9962065,0.00008960406,0.001458302,0.00046782295,0.0011284988,0.0006492542],"domain_scores_gemma":[0.9960985,0.00015256631,0.0015421908,0.0010445417,0.0009654464,0.00019672234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013586339,0.00041847271,0.0004816781,0.00042728643,0.00068415893,0.00051686383,0.0024777094,0.00020761191,0.0000011748677],"category_scores_gemma":[0.0009045027,0.00034462227,0.0002031804,0.0019584284,0.00012127018,0.006508441,0.000368699,0.0005284194,0.00006064488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119355194,0.00063304737,0.0012469153,0.00078567746,0.00024072798,0.000006999782,0.121626854,0.6606274,0.006344677,0.005133854,0.008825174,0.19440927],"study_design_scores_gemma":[0.007066388,0.00079281884,0.016424537,0.009722417,0.0006659336,0.0003647303,0.025879893,0.033761624,0.58606386,0.27308118,0.038582146,0.007594458],"about_ca_topic_score_codex":0.00048801012,"about_ca_topic_score_gemma":0.000024116109,"teacher_disagreement_score":0.6268658,"about_ca_system_score_codex":0.0002666527,"about_ca_system_score_gemma":0.00045452503,"threshold_uncertainty_score":0.9999006},"labels":[],"label_agreement":null},{"id":"W2117624436","doi":"","title":"Bike: Bilingual Keyphrase Experiments","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Machine translation; Information retrieval; Resource (disambiguation)","score_opus":0.01699604029499381,"score_gpt":0.30992152506400705,"score_spread":0.29292548476901326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117624436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0520646,0.000105720865,0.9089478,0.0011497653,0.00007805806,0.00010823023,6.795439e-7,0.00088168733,0.036663424],"genre_scores_gemma":[0.57166076,0.000007530862,0.427228,0.00036414978,0.000072715615,0.000008956658,6.686774e-7,0.0000056608383,0.00065152766],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902827,0.0000252681,0.00016839846,0.00031462862,0.00023808965,0.00022535773],"domain_scores_gemma":[0.99917406,0.00002758267,0.000054226282,0.00061935524,0.00004367378,0.00008108096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000118308344,0.000105559164,0.00011835991,0.00011167713,0.00006861287,0.000060048133,0.0007044833,0.000038161106,0.00015181342],"category_scores_gemma":[0.000031722764,0.00009722935,0.000062586674,0.00030364632,0.00003311612,0.00047622123,0.00021981212,0.000084953994,0.00020421745],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004189655,0.00020421985,0.00025770636,0.000002979564,0.000023902126,0.000025584237,0.0009338486,0.00006773233,0.3192408,0.09265462,0.0066305147,0.5799539],"study_design_scores_gemma":[0.00025664136,0.000055826935,0.00008711762,0.000009667771,0.000006004076,0.000010204665,0.000023770235,0.02802141,0.8680537,0.02750688,0.07567667,0.00029211753],"about_ca_topic_score_codex":0.0000024855683,"about_ca_topic_score_gemma":0.000004455404,"teacher_disagreement_score":0.5796618,"about_ca_system_score_codex":0.000058176967,"about_ca_system_score_gemma":0.00004086838,"threshold_uncertainty_score":0.3964898},"labels":[],"label_agreement":null},{"id":"W2118960523","doi":"10.1145/1242572.1242829","title":"Generating efficient labels to facilitate web accessibility","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Web page; Set (abstract data type); World Wide Web; Information retrieval; Static web page; Matching (statistics); Element (criminal law); Web navigation; Programming language","score_opus":0.04308156580098555,"score_gpt":0.32803185587840494,"score_spread":0.2849502900774194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118960523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26020142,0.00001738126,0.73368657,0.0002094252,0.000047967962,0.00012864963,6.5853357e-7,0.00057418173,0.005133741],"genre_scores_gemma":[0.5513293,4.5026803e-7,0.447574,0.0004981881,0.000015820548,0.0000053072185,3.4458728e-7,0.0000031063755,0.00057347375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838865,0.000034818873,0.00034297982,0.0005423389,0.00031316388,0.00037802462],"domain_scores_gemma":[0.9987154,0.0001082391,0.000056986257,0.00081795617,0.00013861513,0.0001627839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001242934,0.0001302056,0.00015753378,0.00016561065,0.00012526997,0.000120991295,0.0008930965,0.000038187653,0.000032459706],"category_scores_gemma":[0.00012691907,0.000107857486,0.000065356224,0.00089555903,0.00002371983,0.00026822204,0.00050386257,0.00009087627,0.0001066917],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009310236,0.00023915093,0.0034908452,0.000016232709,0.000028343235,0.000034537956,0.0016618106,0.01634955,0.42166856,0.042377427,0.0018549336,0.5122693],"study_design_scores_gemma":[0.00023855298,0.00011507459,0.00419351,0.000015160084,0.000006843135,0.000004859671,0.00006973219,0.55948126,0.4236478,0.003927251,0.0076924,0.00060754985],"about_ca_topic_score_codex":0.000028569515,"about_ca_topic_score_gemma":0.00011812663,"teacher_disagreement_score":0.5431317,"about_ca_system_score_codex":0.00009634388,"about_ca_system_score_gemma":0.000031372678,"threshold_uncertainty_score":0.43983006},"labels":[],"label_agreement":null},{"id":"W2122427912","doi":"10.1023/b:mind.0000045987.92742.71","title":"Inductive Reasoning and Chance Discovery","year":2004,"lang":"en","type":"article","venue":"Minds and Machines","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Surprise; Computer science; Inductive reasoning; Psychology of reasoning; Bayesian probability; Artificial intelligence; Theory of computation; Dilemma; Planner; Machine learning; Model-based reasoning; Epistemology; Psychology; Algorithm; Knowledge representation and reasoning; Philosophy","score_opus":0.005800492898316891,"score_gpt":0.25020309100197474,"score_spread":0.24440259810365786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122427912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4514436,0.000557095,0.54706395,0.00047145862,0.00002356645,0.000038193564,5.9292677e-7,0.00006169372,0.00033982674],"genre_scores_gemma":[0.89080364,0.00008880198,0.108813055,0.00010596469,0.000032841224,0.0000074328113,6.170091e-7,0.000003814607,0.00014385505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994966,0.000008726961,0.00007223174,0.00024448082,0.00006882752,0.00010915309],"domain_scores_gemma":[0.99973285,0.0000141737155,0.00004029288,0.00016070322,0.000016309872,0.000035681733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000649571,0.00008635088,0.00010885959,0.000059010035,0.00009195814,0.0001080862,0.00013321603,0.00002589596,4.98292e-7],"category_scores_gemma":[0.000018478051,0.000067928726,0.000017161112,0.00014079007,0.00005123873,0.00073113106,0.00017877165,0.00006568962,5.6304077e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007655053,0.0000570615,0.011119236,0.000018874925,0.000037023856,0.00002986042,0.0029902176,0.000034923094,0.010318214,0.33553815,0.00003610222,0.6398127],"study_design_scores_gemma":[0.0016059133,0.00046553917,0.13485838,0.00028420656,0.000058582384,0.00021608663,0.00025653717,0.0139724985,0.06399995,0.7790908,0.0038668837,0.001324616],"about_ca_topic_score_codex":0.00010424673,"about_ca_topic_score_gemma":0.000044127828,"teacher_disagreement_score":0.63848805,"about_ca_system_score_codex":0.000010780798,"about_ca_system_score_gemma":0.000010250952,"threshold_uncertainty_score":0.27700529},"labels":[],"label_agreement":null},{"id":"W2123409753","doi":"10.1111/0824-7935.00126","title":"Probability‐Based Chinese Text Processing and Retrieval","year":2000,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; University of Regina","keywords":"Weighting; Computer science; Artificial intelligence; Natural language processing; Probabilistic logic; Word (group theory); Text processing; Term (time); Focus (optics); Relevance (law); Pattern recognition (psychology); Speech recognition; Information retrieval; Mathematics","score_opus":0.027998545217532894,"score_gpt":0.31411299535793963,"score_spread":0.2861144501404067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123409753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03305197,0.00026670043,0.96474373,0.00054769655,0.000018068647,0.00015089397,0.0000011127307,0.00033837484,0.0008814767],"genre_scores_gemma":[0.63018155,0.0000068799313,0.36942968,0.00026180423,0.000018333387,0.000009620883,0.000003517037,0.0000054949364,0.00008312109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998622,0.00004888588,0.00030297795,0.00049819855,0.0003369371,0.00019097768],"domain_scores_gemma":[0.9991316,0.0002165204,0.000077463985,0.00027826708,0.00020796437,0.000088184104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023641122,0.00015998815,0.00016199758,0.00011220679,0.00016517015,0.00017759512,0.0005478349,0.00004681724,0.000119542594],"category_scores_gemma":[0.000092826594,0.00014224075,0.000050224757,0.00086374726,0.00015967932,0.0006164617,0.00008314145,0.00013417866,0.000053994274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021472142,0.00010617657,0.0012377301,0.000034004366,0.0000080176005,0.000008336348,0.00029841054,0.20094147,0.00006454538,0.018480787,0.000039743914,0.7787593],"study_design_scores_gemma":[0.00003313465,0.000035954392,0.002288854,0.000020817346,0.0000024942701,0.000011695916,0.0000022270317,0.7123978,0.00069242466,0.2840789,0.0002965295,0.00013914013],"about_ca_topic_score_codex":0.0000038326025,"about_ca_topic_score_gemma":0.0000017027854,"teacher_disagreement_score":0.7786202,"about_ca_system_score_codex":0.00004695488,"about_ca_system_score_gemma":0.00010133823,"threshold_uncertainty_score":0.58004093},"labels":[],"label_agreement":null},{"id":"W2128027916","doi":"","title":"University of Waterloo at TREC 2008 Blog track","year":2008,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Lexicon; Divergence (linguistics); Information retrieval; Natural language processing; Matching (statistics); Track (disk drive); Artificial intelligence; Polarity (international relations); Linguistics; Statistics; Mathematics","score_opus":0.030359246017418007,"score_gpt":0.23594040493848395,"score_spread":0.20558115892106593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128027916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68257105,0.0001644163,0.3077005,0.0003244411,0.0000662171,0.0001784209,0.000008178374,0.00050622865,0.008480538],"genre_scores_gemma":[0.96156996,0.0002946039,0.027450098,0.00003676345,0.00001263557,2.540736e-7,0.000004497569,0.00000753289,0.010623625],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985034,0.00008036894,0.00024218246,0.0004822871,0.00038691444,0.00030485942],"domain_scores_gemma":[0.9985029,0.000087117354,0.00019358678,0.0008049305,0.00028653748,0.00012492845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001675855,0.00017919378,0.0003451393,0.0001436591,0.00020434953,0.000016554191,0.0012956932,0.0001118573,0.00033241662],"category_scores_gemma":[0.00004183899,0.00017864237,0.00013585365,0.000658846,0.00034209827,0.0004514242,0.00042771947,0.0001713289,0.00016833509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013537076,0.0017034105,0.05193028,0.00024164774,0.0006142288,0.002528308,0.035905957,0.00019946172,0.48913866,0.2366367,0.021762175,0.15798545],"study_design_scores_gemma":[0.0025257366,0.001105144,0.04415562,0.00013816499,0.00012320427,0.00041769465,0.0003632955,0.03444808,0.8655317,0.020745624,0.028525086,0.0019206916],"about_ca_topic_score_codex":0.00014396421,"about_ca_topic_score_gemma":0.00007897935,"teacher_disagreement_score":0.376393,"about_ca_system_score_codex":0.00010070804,"about_ca_system_score_gemma":0.00013936035,"threshold_uncertainty_score":0.7284825},"labels":[],"label_agreement":null},{"id":"W2129647599","doi":"10.1145/2232817.2232852","title":"AckSeer","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; U.S. Air Force; Deutsche Forschungsgemeinschaft; National Aeronautics and Space Administration; U.S. Department of Energy; Office of the Dean for Research, Princeton University; National Science Foundation","keywords":"Computer science; Search engine indexing; Metadata; Information retrieval; Index (typography); Digital library; Gratitude; Information extraction; World Wide Web; Architecture","score_opus":0.012473141275657124,"score_gpt":0.27952524295426245,"score_spread":0.2670521016786053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129647599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001022082,0.000050596696,0.9338763,0.0002184569,0.000040630264,0.000017623743,1.8301396e-8,0.0004674597,0.06430685],"genre_scores_gemma":[0.5993162,0.0000013232581,0.39924955,0.00040435256,0.00002535883,0.0000026272924,7.584565e-8,0.0000014820279,0.0009990172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99963164,0.0000078658,0.000052700787,0.00007393778,0.000084007304,0.00014982125],"domain_scores_gemma":[0.9996067,0.000013680881,0.000014206148,0.00031085135,0.00001695146,0.000037556507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093284056,0.00003700043,0.000043210344,0.000037173464,0.000020729247,0.000019306517,0.00032826813,0.000014752424,0.0000387025],"category_scores_gemma":[0.000009125703,0.000028547234,0.000026127609,0.00017333978,0.000007930564,0.0007958041,0.00012496924,0.000028268307,0.00030871562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4472991e-7,0.000036821246,0.0037542984,6.6594316e-7,0.0000061466753,5.083197e-7,0.00012660574,7.401913e-7,0.007979497,0.9111002,0.007689648,0.06930472],"study_design_scores_gemma":[0.00011798749,0.000024544088,0.006241913,0.0000031124887,0.0000070425863,0.00001551532,0.0000153392,0.0066998936,0.46489742,0.058639947,0.46294576,0.00039153703],"about_ca_topic_score_codex":0.0000022885613,"about_ca_topic_score_gemma":7.938406e-7,"teacher_disagreement_score":0.85246027,"about_ca_system_score_codex":0.000010259962,"about_ca_system_score_gemma":0.000002822917,"threshold_uncertainty_score":0.39680177},"labels":[],"label_agreement":null},{"id":"W2131347559","doi":"10.4018/978-1-60960-625-1.ch004","title":"A Cognitive-Based Approach to Identify Topics in Text Using the Web as a Knowledge Source","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Meaning (existential); Identification (biology); Ambiguity; Representation (politics); Cluster analysis; Artificial intelligence; Knowledge extraction; Natural language processing; Information retrieval; Psychology","score_opus":0.053387598942272685,"score_gpt":0.32637386018812914,"score_spread":0.27298626124585645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131347559","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010739314,0.00015668402,0.44042453,0.00002286858,0.00006735682,0.0004755551,0.0000092144965,0.00020117842,0.5585352],"genre_scores_gemma":[0.7867155,0.000007012315,0.095456675,0.0030741598,0.0005091419,0.00022047998,0.0000074548716,0.00016118852,0.113848396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99754775,0.000084357525,0.00050838897,0.0009490286,0.00043352152,0.00047697936],"domain_scores_gemma":[0.9981249,0.00007571778,0.00027937195,0.0011119066,0.0002434949,0.00016458725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031739962,0.00052814954,0.0005723044,0.0002901244,0.00014771112,0.00022212215,0.0018820341,0.00036959173,0.000010284274],"category_scores_gemma":[0.000055739652,0.0004469492,0.00031119134,0.00017064328,0.00016482672,0.00011738364,0.00089385215,0.0005030935,0.00013104948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015841802,0.000046249897,0.000020966145,0.00002415053,0.000055897995,0.000028624683,0.00042428495,0.00002898213,0.000027554457,0.95864344,0.00017954051,0.04050445],"study_design_scores_gemma":[0.00094412535,0.00022333403,0.000077197066,0.0013333606,0.0002934854,0.000113275055,0.00006210683,0.01751582,0.00090596924,0.8783373,0.098132595,0.0020614269],"about_ca_topic_score_codex":0.00016270134,"about_ca_topic_score_gemma":0.00023119205,"teacher_disagreement_score":0.7866081,"about_ca_system_score_codex":0.00040284588,"about_ca_system_score_gemma":0.00047658762,"threshold_uncertainty_score":0.99979824},"labels":[],"label_agreement":null},{"id":"W2133556763","doi":"10.1007/3-540-47922-8_14","title":"Topic Discovery from Text Using Aggregation of Different Clustering Methods","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Measure (data warehouse); Clustering high-dimensional data; Data mining; Process (computing); Cluster (spacecraft); Vocabulary; Artificial intelligence; Correlation clustering; Machine learning; Information retrieval","score_opus":0.03332615904962769,"score_gpt":0.3142565827528983,"score_spread":0.2809304237032706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133556763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005633726,0.0005088438,0.9972793,0.000082899496,0.0006515499,0.00024059374,0.0000036559688,0.00013397752,0.00053583604],"genre_scores_gemma":[0.114498265,0.00007050322,0.88489693,0.00015767835,0.00019490365,0.000003591282,0.0000031527834,0.000024386687,0.00015059648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967445,0.000078543686,0.0007005264,0.0012930303,0.00076606387,0.00041731758],"domain_scores_gemma":[0.9969846,0.00060608075,0.0006005712,0.0015652173,0.00015743279,0.00008611187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042537102,0.00048486807,0.00076570566,0.00083990267,0.00013396244,0.00034318867,0.0025537333,0.00026306545,0.000020275482],"category_scores_gemma":[0.000086664426,0.00042649612,0.00021294653,0.0005386478,0.00042387322,0.0011370428,0.0017500048,0.00052338827,0.0000026567698],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018966433,0.000022638958,0.0000892818,0.000024046207,0.000019546493,0.0000136060935,0.00036157214,0.020896247,0.0037690157,0.0042142724,8.5066836e-7,0.970587],"study_design_scores_gemma":[0.00009476092,0.000053300773,0.000107358945,0.00047484413,0.000018563243,0.000008121784,9.316832e-8,0.7711266,0.03163757,0.19602147,0.000062840285,0.00039446098],"about_ca_topic_score_codex":0.000067129986,"about_ca_topic_score_gemma":0.000059083064,"teacher_disagreement_score":0.97019255,"about_ca_system_score_codex":0.00040861688,"about_ca_system_score_gemma":0.00009531182,"threshold_uncertainty_score":0.9998187},"labels":[],"label_agreement":null},{"id":"W2134878975","doi":"10.1016/j.ijinfomgt.2010.10.003","title":"Making functional units functional: The role of rhetorical structure in use of scholarly journal articles","year":2010,"lang":"en","type":"article","venue":"International Journal of Information Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reading (process); Computer science; Relevance (law); Set (abstract data type); Taxonomy (biology); Rhetorical question; Function (biology); Information retrieval; Linguistics; Political science","score_opus":0.032068415172043674,"score_gpt":0.2803225324927541,"score_spread":0.2482541173207104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134878975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14992785,0.000038742488,0.84756905,0.0009971743,0.0009421452,0.000090339214,0.0000052268974,0.000013419525,0.00041605262],"genre_scores_gemma":[0.93171906,0.00003339849,0.06791303,0.00020576375,0.00010136918,0.0000014339406,0.0000028200025,0.0000031473853,0.00001999877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99748325,0.00005272568,0.0010205688,0.000061904604,0.0012749807,0.00010654854],"domain_scores_gemma":[0.99608237,0.00011944255,0.0012999651,0.00018829376,0.0022707188,0.00003920786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077027944,0.00009453276,0.00014358103,0.00095920067,0.00005574284,0.00042018035,0.0009631556,0.00004807995,0.00006703802],"category_scores_gemma":[0.00032586275,0.00006783563,0.00010121829,0.0005950075,0.00005114801,0.008385329,0.00023374501,0.00051985047,0.0000024465937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018954196,0.00013109189,0.019332217,0.000016937096,0.00049111684,0.000016648373,0.0011676371,0.038257435,0.0068473965,0.5756335,0.0013082516,0.3566082],"study_design_scores_gemma":[0.0026559522,0.00026773047,0.4137266,0.00036422702,0.000104536324,0.0010474733,0.0019568852,0.07653589,0.023839457,0.27168226,0.20735818,0.00046081832],"about_ca_topic_score_codex":0.000005314826,"about_ca_topic_score_gemma":0.000009653084,"teacher_disagreement_score":0.7817912,"about_ca_system_score_codex":0.000106802894,"about_ca_system_score_gemma":0.00007875392,"threshold_uncertainty_score":0.60791606},"labels":[],"label_agreement":null},{"id":"W2137779158","doi":"10.3115/1654758.1654765","title":"A study of two graph algorithms in topic-driven summarization","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Automatic summarization; Computer science; Sentence; Graph; Natural language processing; Information retrieval; Artificial intelligence; Scope (computer science); Matching (statistics); Algorithm; Theoretical computer science; Mathematics","score_opus":0.012980108970599475,"score_gpt":0.29398154912421026,"score_spread":0.2810014401536108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137779158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15503186,0.000007717761,0.8423744,0.000036614878,0.000015876922,0.00015143548,1.1567521e-7,0.00012153293,0.0022604745],"genre_scores_gemma":[0.8232002,0.0000014983297,0.1765879,0.000015096502,0.000009938601,0.000012087018,0.0000011609243,0.0000024793303,0.00016959794],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992457,0.000039711493,0.00023694981,0.00020740309,0.00016801046,0.00010224542],"domain_scores_gemma":[0.99950564,0.000023431881,0.00006923883,0.00033630047,0.000053086183,0.00001230339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090510744,0.00006472341,0.0001321746,0.00024111736,0.000018570425,0.000019671284,0.00036819765,0.000018493954,0.000004304837],"category_scores_gemma":[0.000005400229,0.000057972233,0.000028645662,0.0008511878,0.000012506834,0.00029050556,0.00011728534,0.000043610486,0.0000013411691],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000298891,0.0021754024,0.5780965,0.0000073404203,0.0000280213,0.000044401095,0.0012952691,0.0099899005,0.003682664,0.33392882,0.00024580958,0.07050287],"study_design_scores_gemma":[0.0034184565,0.0008229674,0.28919438,0.000035565234,0.00003330046,0.0000054835823,0.00046517412,0.33216092,0.042561296,0.3302362,0.00030848556,0.000757785],"about_ca_topic_score_codex":0.0013072167,"about_ca_topic_score_gemma":0.0028404521,"teacher_disagreement_score":0.66816837,"about_ca_system_score_codex":0.000020736434,"about_ca_system_score_gemma":0.000008636313,"threshold_uncertainty_score":0.2364039},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.024613583411413936,"score_gpt":0.3336148891383208,"score_spread":0.30900130572690687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138954094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041185025,0.000024738376,0.9530451,0.002940278,0.000036834517,0.00047213084,4.1623366e-7,0.00048435235,0.0018110727],"genre_scores_gemma":[0.60765606,0.000008658535,0.39136338,0.00014544974,0.000023464243,0.00016345928,0.000003916133,0.000004881918,0.0006307636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998867,0.00004840355,0.0003539338,0.00035412822,0.00019216374,0.00018442226],"domain_scores_gemma":[0.99915177,0.00009365062,0.00020521347,0.00041221947,0.00008830085,0.00004886623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033791037,0.00012239243,0.00015565813,0.00023713279,0.000077028315,0.00009196351,0.00034977472,0.000055726727,0.00006631777],"category_scores_gemma":[0.000050613624,0.00011056416,0.00006086158,0.00044386557,0.000024522444,0.0014835733,0.000045812805,0.0000853126,0.00005019926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000126319155,0.00036187633,0.00031740422,0.000019101719,0.000025485628,0.0000030775789,0.005403575,0.00065998815,0.040710844,0.22991318,0.0049839118,0.7175889],"study_design_scores_gemma":[0.00039267004,0.000070725386,0.0012845754,0.000020676338,0.000007207837,0.000004262358,0.0004689286,0.9514095,0.01820568,0.020247782,0.007676095,0.00021187909],"about_ca_topic_score_codex":0.000010500662,"about_ca_topic_score_gemma":0.0003320111,"teacher_disagreement_score":0.9507495,"about_ca_system_score_codex":0.00029805294,"about_ca_system_score_gemma":0.000056555185,"threshold_uncertainty_score":0.45086756},"labels":[],"label_agreement":null},{"id":"W2139462516","doi":"10.7202/602712ar","title":"Le syntagme nominal : exemple d’un phénomène d’anticipation en lecture","year":2009,"lang":"fr","type":"article","venue":"Revue québécoise de linguistique","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Anticipation (artificial intelligence); Art; Philosophy; Computer science; Artificial intelligence","score_opus":0.010455044568281249,"score_gpt":0.28509243079679375,"score_spread":0.2746373862285125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139462516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010128334,0.0065320134,0.94328135,0.020754348,0.0006566704,0.0004911296,0.000015716525,0.0006532968,0.017487131],"genre_scores_gemma":[0.76952666,0.00045563266,0.22454014,0.0013986091,0.0018504778,0.000035035275,0.000022516671,0.000047875063,0.0021230446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963973,0.00045288008,0.0008331533,0.0010456779,0.0002993031,0.00097164616],"domain_scores_gemma":[0.99699974,0.0003551718,0.00048467235,0.0012970481,0.0005081588,0.00035523012],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008513754,0.0005518107,0.0007353917,0.0003267107,0.00035390636,0.00028567563,0.0012609363,0.00055428053,0.000060532868],"category_scores_gemma":[0.0016077035,0.0006913089,0.00039270328,0.00089818396,0.00012989815,0.0004496035,0.00016766519,0.0008848048,0.0000908811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038694907,0.00046575788,0.00019443718,0.00013576506,0.0000852342,0.00073894707,0.005599096,0.0019511544,0.0066176555,0.8427921,0.00050563517,0.14087553],"study_design_scores_gemma":[0.00076742156,0.00082773535,0.008434564,0.0011767821,0.0004344781,0.0010009982,0.00007235482,0.11414809,0.052717257,0.38201308,0.4364182,0.001989034],"about_ca_topic_score_codex":0.0105378395,"about_ca_topic_score_gemma":0.006799073,"teacher_disagreement_score":0.75939834,"about_ca_system_score_codex":0.0004861161,"about_ca_system_score_gemma":0.0011202185,"threshold_uncertainty_score":0.9995538},"labels":[],"label_agreement":null},{"id":"W2140061837","doi":"10.16995/dscn.253","title":"Toward Next Generation Text Analysis Tools: The Text Analysis Markup Language (TAML)","year":2005,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Markup language; Computer science; Interoperability; Standardization; World Wide Web; Vocabulary; Linguistics; XML","score_opus":0.05723028432510359,"score_gpt":0.29959740054323974,"score_spread":0.24236711621813617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140061837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16552006,0.0043171,0.8173743,0.0058616837,0.000078696125,0.00035549558,0.000033726483,0.0006499666,0.0058089816],"genre_scores_gemma":[0.99255925,0.0006834014,0.0037392848,0.0008202892,0.0003405229,0.00016021112,0.00011063852,0.000027085305,0.0015593376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968648,0.00016724295,0.0007333529,0.001013578,0.0006282829,0.0005927301],"domain_scores_gemma":[0.99722767,0.00035980254,0.0003734424,0.0015371059,0.00037191427,0.00013007474],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005838977,0.00048343337,0.00093105336,0.00070420996,0.00048155588,0.0012461754,0.0014962056,0.00012418855,0.00003155338],"category_scores_gemma":[0.00035008302,0.00035542506,0.0010010478,0.005776496,0.0002151706,0.0031247572,0.00090543285,0.00028116774,0.00008439317],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028617174,0.0006626916,0.005027474,0.00004183436,0.030526208,0.00010893062,0.26360738,0.025395324,0.00242293,0.0047687185,0.008908881,0.658501],"study_design_scores_gemma":[0.0013183707,0.00036994883,0.006631746,0.000057187866,0.00038092604,0.000046394023,0.32251,0.5388965,0.024144452,0.0073235803,0.09412208,0.0041988026],"about_ca_topic_score_codex":0.00009507903,"about_ca_topic_score_gemma":0.0016042304,"teacher_disagreement_score":0.8270392,"about_ca_system_score_codex":0.0002907596,"about_ca_system_score_gemma":0.000055249293,"threshold_uncertainty_score":0.9998898},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; 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","score_opus":0.20036793714287734,"score_gpt":0.3850923397812263,"score_spread":0.18472440263834897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140162241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06664888,0.00007596157,0.9314774,0.000038421644,0.00029422637,0.00014131174,0.0000020713671,0.00044541506,0.00087626715],"genre_scores_gemma":[0.55480254,0.0000030720614,0.4450245,0.000050520845,0.000012374585,0.000003334687,0.0000010514233,0.0000062903405,0.000096309035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773276,0.00007072586,0.00030025182,0.00058342825,0.00090902316,0.00040379516],"domain_scores_gemma":[0.9984842,0.00006259727,0.00023685933,0.0008169024,0.00019717048,0.00020230534],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0014503961,0.000154435,0.00018253864,0.0056326855,0.0002468751,0.00017071022,0.0014374069,0.00009159531,0.000027306176],"category_scores_gemma":[0.0009301903,0.0001457812,0.00010276734,0.029235197,0.00012419117,0.0011284503,0.0005025721,0.00017776723,0.000032558073],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009446847,0.0018646246,0.3969854,0.000044108485,0.000110020366,0.00007000408,0.010153784,0.0002472493,0.008101798,0.125403,0.0006532187,0.45635733],"study_design_scores_gemma":[0.00059774757,0.00017903237,0.3545432,0.000027531969,0.00007081143,0.000015265747,0.000116224415,0.52875143,0.090665884,0.021524392,0.0024248082,0.001083638],"about_ca_topic_score_codex":0.000073182295,"about_ca_topic_score_gemma":0.000011718475,"teacher_disagreement_score":0.5285042,"about_ca_system_score_codex":0.00024355153,"about_ca_system_score_gemma":0.00008151416,"threshold_uncertainty_score":0.9913989},"labels":[],"label_agreement":null},{"id":"W2141430397","doi":"10.1504/ijcat.2010.034534","title":"A schema for ontology-based concept definition and identification","year":2010,"lang":"en","type":"article","venue":"International Journal of Computer Applications in Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Schema (genetic algorithms); Information retrieval; Semantic Web; Ontology; World Wide Web","score_opus":0.01012021903614982,"score_gpt":0.31089422084601154,"score_spread":0.3007740018098617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141430397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02377857,0.00006397448,0.9709807,0.004608015,0.00022390253,0.00021310839,0.0000034274333,0.000098024924,0.000030296644],"genre_scores_gemma":[0.51767844,0.0000072149182,0.48207974,0.00009414175,0.000057308596,0.000073241084,0.0000045666366,0.0000036833708,0.0000016275458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99896836,0.0000143325715,0.0005188712,0.00022248563,0.00016496434,0.000111007386],"domain_scores_gemma":[0.9982849,0.0001835694,0.00047682397,0.00030516964,0.0007196447,0.000029937697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002697818,0.00009407037,0.00017516174,0.0010479692,0.00004387895,0.00006718738,0.0012510597,0.00014409966,0.0000018877632],"category_scores_gemma":[0.00007121287,0.000093772884,0.000063490595,0.0003791445,0.00016003753,0.00031609042,0.00011974208,0.0002827863,0.0000013552607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069908974,0.00013092239,0.0017443823,0.0000031292432,0.000029092203,0.0000031651657,0.000048520214,0.00007859201,0.01194215,0.79544675,0.00009066104,0.19047567],"study_design_scores_gemma":[0.0011591736,0.00014280756,0.0035365738,0.0000300649,0.000017447552,0.00023781114,0.000022259239,0.059057105,0.06629743,0.85563445,0.01365811,0.0002067923],"about_ca_topic_score_codex":0.0000014675952,"about_ca_topic_score_gemma":0.000013528313,"teacher_disagreement_score":0.49389988,"about_ca_system_score_codex":0.000049599494,"about_ca_system_score_gemma":0.00006478337,"threshold_uncertainty_score":0.3823947},"labels":[],"label_agreement":null},{"id":"W2142243548","doi":"10.48550/arxiv.1204.2847","title":"Segmentation Similarity and Agreement","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Segmentation; Similarity (geometry); Metric (unit); Computer science; Scale-space segmentation; Artificial intelligence; Edit distance; Pattern recognition (psychology); Image segmentation; Agreement; Segmentation-based object categorization; Image (mathematics)","score_opus":0.058679598677329574,"score_gpt":0.2023831825991733,"score_spread":0.1437035839218437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142243548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2222465,0.000033854714,0.7762801,0.000044302473,0.000029722623,0.00005783294,3.9252743e-7,0.000111501955,0.0011958006],"genre_scores_gemma":[0.97864276,0.000053715772,0.020834912,0.00011084917,0.000016171265,2.7067517e-7,0.0000012135938,0.0000026079242,0.00033749282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944913,0.00003851928,0.00006236285,0.00022832223,0.00004378676,0.00017785844],"domain_scores_gemma":[0.99949986,0.000027906657,0.000053977437,0.00029022925,0.000032347543,0.00009567679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014187292,0.00007698188,0.00007646001,0.000084207364,0.00009225034,0.00002369564,0.00025161763,0.000031168234,0.00001594228],"category_scores_gemma":[0.000007888119,0.000084383864,0.00003149292,0.00033256857,0.0000370415,0.0011247194,0.00021224689,0.00005774449,0.000024799607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006896298,0.00014051366,0.11626581,0.000010716072,0.000047012825,0.00002180115,0.00048039216,0.0009685861,0.0018082059,0.8699941,0.00032704644,0.009928923],"study_design_scores_gemma":[0.0020711364,0.00030921755,0.13951035,0.00004333054,0.00026092672,0.000026496964,0.0007541754,0.5126422,0.049468618,0.2840871,0.0090964455,0.0017300058],"about_ca_topic_score_codex":0.00001569658,"about_ca_topic_score_gemma":0.000008637782,"teacher_disagreement_score":0.75639623,"about_ca_system_score_codex":0.000067087596,"about_ca_system_score_gemma":0.000007220305,"threshold_uncertainty_score":0.34410742},"labels":[],"label_agreement":null},{"id":"W2147695060","doi":"10.13053/cys-17-2-1523","title":"A Knowledge-Base Oriented Approach for Automatic Keyword Extraction","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Polytechnique Montréal","funders":"","keywords":"Keyword extraction; Computer science; Information retrieval; Rank (graph theory); Novelty; Task (project management); Process (computing); Keyword density; Knowledge base; Artificial intelligence; Data mining; Natural language processing; Keyword search; Mathematics","score_opus":0.02112686952801224,"score_gpt":0.30501400958426567,"score_spread":0.28388714005625343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147695060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018387218,0.000033864857,0.98539376,0.00016466765,0.000057429017,0.00062740745,2.5269426e-7,0.0013447446,0.010539142],"genre_scores_gemma":[0.21743165,0.0000017182639,0.77902675,0.00007867815,0.000030232162,0.00054776744,0.000005251837,0.000009158048,0.0028687755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896,0.00003185872,0.00023747493,0.00037250115,0.00012852468,0.00026959658],"domain_scores_gemma":[0.9989143,0.00011161502,0.000093678456,0.000575621,0.00021416786,0.00009059788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019258707,0.00013063413,0.00016375078,0.00017055274,0.00010265325,0.000114807866,0.00046055173,0.000054812142,0.000064999054],"category_scores_gemma":[0.000073835094,0.00010648528,0.00010226554,0.0005425903,0.000025216661,0.0010403094,0.00010274486,0.00007331397,0.0001214126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028107,0.00069253234,0.00016258736,0.00008525843,0.000058230973,8.974875e-7,0.00044599347,0.00012717133,0.008873551,0.19452803,0.021334441,0.7736885],"study_design_scores_gemma":[0.00017208187,0.00005595444,0.0001951523,0.00000617776,0.00000987423,0.0000045187444,0.000034468572,0.97505116,0.011259587,0.009837141,0.003209993,0.00016391392],"about_ca_topic_score_codex":0.00002406124,"about_ca_topic_score_gemma":0.0000049988116,"teacher_disagreement_score":0.97492397,"about_ca_system_score_codex":0.00007512392,"about_ca_system_score_gemma":0.000035495083,"threshold_uncertainty_score":0.43423438},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.019390900814182644,"score_gpt":0.326621961672267,"score_spread":0.3072310608580843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148404145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009509153,0.00007545534,0.98896396,0.000092843875,0.000038157894,0.0001544137,5.577827e-7,0.00007890109,0.0010865476],"genre_scores_gemma":[0.60510147,0.000013738212,0.3947635,0.000030580206,0.000027400492,0.000001249332,0.0000018104953,0.0000032215971,0.00005703692],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923104,0.00006039278,0.00023046769,0.00024581098,0.00013548558,0.00009682238],"domain_scores_gemma":[0.9990905,0.00002273099,0.00023587373,0.0005343946,0.000092225695,0.000024297002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020611499,0.00008584302,0.0001923725,0.0000784545,0.00003515889,0.000022925162,0.0003560932,0.00002334645,0.000014786297],"category_scores_gemma":[0.00011601655,0.00006362198,0.000047659312,0.00033646883,0.000036028538,0.0006262644,0.00008728488,0.00006171958,0.000002099888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032543742,0.00007364931,0.0021908423,0.00006536068,0.00002829654,6.1280207e-7,0.00038824562,0.0019374597,0.3085596,0.17161568,0.0004678043,0.5146692],"study_design_scores_gemma":[0.00014661497,0.000066607674,0.0034852964,0.000097731696,0.000051296538,0.0000069073394,0.000022113016,0.1606044,0.76110345,0.06768873,0.0063082343,0.00041863933],"about_ca_topic_score_codex":0.000024249746,"about_ca_topic_score_gemma":0.000018218985,"teacher_disagreement_score":0.5955923,"about_ca_system_score_codex":0.000021373735,"about_ca_system_score_gemma":0.000015836347,"threshold_uncertainty_score":0.25944287},"labels":[],"label_agreement":null},{"id":"W2148945625","doi":"10.19173/irrodl.v14i1.1389","title":"Automatic evaluation for e-learning using latent semantic analysis: A use case","year":2013,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitat Oberta de Catalunya; European Commission","keywords":"Animal science; Biology","score_opus":0.184779399202003,"score_gpt":0.4953805839448462,"score_spread":0.31060118474284315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148945625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3604336,0.0051700026,0.62793815,0.0033008708,0.00003136659,0.0028915736,0.0000075457006,0.00005762476,0.00016925123],"genre_scores_gemma":[0.97857684,0.0019177771,0.019037047,0.000056193723,0.000010482232,0.0002935623,0.000059791306,0.0000059940585,0.000042293235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972741,0.000936923,0.0004801011,0.00030488858,0.0007722987,0.00023170158],"domain_scores_gemma":[0.99682873,0.0013418192,0.0002779896,0.00031042873,0.0011851636,0.000055865243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008460557,0.00009813916,0.00031292826,0.00038361584,0.00023642191,0.0005541602,0.0010749237,0.000029474371,0.000107239204],"category_scores_gemma":[0.0043330975,0.00007029172,0.0001022628,0.0015921394,0.00007424079,0.0010265352,0.0008706251,0.00036099905,0.000004119284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004165457,0.00040830424,0.11421492,0.0031935868,0.0019288161,0.00016121646,0.00094825524,0.06754012,0.0012640725,0.029816244,0.0009941136,0.7794887],"study_design_scores_gemma":[0.00022370876,0.000039278013,0.002897774,0.0017383648,0.00009712391,0.000047506885,0.00022403034,0.99107885,0.00004221894,0.003179839,0.0003530491,0.00007826633],"about_ca_topic_score_codex":0.0012066473,"about_ca_topic_score_gemma":0.00003363462,"teacher_disagreement_score":0.92353874,"about_ca_system_score_codex":0.00017659806,"about_ca_system_score_gemma":0.00010894823,"threshold_uncertainty_score":0.53437793},"labels":[],"label_agreement":null},{"id":"W2149120305","doi":"10.21437/interspeech.2007-66","title":"The voice-rate dialog system for consumer ratings","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dialog box; Phone; Computer science; Dialog system; Product (mathematics); Matching (statistics); Speech recognition; Key (lock); Quarter (Canadian coin); World Wide Web; Computer security","score_opus":0.0127989999599461,"score_gpt":0.28152221592549637,"score_spread":0.26872321596555027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149120305","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006145105,0.00008824714,0.98880136,0.00038102557,0.00013563156,0.0002543107,4.2576255e-7,0.00062883546,0.009095676],"genre_scores_gemma":[0.71414435,0.0000076975475,0.28352594,0.00031903997,0.00005883947,0.00004836721,7.428396e-7,0.0000086157415,0.0018863988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990707,0.000029641213,0.00025359401,0.00023622035,0.00012344157,0.0002863873],"domain_scores_gemma":[0.99831253,0.00085554965,0.00011256883,0.00051943347,0.0001487586,0.000051138053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013930937,0.00009318114,0.00011817605,0.00004665601,0.00030868713,0.00014861026,0.00071570824,0.00003695424,9.568738e-7],"category_scores_gemma":[0.00011533549,0.000056489716,0.00007911373,0.00025428072,0.00005120837,0.00024301781,0.00011738752,0.00005858879,0.000035620076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008118089,0.000012285624,0.000255128,0.000014096191,0.000033246808,0.000004531279,0.00012130669,0.0000064924798,0.006498268,0.9030954,0.0040770224,0.0858741],"study_design_scores_gemma":[0.000888215,0.00021118873,0.0012180237,0.000060702256,0.00006188223,0.000030647814,0.00038378168,0.095197216,0.5307647,0.073482804,0.2968054,0.0008954337],"about_ca_topic_score_codex":0.000018645469,"about_ca_topic_score_gemma":0.00010447982,"teacher_disagreement_score":0.8296126,"about_ca_system_score_codex":0.00004859415,"about_ca_system_score_gemma":0.000020855487,"threshold_uncertainty_score":0.2374203},"labels":[],"label_agreement":null},{"id":"W2149639484","doi":"","title":"Clustering Voices in The Waste Land","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Task (project management); Computer science; Cluster (spacecraft); Segmentation; Artificial intelligence; Natural language processing; Engineering","score_opus":0.01142973882149155,"score_gpt":0.2595858226516054,"score_spread":0.24815608383011384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149639484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027405046,0.000025442441,0.95699304,0.0015774916,0.000016067035,0.00009834256,2.4110188e-8,0.000121967874,0.013762548],"genre_scores_gemma":[0.9026618,0.0000056414447,0.096348524,0.00062064745,0.000016238955,0.00002563124,1.2648663e-7,0.0000018134685,0.0003195596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953485,0.000028146307,0.00009144632,0.00012561232,0.00010515136,0.00011481893],"domain_scores_gemma":[0.9995504,0.000056246612,0.000023084693,0.000340902,0.000016067725,0.000013296331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013852038,0.000047696743,0.000057176774,0.00005534991,0.00002882618,0.00013307207,0.00074552465,0.000014761511,0.000022465296],"category_scores_gemma":[0.000008721181,0.000026800937,0.000020248437,0.00024801935,0.000011318388,0.0005637053,0.00015716956,0.00005586347,0.00007102844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003384954,0.00028464873,0.08345688,0.000048509406,0.00005351058,0.000059464983,0.01024758,0.0077135935,0.00796112,0.11113634,0.017444309,0.76159066],"study_design_scores_gemma":[0.00014702496,0.000029921352,0.008775793,0.000015538219,0.0000025538855,0.000010171647,0.00028319668,0.9485518,0.0036193803,0.035090607,0.003257301,0.00021671802],"about_ca_topic_score_codex":0.00026227866,"about_ca_topic_score_gemma":0.00039507824,"teacher_disagreement_score":0.9408382,"about_ca_system_score_codex":0.000007941944,"about_ca_system_score_gemma":0.000003268536,"threshold_uncertainty_score":0.13853827},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Factorial experiment; Mathematics; Statistics; Computer science; Artificial intelligence","score_opus":0.016361447109000178,"score_gpt":0.31600834063477085,"score_spread":0.2996468935257707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150630862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86972797,0.00013523364,0.09049683,0.0034828954,0.0034852019,0.0009652104,0.000008972474,0.0013165924,0.030381063],"genre_scores_gemma":[0.97473294,0.0000147098035,0.023875576,0.00031107446,0.000284113,0.00008233158,0.0000029902594,0.000013365457,0.00068291323],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99874467,0.00004286963,0.00020565838,0.00036188104,0.00037044653,0.00027446685],"domain_scores_gemma":[0.9988342,0.00003239697,0.00009802637,0.00093099463,0.000023188857,0.00008118291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017713723,0.00017588398,0.00015636288,0.000053935404,0.00020374861,0.0001387524,0.0011344575,0.00005990662,0.00024052389],"category_scores_gemma":[0.000006302678,0.00012152915,0.00011337397,0.00016784795,0.00010261707,0.00038730403,0.0004584637,0.000213906,0.00010020235],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012556984,0.000087911685,0.00004244703,8.165018e-7,0.000021737565,0.0000026215143,0.005688558,2.502804e-7,0.92801976,0.05740183,0.0025036908,0.006217807],"study_design_scores_gemma":[0.0002501748,0.00009138152,0.000051065945,0.00000365988,0.0000049675205,0.000006652485,0.00012437084,0.0008806179,0.9745613,0.006755418,0.017101724,0.00016870904],"about_ca_topic_score_codex":0.00014756521,"about_ca_topic_score_gemma":0.000014915188,"teacher_disagreement_score":0.10500493,"about_ca_system_score_codex":0.00008462057,"about_ca_system_score_gemma":0.000031564334,"threshold_uncertainty_score":0.49558148},"labels":[],"label_agreement":null},{"id":"W2151674174","doi":"","title":"Multilabel Subject-Based Classification of Poetry","year":2015,"lang":"en","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Poetry; Computer science; Latent Dirichlet allocation; Artificial intelligence; Context (archaeology); Support vector machine; Set (abstract data type); Style (visual arts); Subject (documents); Natural language processing; Task (project management); Machine learning; Simple (philosophy); Pattern recognition (psychology); Topic model; Linguistics; World Wide Web; Literature; Engineering; Art","score_opus":0.017192345718264498,"score_gpt":0.23033702888413238,"score_spread":0.21314468316586788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151674174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38191718,0.0007003664,0.5011151,0.009633941,0.0001877722,0.0014154568,0.00022013388,0.0012986694,0.10351136],"genre_scores_gemma":[0.9786014,0.00013539109,0.013805568,0.0009823003,0.000054417433,0.000007886979,0.0001188289,0.00007414419,0.0062200576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596465,0.00041496436,0.0005058551,0.0012281347,0.00084131246,0.0010450656],"domain_scores_gemma":[0.9953988,0.0006607035,0.0007150607,0.0015830711,0.0006874733,0.0009548627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007174124,0.00073823036,0.00093118905,0.001569652,0.00095117954,0.00095147785,0.004685605,0.00045903798,0.000048449147],"category_scores_gemma":[0.0002759276,0.0007534347,0.0004679243,0.0032813756,0.0010334102,0.0027253628,0.0036290425,0.0005937907,0.00003742406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045074727,0.0005787247,0.015992282,0.00017827371,0.00059315417,0.000997239,0.067161,0.0021980114,0.0018410725,0.86986876,0.0054892786,0.030594733],"study_design_scores_gemma":[0.02301098,0.00171083,0.04753514,0.00061921444,0.0012238066,0.00055427116,0.013043978,0.14979434,0.023067832,0.046392154,0.6876598,0.005387663],"about_ca_topic_score_codex":0.00063648657,"about_ca_topic_score_gemma":0.00008788687,"teacher_disagreement_score":0.8234766,"about_ca_system_score_codex":0.0019374278,"about_ca_system_score_gemma":0.0007553437,"threshold_uncertainty_score":0.9994917},"labels":[],"label_agreement":null},{"id":"W2152267628","doi":"10.1109/grc.2006.1635894","title":"The STP model for solving imprecise problems","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Matching (statistics); Process (computing); Optimization problem; Problem statement; Mathematical optimization; Mathematics; Algorithm; Management science","score_opus":0.014803621059243415,"score_gpt":0.2621537197575264,"score_spread":0.24735009869828298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152267628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001893064,0.00010324074,0.9947662,0.0006030536,0.000022498094,0.00024250164,4.4742498e-7,0.00044692605,0.0036258274],"genre_scores_gemma":[0.33287835,0.00001200529,0.65964675,0.00008655026,0.00002906974,0.00012148946,7.970886e-7,0.000007466799,0.007217542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920857,0.0000061940805,0.00017964651,0.0002307582,0.00013610358,0.00023869904],"domain_scores_gemma":[0.99918425,0.00012727852,0.00006278473,0.000510592,0.00009266752,0.000022438924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025410275,0.00008223017,0.000083254876,0.00003618454,0.00024985863,0.00018046795,0.000800788,0.0000271195,9.942154e-7],"category_scores_gemma":[0.000019049683,0.00005098839,0.00008161011,0.00016265901,0.000026016154,0.0003941077,0.00016468026,0.000046516805,0.000004169681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017867025,0.000034129473,0.000043139185,0.000005013994,0.000009153561,2.9497528e-7,0.000083456776,0.035615228,0.006014696,0.85806644,0.010748126,0.08937852],"study_design_scores_gemma":[0.0000409411,0.000008188942,0.0000075337157,0.0000018393323,0.0000020368466,3.9741002e-7,0.000001663277,0.68400896,0.0041476446,0.30966458,0.0020581228,0.000058093257],"about_ca_topic_score_codex":0.000027079526,"about_ca_topic_score_gemma":0.00018178746,"teacher_disagreement_score":0.64839375,"about_ca_system_score_codex":0.000029457446,"about_ca_system_score_gemma":0.000023346654,"threshold_uncertainty_score":0.20792462},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.040886315015554765,"score_gpt":0.28119789087673647,"score_spread":0.2403115758611817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153207410","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000686855,0.0039852266,0.8540983,0.0002580994,0.00001736717,0.00005310471,2.6765553e-8,0.0005706573,0.1410103],"genre_scores_gemma":[0.012838268,0.0050222827,0.9745328,0.00606633,0.00000959176,0.00001366245,2.2832221e-7,0.000004537333,0.0015123268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995361,0.0000140831335,0.0001119503,0.00016554465,0.00007313144,0.00009917752],"domain_scores_gemma":[0.9993274,0.000007264055,0.000034172055,0.00055741606,0.000037426107,0.000036329973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011757669,0.00005399183,0.000097530574,0.000036801026,0.00002008614,0.000008297684,0.0006557313,0.0000131202505,0.0002528748],"category_scores_gemma":[0.000014172285,0.000039803217,0.000050258965,0.00029183182,0.0000116136725,0.0003403831,0.00013819776,0.000035107852,0.00029730872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6695056e-7,0.000038533388,0.00014780769,0.000052829495,0.000010141353,0.000011524965,0.00007056102,2.47899e-8,0.00015878495,0.78488094,0.044874486,0.16975412],"study_design_scores_gemma":[0.000099213175,0.00009389287,0.0010609096,0.0005984436,0.00003309425,0.000038904178,0.0000035217172,0.0010853711,0.08161593,0.22362198,0.69116926,0.0005794518],"about_ca_topic_score_codex":0.000008533242,"about_ca_topic_score_gemma":0.000002526447,"teacher_disagreement_score":0.6462948,"about_ca_system_score_codex":0.00000803016,"about_ca_system_score_gemma":0.0000073110427,"threshold_uncertainty_score":0.38214013},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.013367564952236293,"score_gpt":0.24368251737275914,"score_spread":0.23031495242052286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161427841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07226845,0.000032120835,0.9253579,0.00046629237,0.00021114189,0.0002940832,0.000018889226,0.0001294875,0.0012216306],"genre_scores_gemma":[0.76673037,0.000002116247,0.23304176,0.00005520412,0.00006129601,0.0000057758175,0.000008838416,0.000005578057,0.000089050984],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998931,0.00006599862,0.0002368311,0.000188357,0.00045778154,0.000120025135],"domain_scores_gemma":[0.99629694,0.0018564148,0.00056423567,0.000132519,0.0011248821,0.000025014782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005475976,0.00008702647,0.00015575516,0.000064769236,0.00036617054,0.000028048758,0.00023278751,0.00004476954,2.6889884e-7],"category_scores_gemma":[0.0047084196,0.00007067721,0.000061153245,0.00024367787,0.00005630504,0.00006903361,0.00010414114,0.00007745086,4.074625e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036087247,0.00010572252,0.6116477,0.000052736876,0.0001581404,0.000001944237,0.0006961052,0.070892565,0.00025738848,0.31483656,0.00085511,0.00045989355],"study_design_scores_gemma":[0.0013151745,0.00020750951,0.2991844,0.0001450173,0.00010556375,0.000018357006,0.00003321941,0.51260924,0.0061377236,0.1761356,0.003662907,0.00044528788],"about_ca_topic_score_codex":0.000016009984,"about_ca_topic_score_gemma":0.000007850972,"teacher_disagreement_score":0.69446194,"about_ca_system_score_codex":0.00014413641,"about_ca_system_score_gemma":0.00011173052,"threshold_uncertainty_score":0.5636758},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.021402194804987354,"score_gpt":0.289623304492584,"score_spread":0.26822110968759666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163284121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03200971,0.00079479173,0.9646885,0.00008066866,0.00004534854,0.00038258135,0.000003342393,0.000028664563,0.001966401],"genre_scores_gemma":[0.99752927,0.000264215,0.0020713622,0.000011878543,0.000010436104,0.000026450447,0.0000018393289,0.0000022766794,0.00008226526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983367,0.00013525497,0.0009397232,0.00007888584,0.0003980218,0.000111460344],"domain_scores_gemma":[0.99798286,0.00026979184,0.00089781714,0.00017790697,0.0006363121,0.000035318553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009924205,0.00009335287,0.00026765553,0.0012028031,0.0001054214,0.00041142787,0.00030264052,0.000027571486,0.0000016480378],"category_scores_gemma":[0.00006087607,0.000066357694,0.000086141175,0.0015840335,0.00003762794,0.0034205683,0.00002755193,0.00009403218,0.0000023960217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013299329,0.00028542947,0.0076268334,0.0009166214,0.0026245757,0.000016581978,0.034991268,0.8032353,0.0000056662334,0.04645509,0.0003626401,0.10334702],"study_design_scores_gemma":[0.0008654243,0.000114928494,0.008270774,0.00082061323,0.00040800608,0.000017506523,0.034123152,0.9497358,0.000054195843,0.00011829252,0.00526869,0.00020260262],"about_ca_topic_score_codex":0.000020953821,"about_ca_topic_score_gemma":0.000011308834,"teacher_disagreement_score":0.96551955,"about_ca_system_score_codex":0.00009027639,"about_ca_system_score_gemma":0.000031148207,"threshold_uncertainty_score":0.39674085},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.02853358991606894,"score_gpt":0.3131675310217468,"score_spread":0.28463394110567786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163490678","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16034608,0.0000073642354,0.8388078,0.00004889977,0.000013976692,0.00015019011,0.0000070346596,0.0001349226,0.0004837282],"genre_scores_gemma":[0.48870075,0.000012273224,0.5110304,0.000020418845,0.000011968304,0.000011171409,0.0000070524366,0.0000049556097,0.00020103481],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927723,0.000034091772,0.00022323571,0.00019800251,0.00016374614,0.00010371603],"domain_scores_gemma":[0.9990458,0.00014133734,0.00014461204,0.00047064034,0.00016341514,0.00003420334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013192395,0.00007330809,0.0001457793,0.000095124036,0.000037356684,0.000021895587,0.00026881788,0.000047765403,0.00010393093],"category_scores_gemma":[0.0000977303,0.00006947477,0.00006615898,0.00026011065,0.000035645007,0.0010504733,0.000019551693,0.000040487328,0.000002403457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003112592,0.00013226758,0.00020050518,0.000013316911,0.000011528983,8.807249e-7,0.00018147245,0.00047755233,0.08185988,0.0047173533,0.00014757103,0.91222656],"study_design_scores_gemma":[0.0002972839,0.00040300476,0.0030989193,0.00003794174,0.00004315684,0.0000063368307,0.000015238402,0.10556589,0.79105973,0.09201366,0.007239498,0.00021931958],"about_ca_topic_score_codex":0.00002741661,"about_ca_topic_score_gemma":0.000012278776,"teacher_disagreement_score":0.9120072,"about_ca_system_score_codex":0.000022737024,"about_ca_system_score_gemma":0.000021715985,"threshold_uncertainty_score":0.28330988},"labels":[],"label_agreement":null},{"id":"W2163630478","doi":"10.1007/978-3-642-04346-8_20","title":"Chance Encounters in the Digital Library","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Novelty; Computer science; Digital library; Interface (matter); Focus (optics); Human–computer interaction; Value (mathematics); Data science; World Wide Web; Machine learning; Psychology","score_opus":0.009265452476631342,"score_gpt":0.23472269564367335,"score_spread":0.225457243167042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163630478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003234288,0.00048824705,0.98296803,0.0022553517,0.00026426924,0.0003512202,0.0000051170364,0.00030030534,0.013335135],"genre_scores_gemma":[0.4237113,0.00024768655,0.5624597,0.011985678,0.0006067092,0.000027104907,0.000017610326,0.00005989061,0.0008842979],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99623084,0.000038275037,0.0005357615,0.0014483556,0.0010844376,0.0006623129],"domain_scores_gemma":[0.9972105,0.00049266225,0.00027623537,0.0018737952,0.00005957112,0.0000872368],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006058257,0.0005276175,0.0004973608,0.0010467133,0.00015025833,0.0013845284,0.007400215,0.00023878993,0.000010160899],"category_scores_gemma":[0.00006213629,0.00039288317,0.00016695666,0.0013901221,0.0005880933,0.0024556322,0.0011214649,0.0010140109,0.000038284565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024494705,0.00002956148,0.000058261758,0.000007392696,0.0000035351507,0.00017845139,0.0005464824,0.0025225626,0.000014096372,0.021149924,0.00006807919,0.9754192],"study_design_scores_gemma":[0.00018542886,0.00022818866,0.00025992646,0.00049588346,0.000005776389,0.000113110655,4.4750587e-7,0.14279717,0.0008816283,0.83637655,0.01766717,0.0009886889],"about_ca_topic_score_codex":0.0000035508795,"about_ca_topic_score_gemma":0.000022319407,"teacher_disagreement_score":0.9744305,"about_ca_system_score_codex":0.00017713019,"about_ca_system_score_gemma":0.0002750218,"threshold_uncertainty_score":0.9998523},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.1082659095785678,"score_gpt":0.424850168063926,"score_spread":0.3165842584853582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169142063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21495397,0.000177129,0.7828961,0.001651909,0.000049526996,0.00013543857,8.147802e-8,0.000011412539,0.0001244048],"genre_scores_gemma":[0.8893526,0.00022837993,0.110312805,0.000026162365,0.000050243845,0.000007254876,1.3010883e-7,0.0000031377267,0.000019244195],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857366,0.00016097615,0.00046214083,0.00013560754,0.00044700276,0.00022060056],"domain_scores_gemma":[0.99868536,0.00033001683,0.000120939345,0.00015596033,0.00062738115,0.00008034636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014832333,0.000056077577,0.00012926375,0.00061737647,0.00009331142,0.0002190246,0.0004075541,0.00003963238,0.000054873683],"category_scores_gemma":[0.00033087758,0.000049506623,0.000032053413,0.000753769,0.00009904255,0.0010674554,0.000115013645,0.00035483687,0.00003760059],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050794783,0.00009118294,0.0016658598,0.000009693793,0.000012905411,0.000021459484,0.0020881363,0.00059849734,0.049458023,0.0401774,0.00006379978,0.905808],"study_design_scores_gemma":[0.00005879125,0.00043670638,0.0018083883,0.000096507196,0.000004935979,0.00003980524,0.003578268,0.16953956,0.28077537,0.543384,0.00011159923,0.00016607049],"about_ca_topic_score_codex":0.00014920614,"about_ca_topic_score_gemma":0.00006485697,"teacher_disagreement_score":0.9056419,"about_ca_system_score_codex":0.00013642163,"about_ca_system_score_gemma":0.000098161196,"threshold_uncertainty_score":0.21120593},"labels":[],"label_agreement":null},{"id":"W2169517221","doi":"10.1177/0146621610391777","title":"Accuracy of Person-Fit Statistics","year":2011,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"","keywords":"Statistics; Cheating; Monte Carlo method; Mathematics; Econometrics; Psychology; Social psychology","score_opus":0.24308051572562275,"score_gpt":0.34340061958845114,"score_spread":0.10032010386282839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169517221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001705557,0.000088764406,0.95631826,0.000055831213,0.00006713179,0.0002469835,0.0000024578217,0.00023410442,0.04128091],"genre_scores_gemma":[0.60950327,0.000016308699,0.39021766,0.00019613077,0.000010528735,0.00004218567,5.223339e-7,0.00000494812,0.000008437964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819034,0.000046201672,0.00033294692,0.00047939876,0.0006786055,0.00027248735],"domain_scores_gemma":[0.9985755,0.000057893154,0.00024502332,0.0008258362,0.0001964074,0.000099330246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060128054,0.00016926057,0.00026161643,0.000081844926,0.000051934363,0.000017048136,0.0010485186,0.000079263904,0.00016749992],"category_scores_gemma":[0.00009860872,0.00013337107,0.00007115871,0.00033371203,0.000098313496,0.00009688462,0.00010480464,0.00015548938,0.000072316005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043559463,0.00090991834,0.00029746705,0.00001418767,0.00007003129,0.000011031197,0.0007323579,0.0000035988805,0.031224005,0.609364,0.0036980105,0.35363188],"study_design_scores_gemma":[0.0023307512,0.0018557762,0.109068535,0.00008059844,0.00014596827,0.000022928905,0.00031648792,0.00092863233,0.25544438,0.618771,0.009245131,0.0017897821],"about_ca_topic_score_codex":0.000008275875,"about_ca_topic_score_gemma":0.0000025080528,"teacher_disagreement_score":0.60779774,"about_ca_system_score_codex":0.000050905313,"about_ca_system_score_gemma":0.000013786426,"threshold_uncertainty_score":0.5438714},"labels":[],"label_agreement":null},{"id":"W2170783728","doi":"10.1002/meet.14505001072","title":"Exact versus estimated pruning of subject hierarchies","year":2013,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subject (documents); Hierarchy; Computer science; Pruning; Data science; Information retrieval; Visualization; Artificial intelligence; Theoretical computer science; World Wide Web","score_opus":0.013886144264422492,"score_gpt":0.2833045487715939,"score_spread":0.2694184045071714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170783728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9642922,0.000019317677,0.032151587,0.0020955007,0.000028660894,0.00039666964,0.0000017053334,0.000245211,0.0007691302],"genre_scores_gemma":[0.8032343,0.000039852337,0.19658671,0.0000853435,0.0000020346615,0.00004574939,1.8378542e-7,0.0000019280633,0.0000039042643],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990062,0.0000010393334,0.00028249403,0.0001430642,0.00033083357,0.00023636862],"domain_scores_gemma":[0.99762034,0.00006125419,0.0007339889,0.00017804882,0.0013768646,0.000029477644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005056473,0.00008607887,0.00019529917,0.00033835217,0.0002340968,0.0000851187,0.0012845319,0.000033456072,3.904374e-7],"category_scores_gemma":[0.000589954,0.00006195955,0.00008458207,0.0044440622,0.0026327276,0.0037893374,0.0005188706,0.000090986454,6.841588e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016371445,0.000027274282,0.006854758,0.000108161774,0.000060937095,5.8417897e-9,0.0030569767,0.000011546528,0.22336595,0.3139222,0.001224189,0.4513516],"study_design_scores_gemma":[0.0007099812,0.0008270184,0.008665512,0.00008075269,0.000038770897,0.000010506608,0.009489328,0.10683473,0.82093036,0.049724586,0.0023235774,0.00036485435],"about_ca_topic_score_codex":0.000025951997,"about_ca_topic_score_gemma":1.9149061e-7,"teacher_disagreement_score":0.5975644,"about_ca_system_score_codex":0.00004606785,"about_ca_system_score_gemma":0.00008916152,"threshold_uncertainty_score":0.9700395},"labels":[],"label_agreement":null},{"id":"W2177607365","doi":"10.1007/s10515-015-0184-4","title":"Concept extraction from business documents for software engineering projects","year":2015,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Documentation; Domain engineering; Software mining; Software engineering; Process (computing); Domain (mathematical analysis); Software; Data science; Knowledge extraction; Data mining; Domain analysis; Information extraction; Software development; Information retrieval; Software construction; Programming language","score_opus":0.016569986768452373,"score_gpt":0.2722598448418184,"score_spread":0.255689858073366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177607365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021664416,0.0003307968,0.95928425,0.000029972967,0.0007589163,0.00045722586,0.000018907009,0.017451933,0.0000035610867],"genre_scores_gemma":[0.24302131,0.000006747086,0.7563935,0.00003497026,0.00013795482,0.0002072986,0.000091367,0.00006959172,0.000037293765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979934,0.000017067285,0.00041952377,0.0006257806,0.0004008768,0.0005433232],"domain_scores_gemma":[0.9981729,0.0003824842,0.00015775744,0.0006714963,0.00040838012,0.00020697514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020223073,0.00038385173,0.00039244618,0.00032215312,0.000080486316,0.00022493233,0.0007526052,0.00018604442,0.0000038043659],"category_scores_gemma":[0.0019906054,0.00041800714,0.00010647984,0.0010078272,0.000014648039,0.0017596754,0.0002103357,0.00020350872,0.000018810959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029393908,0.00020502182,0.0041214516,0.00026629216,0.0005107497,0.00013962825,0.0025630714,0.9423791,0.011726484,0.0018056488,0.008071024,0.028182127],"study_design_scores_gemma":[0.0008843927,0.00006965903,0.00415256,0.00023292092,0.000052816686,0.00002401075,0.000022680217,0.96454656,0.02147765,0.00030192343,0.007369195,0.0008656033],"about_ca_topic_score_codex":0.00007763292,"about_ca_topic_score_gemma":0.000002435319,"teacher_disagreement_score":0.2213569,"about_ca_system_score_codex":0.00031487586,"about_ca_system_score_gemma":0.00010865043,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"W2184546122","doi":"","title":"PRIS at Knowledge Base Population 2013","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bootstrapping (finance); Computer science; Ranking (information retrieval); Task (project management); Knowledge base; Entity linking; Population; Similarity (geometry); Base (topology); Artificial intelligence; Data mining; Information retrieval; Natural language processing; Machine learning; Mathematics; Image (mathematics); Engineering","score_opus":0.007412972671835042,"score_gpt":0.2606132115266101,"score_spread":0.25320023885477505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184546122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023806741,0.0006309571,0.97167915,0.00019234479,0.000008388547,0.0002973638,0.0000013688767,0.0001654273,0.0032182694],"genre_scores_gemma":[0.9772416,0.000080330145,0.021008953,0.000024388717,0.000020472313,0.00031431922,0.000010902153,0.000005025783,0.0012940546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99942803,0.000053143754,0.00017002822,0.0001847625,0.00006321082,0.00010081584],"domain_scores_gemma":[0.9991142,0.00014918127,0.000101383215,0.0004773014,0.00011282353,0.00004510337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023913603,0.00007853568,0.000116046336,0.00008350901,0.00013881676,0.00003174035,0.00030010284,0.00003415114,0.00004651497],"category_scores_gemma":[0.000016770862,0.000068518995,0.000028752367,0.00027624218,0.00011464418,0.00046589668,0.00018124329,0.000038322072,0.00005851743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015071267,0.000023764009,0.00034027043,0.000009994966,0.000005717785,2.0114786e-8,0.00016324055,0.0000045823886,0.0015676926,0.94715136,0.0002825093,0.050449364],"study_design_scores_gemma":[0.000044559194,0.000012932887,0.0021519782,0.000002978511,0.000009457443,0.0000016642621,0.000046592148,0.0005963424,0.023197152,0.9695851,0.0042605107,0.00009069733],"about_ca_topic_score_codex":0.000052128795,"about_ca_topic_score_gemma":0.000011926789,"teacher_disagreement_score":0.9534348,"about_ca_system_score_codex":0.000017680799,"about_ca_system_score_gemma":0.000008726007,"threshold_uncertainty_score":0.27941236},"labels":[],"label_agreement":null},{"id":"W2207763101","doi":"","title":"Social Annotation: Emergent Text Signals through Self-Organization","year":2010,"lang":"en","type":"article","venue":"EdMedia: World Conference on Educational Media and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Athabasca University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence; Data science","score_opus":0.020922287943656633,"score_gpt":0.29768968425692305,"score_spread":0.2767673963132664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2207763101","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019573975,0.00011888845,0.052039307,0.921374,0.0019010904,0.00039472064,0.0000069237685,0.0013664808,0.0032245766],"genre_scores_gemma":[0.9436417,0.00009932686,0.054801125,0.00046786497,0.0005089627,0.00012368224,0.000048707676,0.000016590378,0.0002920261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835277,0.00003828933,0.00034187362,0.0005870073,0.00036636522,0.0003136706],"domain_scores_gemma":[0.9983328,0.00025202456,0.00021872026,0.00043726378,0.0006636847,0.0000954788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014154133,0.00023177562,0.00026072087,0.0006349365,0.0003118347,0.00009099776,0.000794282,0.00021919764,0.00047422046],"category_scores_gemma":[0.00040060005,0.00022966243,0.00003463492,0.0022746949,0.0002779769,0.0004788136,0.00018027968,0.0005501242,0.00009976756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011232792,0.00015928109,0.0022750245,0.000005294887,0.000021064972,0.0000017597695,0.0009998129,3.2151135e-7,0.0056035863,0.9819014,0.0034684325,0.005562889],"study_design_scores_gemma":[0.00015678952,0.000037550326,0.0041591926,0.000010953929,0.000016295415,0.000011602378,0.000027975206,0.00026355064,0.017976763,0.9752721,0.0018070941,0.0002601072],"about_ca_topic_score_codex":0.0000051019015,"about_ca_topic_score_gemma":0.0001063513,"teacher_disagreement_score":0.92406774,"about_ca_system_score_codex":0.000044926903,"about_ca_system_score_gemma":0.00037205743,"threshold_uncertainty_score":0.9365362},"labels":[],"label_agreement":null},{"id":"W2212854643","doi":"10.15837/ijccc.2011.3.2132","title":"Human-inspired Identification of High-level Concepts using OWA and Linguistic Quantifiers","year":2011,"lang":"en","type":"article","venue":"International Journal of Computers Communications & Control","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Schema (genetic algorithms); Schema matching; Identification (biology); Matching (statistics); Artificial intelligence; Natural language processing; Machine learning; Data mining; Mathematics; Data integration","score_opus":0.08137653461828818,"score_gpt":0.3690841034683447,"score_spread":0.2877075688500565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212854643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040518895,0.0003772197,0.9579971,0.00042243817,0.00041267017,0.00011422613,0.000009670083,0.00004032385,0.00010747529],"genre_scores_gemma":[0.7186636,0.00006074357,0.28111574,0.00009506862,0.00004480801,0.0000026005332,0.0000026858525,0.000007495643,0.000007278633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790204,0.00021545014,0.001145246,0.00017673011,0.00043458882,0.0001259425],"domain_scores_gemma":[0.9951777,0.00027499348,0.0016843778,0.00096257875,0.0018233296,0.00007703755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068074063,0.00014072594,0.00034772354,0.000540708,0.0001335095,0.000107628184,0.0036018367,0.000056065237,0.0000041244284],"category_scores_gemma":[0.00019385194,0.00014223404,0.00014876493,0.0002284792,0.00029421272,0.00064799975,0.0004260124,0.0002196166,0.0000013009831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009561983,0.00086330937,0.0048205503,0.000021463908,0.001714139,0.00004154712,0.0061586774,0.0018143391,0.0844991,0.8229173,0.00015967072,0.07689432],"study_design_scores_gemma":[0.006331912,0.0005408026,0.06944392,0.00067790964,0.00050612836,0.0004637551,0.00028490127,0.71855056,0.0287264,0.17238005,0.0011755528,0.00091812556],"about_ca_topic_score_codex":0.00011890956,"about_ca_topic_score_gemma":0.000012533079,"teacher_disagreement_score":0.7167362,"about_ca_system_score_codex":0.00010074136,"about_ca_system_score_gemma":0.000093454284,"threshold_uncertainty_score":0.6693169},"labels":[],"label_agreement":null},{"id":"W2219965243","doi":"","title":"The RhetFig project: computational rhetorics and models of persuasion","year":2011,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Persuasion; Automatic summarization; Topos theory; Ontology; Computer science; Rhetoric; Annotation; Ontology engineering; Natural language processing; Artificial intelligence; Epistemology; Linguistics; Process ontology; Semantic Web; Philosophy","score_opus":0.26881621305356274,"score_gpt":0.3706189476740427,"score_spread":0.10180273462047995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2219965243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014646022,0.00004379741,0.9861689,0.0003581302,0.00007562307,0.00017435772,0.0000049187743,0.000078284,0.011631348],"genre_scores_gemma":[0.9290635,0.00008655383,0.07067804,0.00007175803,0.000018003826,0.000021996406,0.0000027060114,0.000005074702,0.0000523761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835044,0.000068345784,0.00039572574,0.00032842328,0.00069370534,0.0001633402],"domain_scores_gemma":[0.9981488,0.0003158177,0.00020435952,0.00022171339,0.0010651964,0.000044107263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051875756,0.00012834203,0.00013601172,0.00017568539,0.00024445198,0.00008732741,0.0006612054,0.000059625305,0.000013051206],"category_scores_gemma":[0.00019925492,0.000098519326,0.00005093744,0.00046833465,0.00023461801,0.00044288527,0.00014572845,0.00015241234,0.000013641167],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017011063,0.00005953351,0.000010261875,0.0000022210486,0.0000079556585,5.341087e-7,0.00068111724,0.001042108,0.00014524042,0.9262269,0.000030716958,0.07177641],"study_design_scores_gemma":[0.000007943608,0.00006629045,0.00008134915,0.000010425014,0.0000018693283,0.000001649841,0.00009253281,0.4059813,0.005787253,0.58785933,0.00003958122,0.000070438036],"about_ca_topic_score_codex":0.000035342342,"about_ca_topic_score_gemma":0.000025426349,"teacher_disagreement_score":0.9275989,"about_ca_system_score_codex":0.000050825292,"about_ca_system_score_gemma":0.00022271341,"threshold_uncertainty_score":0.40175015},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.047122001145699366,"score_gpt":0.36743177930217613,"score_spread":0.32030977815647677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2230887875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06508529,0.00038188646,0.9326547,0.00009692932,0.00026645281,0.0013651322,0.000011662159,0.000061012342,0.00007693116],"genre_scores_gemma":[0.97080356,0.00007808747,0.028642835,0.0000017367795,0.000016422307,0.00022626991,6.6751744e-7,0.000008559219,0.00022188471],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978935,0.0002175406,0.00060361094,0.00043370872,0.00059849554,0.00025312405],"domain_scores_gemma":[0.99281883,0.004800117,0.0005465073,0.0008948438,0.00090898987,0.00003072895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005625145,0.00013390147,0.0003712152,0.00021128546,0.00062657346,0.00005650282,0.0011917038,0.000029720055,6.90354e-7],"category_scores_gemma":[0.0026227299,0.00006351219,0.000080446465,0.0007180067,0.00066181686,0.00042804136,0.000381981,0.0000518974,3.8735112e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112679416,0.00040823105,0.0015309006,0.00016091454,0.0005057239,0.0000017934955,0.011902897,0.00013601551,0.19377854,0.20999867,0.00086679455,0.58059686],"study_design_scores_gemma":[0.0027501243,0.0019594976,0.012005637,0.0007698658,0.00038019166,0.0000050958197,0.011563359,0.023316212,0.8872185,0.058544476,0.0009987445,0.000488312],"about_ca_topic_score_codex":0.000007264964,"about_ca_topic_score_gemma":0.00006586709,"teacher_disagreement_score":0.90571827,"about_ca_system_score_codex":0.000060070597,"about_ca_system_score_gemma":0.000031952943,"threshold_uncertainty_score":0.48191598},"labels":[],"label_agreement":null},{"id":"W2250467175","doi":"","title":"An initial study of topical poetry segmentation","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Poetry; Focus (optics); Segmentation; Test (biology); Computer science; Artificial intelligence; Natural language processing; Art; Literature; Geology","score_opus":0.018801084788205018,"score_gpt":0.3477503906298853,"score_spread":0.32894930584168025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250467175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4873714,5.742078e-7,0.5114744,0.000019587027,0.000010806643,0.0000947664,2.5767422e-8,0.00008688412,0.0009416002],"genre_scores_gemma":[0.8421653,2.2208116e-7,0.15769961,0.000058228987,0.000012576297,0.000016680151,4.821678e-7,0.0000016438673,0.00004523252],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945146,0.000041403222,0.00014423252,0.00014650777,0.00014916915,0.000067205976],"domain_scores_gemma":[0.99952173,0.00001624743,0.000041248393,0.00032897186,0.00006027328,0.000031503794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000045914294,0.000044619585,0.00007694363,0.000058682846,0.000022513996,0.00003325857,0.00034933494,0.000017616072,0.00007694926],"category_scores_gemma":[0.0000054680067,0.00003639983,0.000016513237,0.00016566463,0.000012238576,0.0007458501,0.00007377403,0.000033237644,0.000013600291],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056643376,0.0036455549,0.13012598,0.000009623777,0.00007165857,0.000011394257,0.008724074,0.00015060359,0.15322293,0.062079277,0.0005846069,0.6413686],"study_design_scores_gemma":[0.0011796365,0.003877331,0.38613918,0.0000068277554,0.0000270304,0.0000065875893,0.0063155056,0.092398524,0.46501577,0.04450757,0.000034416804,0.00049160223],"about_ca_topic_score_codex":0.00019547924,"about_ca_topic_score_gemma":0.000039205606,"teacher_disagreement_score":0.640877,"about_ca_system_score_codex":0.000012171902,"about_ca_system_score_gemma":0.000006013193,"threshold_uncertainty_score":0.1484342},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02111276075879438,"score_gpt":0.24509023218057135,"score_spread":0.22397747142177699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250595592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036166946,0.0000414696,0.97789633,0.00076633587,0.000032099015,0.000098427096,2.2676035e-7,0.0006240784,0.01692434],"genre_scores_gemma":[0.7205691,0.0000038507337,0.27861375,0.00026941497,0.000043898784,0.000009458846,0.000004312913,0.000009987335,0.00047625415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987681,0.0001484402,0.00025189004,0.0004162908,0.00021417973,0.0002010822],"domain_scores_gemma":[0.99854094,0.0007129553,0.00014911068,0.0004158665,0.000099745645,0.000081389815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000678648,0.00014195198,0.00015796439,0.0001946728,0.0003692729,0.00018477612,0.00032219262,0.00006982795,0.000009174621],"category_scores_gemma":[0.0002589215,0.00013606474,0.000043068296,0.00042751778,0.0000495578,0.00077355787,0.00014974254,0.0002145211,0.000014466856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037721584,0.00027378148,0.24962828,0.0001454447,0.00016978712,0.000017218988,0.003274142,0.05604264,0.011492545,0.2884952,0.007883492,0.38253975],"study_design_scores_gemma":[0.0003799021,0.000046266843,0.014509908,0.00011015149,0.000023251328,0.000007722999,0.0001158432,0.9365352,0.011202449,0.02105471,0.015517451,0.0004971825],"about_ca_topic_score_codex":0.00004654372,"about_ca_topic_score_gemma":0.000034397344,"teacher_disagreement_score":0.8804925,"about_ca_system_score_codex":0.000042586147,"about_ca_system_score_gemma":0.00002887687,"threshold_uncertainty_score":0.5548559},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.005305981004063103,"score_gpt":0.23099926973793516,"score_spread":0.22569328873387207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2251442452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065701175,0.000001776338,0.98260313,0.00055388035,0.000013631029,0.00006333814,9.990163e-7,0.00012938076,0.010063733],"genre_scores_gemma":[0.86760265,0.0000022575591,0.13209389,0.00019618004,0.0000073023343,0.0000043731966,0.0000040974255,0.0000029311786,0.00008632628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994839,0.00003122197,0.00012094185,0.0001664639,0.00012910193,0.00006836671],"domain_scores_gemma":[0.99938405,0.00017838196,0.00008348897,0.0002451637,0.00008197629,0.000026947713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012684474,0.00006225965,0.0001008201,0.00011135361,0.000039549046,0.00002647323,0.00015125968,0.000030006042,0.00001646204],"category_scores_gemma":[0.00007156787,0.00005517469,0.0000226205,0.00016821855,0.000058079455,0.00034577327,0.000038414928,0.00004076797,0.0000034147681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020707004,0.000143635,0.018328372,0.000021046822,0.000030845804,0.0000010585535,0.0004953444,0.00197294,0.009539726,0.9134555,0.00047382162,0.055516988],"study_design_scores_gemma":[0.00036248227,0.00022763613,0.053706564,0.00002196482,0.000017236734,6.1188337e-7,0.000060682683,0.79751205,0.117265284,0.02914965,0.0014580629,0.00021779259],"about_ca_topic_score_codex":0.00004579184,"about_ca_topic_score_gemma":0.000021824542,"teacher_disagreement_score":0.88430583,"about_ca_system_score_codex":0.00001442916,"about_ca_system_score_gemma":0.000016717828,"threshold_uncertainty_score":0.22499585},"labels":[],"label_agreement":null},{"id":"W2252024428","doi":"","title":"Towards Topic Labeling with Phrase Entailment and Aggregation","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Textual entailment; Phrase; Computer science; Logical consequence; Natural language processing; Artificial intelligence; Generalization; Set (abstract data type); Aggregate (composite); Graph; Mathematics; Theoretical computer science","score_opus":0.006640097068752401,"score_gpt":0.23190119143036342,"score_spread":0.22526109436161101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252024428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089203715,0.00005468169,0.9071536,0.0010531005,0.000010129965,0.00011904577,4.43159e-8,0.00021662682,0.0021890206],"genre_scores_gemma":[0.5986479,0.000016094955,0.40072107,0.0002464898,0.000007548145,0.000019972102,4.0582825e-7,0.0000020496648,0.0003384405],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994959,0.000010766574,0.00008394044,0.00018347768,0.00012438941,0.00010147827],"domain_scores_gemma":[0.9996368,0.000009167894,0.00003347694,0.00022415393,0.000052399642,0.000043956476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005033185,0.00006428597,0.00006980438,0.000050001046,0.00004316926,0.000106110216,0.00015940025,0.000016437296,0.000044854707],"category_scores_gemma":[0.0000059964977,0.000044746394,0.000011043549,0.00014178897,0.000017410139,0.0006128519,0.000094603245,0.00003578056,0.000017625567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.1058484e-7,0.00003165388,0.00367866,0.0000073426863,0.000019101284,0.000003955479,0.0003100324,0.000023381745,0.0037770465,0.07585471,0.000297637,0.9159956],"study_design_scores_gemma":[0.0016053017,0.00074462924,0.022535123,0.00015473686,0.000057436442,0.000060400424,0.00038390758,0.2676329,0.4843525,0.21439175,0.0067603905,0.001320914],"about_ca_topic_score_codex":0.00012695389,"about_ca_topic_score_gemma":0.00001937069,"teacher_disagreement_score":0.91467464,"about_ca_system_score_codex":0.000022420603,"about_ca_system_score_gemma":0.000010518425,"threshold_uncertainty_score":0.1824705},"labels":[],"label_agreement":null},{"id":"W2252545675","doi":"10.1007/978-3-319-25252-0_18","title":"Ontology-Based Topic Labeling and Quality Prediction","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Reliability (semiconductor); Probabilistic logic; Ontology; Coherence (philosophical gambling strategy); Quality (philosophy); Artificial intelligence; Information retrieval; Natural language processing; Semantics (computer science); Machine learning; Data mining","score_opus":0.0454640940380162,"score_gpt":0.31517178953091995,"score_spread":0.26970769549290374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252545675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012325685,0.00079957914,0.99609023,0.00057804165,0.00048433366,0.00023115368,0.000004848755,0.00036214804,0.0013264066],"genre_scores_gemma":[0.090159446,0.000030997217,0.90833795,0.0009903358,0.00021747086,0.000009939419,0.000006391146,0.000019595935,0.00022785763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969046,0.00005448572,0.0005093281,0.0013332878,0.00077947794,0.00041879338],"domain_scores_gemma":[0.99772775,0.00032151293,0.00028925794,0.0012047663,0.00029661556,0.00016009339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013475744,0.00037515792,0.0005246187,0.0006608307,0.00016992053,0.00024359795,0.0016383509,0.00032289934,0.0000057060543],"category_scores_gemma":[0.0001683717,0.00034918365,0.00007872645,0.00042853854,0.00058889796,0.0005480628,0.0007737239,0.00061548984,0.000006037098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006502648,0.000029031029,0.0006801331,0.000051663694,0.000014993891,0.000039141,0.0003774437,0.015368528,0.00047254987,0.06340414,0.000027804746,0.91952807],"study_design_scores_gemma":[0.0003425723,0.00020426688,0.00037265656,0.00024337028,0.000015478045,0.000026921834,1.2983483e-7,0.5165421,0.0016256078,0.4778386,0.0021737178,0.0006145755],"about_ca_topic_score_codex":0.00003632082,"about_ca_topic_score_gemma":0.00022518009,"teacher_disagreement_score":0.9189135,"about_ca_system_score_codex":0.0003672192,"about_ca_system_score_gemma":0.00043404067,"threshold_uncertainty_score":0.999896},"labels":[],"label_agreement":null},{"id":"W2271445843","doi":"","title":"Interpersonal Awareness During Web-based Concept Mapping: The Effect of Different Communication Channels","year":2004,"lang":"en","type":"article","venue":"EdMedia: World Conference on Educational Media and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Interpersonal communication; Computer science; Interpersonal relationship; World Wide Web; Psychology; Knowledge management; Internet privacy; Social psychology; Communication","score_opus":0.021766113883649373,"score_gpt":0.2753001712164939,"score_spread":0.25353405733284456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271445843","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47656763,0.00079851557,0.03614428,0.4840968,0.00090461643,0.00070155645,0.000010348582,0.0004884255,0.00028782865],"genre_scores_gemma":[0.9963502,0.00006641,0.002976818,0.00009932791,0.00007591317,0.00034544873,0.000025806967,0.000010279981,0.000049791706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985703,0.00011546366,0.00032626954,0.00040753788,0.00031508988,0.00026534556],"domain_scores_gemma":[0.9978269,0.0008604453,0.00024970472,0.00080074224,0.00018355987,0.00007865988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001842151,0.00024209455,0.00036078738,0.0007499437,0.00020838261,0.0000482812,0.0013220857,0.0001192866,0.00003985966],"category_scores_gemma":[0.00028073374,0.00017186104,0.00006447732,0.000973112,0.0007466897,0.0001551604,0.00025859056,0.0004298238,0.000006271593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021500098,0.00018993813,0.012823578,0.00004630584,0.000056699282,0.000002604193,0.0012502837,0.000047105917,0.0060392916,0.9732812,0.000093859206,0.0061476254],"study_design_scores_gemma":[0.001291042,0.00026593366,0.008943712,0.0004404109,0.000027199067,0.00001369447,0.00006651888,0.0026160714,0.20775315,0.77820826,0.00004945536,0.00032458076],"about_ca_topic_score_codex":0.000013025257,"about_ca_topic_score_gemma":0.000079789024,"teacher_disagreement_score":0.51978254,"about_ca_system_score_codex":0.00010731022,"about_ca_system_score_gemma":0.00026607118,"threshold_uncertainty_score":0.700829},"labels":[],"label_agreement":null},{"id":"W2278408372","doi":"10.1007/3-540-45153-6_27","title":"Évaluation d’un Système pour le Résumé Automatique de Documents ÉLectroniques","year":2001,"lang":"fr","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Valuation (finance); Business; Accounting","score_opus":0.024545233327482822,"score_gpt":0.2934102087685686,"score_spread":0.2688649754410858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278408372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010623699,0.0012327787,0.9864176,0.004008407,0.0007025392,0.0009148015,0.00000451725,0.0008693553,0.004787661],"genre_scores_gemma":[0.3449491,0.0003944645,0.6526026,0.0012151145,0.00040661485,0.000047505047,0.000008419629,0.000064011634,0.0003121747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918685,0.00046514554,0.0013311598,0.0027065712,0.0017990648,0.0018295469],"domain_scores_gemma":[0.9947085,0.0009272917,0.00091639964,0.0022367747,0.0008206663,0.00039039395],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0037637965,0.0011601727,0.0011582753,0.0015318714,0.0008246238,0.0012770357,0.004864285,0.00077583984,0.00011538129],"category_scores_gemma":[0.00042198037,0.0012148523,0.00039673838,0.0018743172,0.0013206137,0.0024349804,0.001811038,0.0015312631,0.000105315434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008175248,0.00013375329,0.0004261686,0.000060284514,0.000053496544,0.00020005256,0.001385547,0.0717619,0.0020474237,0.13408351,0.000028452536,0.78981125],"study_design_scores_gemma":[0.00021394888,0.00016226199,0.0005939115,0.000571182,0.000027837452,0.00022717714,3.7414742e-7,0.51800525,0.026273692,0.4527189,0.0005036222,0.00070185453],"about_ca_topic_score_codex":0.0010286684,"about_ca_topic_score_gemma":0.00057022594,"teacher_disagreement_score":0.7891094,"about_ca_system_score_codex":0.0032295713,"about_ca_system_score_gemma":0.0037843576,"threshold_uncertainty_score":0.99975973},"labels":[],"label_agreement":null},{"id":"W2294408224","doi":"10.1007/s12080-016-0292-1","title":"Introduction to the special issue: theory of food webs","year":2016,"lang":"en","type":"article","venue":"Theoretical Ecology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Mathematical economics; Mathematics","score_opus":0.004947937222468709,"score_gpt":0.24462835334006192,"score_spread":0.23968041611759322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294408224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008596253,0.000006860693,0.9232408,0.058381915,0.00045280377,0.00016717518,0.0000018062301,0.00011670394,0.009035678],"genre_scores_gemma":[0.9793749,0.0000090183,0.015745627,0.0007229032,0.0036247512,0.000025153167,2.7570553e-7,0.000007756104,0.00048962876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877197,0.00030195728,0.00022822173,0.00031308265,0.00013846335,0.00024631157],"domain_scores_gemma":[0.9984371,0.00061063084,0.000068628324,0.00073308276,0.00009115867,0.00005941271],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008254729,0.0000949863,0.00019886895,0.000090979345,0.000055066193,0.000010696739,0.00093113823,0.00007112038,0.0024422638],"category_scores_gemma":[0.0007532429,0.00004869845,0.00006789531,0.0002966103,0.0006780517,0.00010804497,0.000372891,0.00008325077,0.0004443591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023036087,0.000028885152,0.000018483746,8.950374e-7,0.000014888859,6.7986963e-7,0.00010082954,0.000002680181,0.0010918593,0.92717403,0.009495398,0.062048346],"study_design_scores_gemma":[0.00009541445,0.00045648447,0.00030877988,0.0000024883477,0.00001068595,0.000006945452,0.000010694579,0.00005209903,0.03215613,0.91758037,0.04925076,0.00006916416],"about_ca_topic_score_codex":1.1896635e-7,"about_ca_topic_score_gemma":0.0000064972696,"teacher_disagreement_score":0.97077864,"about_ca_system_score_codex":0.000042620664,"about_ca_system_score_gemma":0.00002452099,"threshold_uncertainty_score":0.99846965},"labels":[],"label_agreement":null},{"id":"W2298270464","doi":"","title":"The distribution of references in scientific papers: An analysis of the IMRaD structure","year":2013,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Categorization; Section (typography); Matching (statistics); Information retrieval; Scientific literature; Data science; Artificial intelligence; Mathematics; Statistics","score_opus":0.01170373291071532,"score_gpt":0.24597000095097465,"score_spread":0.23426626804025932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298270464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7566378,0.0007429802,0.23664469,0.0031229935,0.0002067311,0.00056427164,0.00015573371,0.00013209382,0.0017926922],"genre_scores_gemma":[0.9788451,0.00017688927,0.020060318,0.000010461844,0.0000042262345,0.00003588454,0.00031527667,0.000010027941,0.00054181024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99277735,0.0045063575,0.0008315231,0.0008321222,0.000758216,0.00029445149],"domain_scores_gemma":[0.99009234,0.0010285138,0.0012935081,0.0051737484,0.0023349102,0.00007695448],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004801967,0.0002637853,0.00051249564,0.00035235257,0.00042947364,0.0005839441,0.005627499,0.0002197993,0.000023970468],"category_scores_gemma":[0.0011503779,0.00017632978,0.0003676682,0.00313826,0.00081235135,0.0003372021,0.002541539,0.0005548163,9.3399404e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007158602,0.0005245815,0.024563745,0.00009845216,0.0005436061,6.8748255e-7,0.010955897,0.0033755044,0.014939531,0.8202688,0.00018121493,0.12454078],"study_design_scores_gemma":[0.00028525395,0.0000014355069,0.23940416,0.0011757853,0.0005157575,0.0000016780634,0.00040994614,0.45702696,0.19263142,0.10430567,0.0035347086,0.0007072257],"about_ca_topic_score_codex":0.001857492,"about_ca_topic_score_gemma":0.014871549,"teacher_disagreement_score":0.7159632,"about_ca_system_score_codex":0.00013894115,"about_ca_system_score_gemma":0.00027745406,"threshold_uncertainty_score":0.9997525},"labels":[],"label_agreement":null},{"id":"W2302088940","doi":"10.7202/1029091ar","title":"Vers une nouvelle génération d’outils d’analyse et de recherche d’information","year":2015,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.11358409482440322,"score_gpt":0.41908623043501403,"score_spread":0.3055021356106108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302088940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024533751,0.0013224491,0.92383456,0.018332917,0.0004482118,0.0004059174,0.000017460316,0.0005482966,0.052636817],"genre_scores_gemma":[0.25677904,0.0114298565,0.7056826,0.012140206,0.00020305385,0.00014737919,0.00045613982,0.000051593775,0.013110155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951968,0.0021141127,0.0008542744,0.0004556578,0.0008722726,0.00050684926],"domain_scores_gemma":[0.9969047,0.0005293661,0.00064207456,0.00064356707,0.00094511325,0.00033522875],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.005907139,0.0003594239,0.00035799647,0.0030532693,0.00015010645,0.006006713,0.0006737241,0.0003963158,0.00050442124],"category_scores_gemma":[0.0010038214,0.0004074241,0.00018247921,0.009837841,0.00013507834,0.059607107,0.00019850563,0.000600612,0.00043380738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009967103,0.0003265015,0.0014646221,0.00011712705,0.00028203623,0.000020191252,0.06975655,0.00921342,0.002315621,0.6830098,0.10268277,0.1307117],"study_design_scores_gemma":[0.0024592427,0.00075639726,0.001771723,0.00030710953,0.00037404886,0.000065171356,0.010351806,0.102977626,0.055900034,0.34696174,0.47662058,0.0014545119],"about_ca_topic_score_codex":0.0065087015,"about_ca_topic_score_gemma":0.0008732822,"teacher_disagreement_score":0.37393782,"about_ca_system_score_codex":0.002117384,"about_ca_system_score_gemma":0.0020175995,"threshold_uncertainty_score":0.99983776},"labels":[],"label_agreement":null},{"id":"W2303554020","doi":"","title":"L'utilisation des POMDP pour les résumés multi-documents orientés par une thématique","year":2013,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Humanities; Political science; Philosophy; Computer science","score_opus":0.03534792806896733,"score_gpt":0.28854973517114635,"score_spread":0.253201807102179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2303554020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08426321,0.0016189414,0.87645257,0.01548836,0.00036992706,0.0012569058,0.000044448712,0.0009780624,0.019527588],"genre_scores_gemma":[0.43102348,0.0020396942,0.537332,0.00012997922,0.00004805897,0.00032749807,0.00033252104,0.00009603647,0.028670762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9831596,0.010386349,0.0017600852,0.0023443755,0.0011675208,0.0011820586],"domain_scores_gemma":[0.98322386,0.002063196,0.0017920822,0.005450927,0.006890807,0.000579107],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0069461246,0.0011337966,0.0010854267,0.00056136586,0.0014593542,0.0017899367,0.0049934704,0.0008548774,0.0007822517],"category_scores_gemma":[0.0029522253,0.0012395205,0.00066789496,0.0017707805,0.0012407693,0.0019763028,0.0043652793,0.0015312657,0.00067560136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013714813,0.0023619332,0.016204925,0.00038769306,0.00039460338,0.000021048303,0.027378282,0.00062046235,0.014266973,0.6314911,0.0033083442,0.30355087],"study_design_scores_gemma":[0.0019038677,0.0000040473287,0.069854274,0.00700385,0.00033148064,0.000063100204,0.0007342438,0.4151108,0.2507055,0.20572755,0.045686033,0.002875234],"about_ca_topic_score_codex":0.01398571,"about_ca_topic_score_gemma":0.007231812,"teacher_disagreement_score":0.42576358,"about_ca_system_score_codex":0.0007997425,"about_ca_system_score_gemma":0.00068373396,"threshold_uncertainty_score":0.9998406},"labels":[],"label_agreement":null},{"id":"W2331950033","doi":"10.5406/amerjpsyc.127.2.0137","title":"A Remember-Know Analysis of the Semantic Serial Position Function","year":2014,"lang":"en","type":"article","venue":"The American Journal of Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Psychology; Function (biology); Serial position effect; Cognitive psychology; Semantic memory; Cognitive science; Cognition; Neuroscience; Free recall; Recall","score_opus":0.008009751395029338,"score_gpt":0.30607213291306895,"score_spread":0.2980623815180396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331950033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3622063,0.000025663845,0.6341986,0.0031058728,0.00020774936,0.000029527115,2.735737e-7,0.000013822904,0.00021216298],"genre_scores_gemma":[0.9869891,0.000032888056,0.011490737,0.0013440077,0.00011978899,0.000001203787,2.5907477e-7,0.000005173283,0.000016850807],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983871,0.000614464,0.00044396383,0.00015137135,0.0002599362,0.00014316886],"domain_scores_gemma":[0.99736285,0.00014161224,0.0014694836,0.00077798386,0.00021285092,0.000035188146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009663661,0.00009154113,0.0004203969,0.0003351593,0.000076236465,0.00001823628,0.001173253,0.000023881594,0.000015991924],"category_scores_gemma":[0.00006930912,0.0000504613,0.00035073393,0.0022152318,0.00030688266,0.00015657594,0.000090062786,0.00020066956,0.0000027897065],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007916097,0.00041703705,0.0129525615,0.0000073306264,0.0044840025,0.000008666107,0.0015924311,0.007952857,0.17224263,0.028964225,0.0035596092,0.7670271],"study_design_scores_gemma":[0.0014675269,0.0065827034,0.7951441,0.000095861236,0.0067950846,0.00072298344,0.0002917822,0.050813027,0.009721162,0.119313784,0.0084538385,0.0005981399],"about_ca_topic_score_codex":0.000018912244,"about_ca_topic_score_gemma":0.00002285802,"teacher_disagreement_score":0.7821915,"about_ca_system_score_codex":0.000024140356,"about_ca_system_score_gemma":0.00001974403,"threshold_uncertainty_score":0.21802156},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.021723976246193644,"score_gpt":0.3300711010410206,"score_spread":0.30834712479482695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336430626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07459085,0.000012440939,0.9239041,0.00075282686,0.0002405714,0.00009342061,6.2753423e-7,0.00003142462,0.0003737255],"genre_scores_gemma":[0.59889114,0.000012165907,0.40059173,0.0002773812,0.00020869228,0.00000694346,2.3350603e-7,0.0000062535305,0.0000054814936],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99894714,0.00003225331,0.0004959835,0.0002049086,0.00015893557,0.00016076984],"domain_scores_gemma":[0.9986736,0.0001323569,0.0006648156,0.00019917183,0.00025966676,0.000070345006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046440942,0.00010278005,0.000279673,0.0003402005,0.00006187381,0.000016255617,0.0004934114,0.000082051505,0.0000074315076],"category_scores_gemma":[0.000020559857,0.00007413855,0.00009903928,0.0002812818,0.000095069554,0.00031241833,0.00005107207,0.00011322535,0.0000023842274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030570594,0.000118614735,0.000951594,0.00003364234,0.00019726074,0.0000064707,0.0027591202,0.00021063362,0.5212338,0.12648265,0.003945152,0.34375536],"study_design_scores_gemma":[0.0039126985,0.0014449893,0.0017346618,0.0001422514,0.00007721538,0.00021785464,0.00007218639,0.004437962,0.28099418,0.70397896,0.0025827186,0.0004043331],"about_ca_topic_score_codex":0.0000028970817,"about_ca_topic_score_gemma":0.000005700098,"teacher_disagreement_score":0.5774963,"about_ca_system_score_codex":0.0000553004,"about_ca_system_score_gemma":0.00005536285,"threshold_uncertainty_score":0.30232823},"labels":[],"label_agreement":null},{"id":"W2342073150","doi":"10.1108/jdoc-09-2015-0111","title":"On the composition of scientific abstracts","year":2016,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Sentence; Computer science; Rhetorical question; Argumentation theory; Relation (database); Information retrieval; Originality; Similarity (geometry); Scientific writing; Composition (language); Value (mathematics); Linguistics; Natural language processing; Artificial intelligence; Sociology; Qualitative research","score_opus":0.013616701985817723,"score_gpt":0.3029858504638016,"score_spread":0.2893691484779839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342073150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50954115,0.000010677035,0.48789257,0.0021200855,0.00010546458,0.000030928106,3.3360942e-7,0.000009184007,0.0002895847],"genre_scores_gemma":[0.9825998,0.000007293326,0.017235503,0.0000632464,0.000018168437,7.946938e-7,2.0868552e-7,0.0000018270158,0.00007318478],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991562,0.000049188413,0.00031197432,0.00006694288,0.00035846146,0.000057229612],"domain_scores_gemma":[0.9987911,0.00019409903,0.0006179136,0.0001694714,0.00020620697,0.000021195954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005761395,0.000040443138,0.0000742152,0.00015263342,0.00005766597,0.00008001317,0.00033087324,0.000012789231,0.000024354653],"category_scores_gemma":[0.00004697774,0.000019813322,0.00006132214,0.00020006008,0.000048169288,0.001047699,0.000021805388,0.000042986154,0.000010434332],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020091276,0.00008894367,0.00020266602,0.0000033050735,0.000028761287,0.000003879211,0.00023848261,0.00019693197,0.817978,0.10289313,0.0017698376,0.07657597],"study_design_scores_gemma":[0.00028048,0.00021135242,0.0054366062,0.000115972594,0.000013429359,0.000015597725,0.000018295867,0.00013136215,0.88677335,0.10664474,0.00030773735,0.00005108739],"about_ca_topic_score_codex":0.000001087841,"about_ca_topic_score_gemma":7.1212634e-7,"teacher_disagreement_score":0.4730586,"about_ca_system_score_codex":0.000054481796,"about_ca_system_score_gemma":0.000023139432,"threshold_uncertainty_score":0.08079638},"labels":[],"label_agreement":null},{"id":"W2342967932","doi":"10.3389/fpsyg.2016.00577","title":"Editorial: Quantum Structures in Cognitive and Social Science","year":2016,"lang":"en","type":"editorial","venue":"Frontiers in Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Psychology; Cognition; Cognitive science; Social cognition; Cognitive psychology; Neuroscience","score_opus":0.009621518641293408,"score_gpt":0.3548133138391087,"score_spread":0.3451917951978153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342967932","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014287582,0.00034124334,0.29832387,0.00014396134,0.7002227,0.00016862221,0.000021420308,0.00009191469,0.0006719886],"genre_scores_gemma":[0.0009901809,0.00050279446,0.030735692,0.00012163056,0.9675003,0.00006703559,0.000015691645,0.000030907882,0.000035739296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961042,0.00020759738,0.0005280005,0.0015702178,0.00085543,0.0007345889],"domain_scores_gemma":[0.99839944,0.0003322202,0.00035160469,0.00054451363,0.00029718442,0.000075014104],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011254662,0.00038022746,0.0007893704,0.0017805571,0.00013472758,0.00012186281,0.0021594355,0.0011990068,0.0000039574966],"category_scores_gemma":[0.00080500764,0.00034306067,0.00007264506,0.0011127858,0.0014160783,0.000687436,0.0005438316,0.0012014841,0.0000032644175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044845725,0.000026567985,0.00025990646,0.000008192576,0.000013640323,0.000016313092,0.00029467538,2.645129e-8,0.000049233568,0.0017714796,0.9444602,0.053054877],"study_design_scores_gemma":[0.0010042959,0.0000943835,0.00023451926,0.00006542807,0.000010418387,0.0000015031075,0.00003781684,0.00004671472,0.000034163233,0.3008746,0.69718283,0.0004133579],"about_ca_topic_score_codex":0.000019130468,"about_ca_topic_score_gemma":0.000017035032,"teacher_disagreement_score":0.2991031,"about_ca_system_score_codex":0.00027148798,"about_ca_system_score_gemma":0.00034533165,"threshold_uncertainty_score":0.9999021},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07264841213761936,"score_gpt":0.37943749962019485,"score_spread":0.3067890874825755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345836734","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.0230504e-7,0.8738935,0.1231332,0.0004099481,0.00025215923,0.0012614119,0.00007696773,0.00010803019,0.00086445577],"genre_scores_gemma":[0.000026341502,0.9702747,0.029216142,0.00008295566,0.00006167097,0.0001671366,0.000028030317,0.000047543774,0.00009546444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941463,0.000696933,0.0030638385,0.0010903591,0.0004946957,0.0005078793],"domain_scores_gemma":[0.9884364,0.0029192516,0.004808929,0.0034526743,0.0002467064,0.0001360282],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002053376,0.0007070921,0.003765243,0.00017421928,0.00016938602,0.000059771894,0.0039082835,0.0002163553,0.00007760468],"category_scores_gemma":[0.00043681174,0.00043168114,0.0013356966,0.00051184837,0.00023926981,0.000168104,0.0006544654,0.0005437888,0.00020861393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.235105e-7,0.000052206313,4.9755744e-7,0.012840975,0.00023432772,0.0000020827115,0.0000311771,0.0000023904117,0.0000032963198,0.008067524,0.0054814415,0.9732832],"study_design_scores_gemma":[0.000058293117,0.00001919936,1.3264378e-7,0.14478919,0.00060805277,0.00001227421,0.0000020366138,0.0001254251,0.000011865489,0.002793652,0.8512012,0.00037873624],"about_ca_topic_score_codex":0.000016098978,"about_ca_topic_score_gemma":0.0000019846111,"teacher_disagreement_score":0.97290444,"about_ca_system_score_codex":0.00010370002,"about_ca_system_score_gemma":0.00024107679,"threshold_uncertainty_score":0.9998135},"labels":[],"label_agreement":null},{"id":"W2347003616","doi":"10.82308/10338","title":"SE-3D: a controlled comparative usability study of a virtual reality semantic hierarchy explorer","year":2011,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Information retrieval; Subject (documents); Ontology; Relevance (law); Vocabulary; Object (grammar); Visualization; World Wide Web; Usability; Ranking (information retrieval); Hierarchy; Human–computer interaction; Artificial intelligence","score_opus":0.08328705605839519,"score_gpt":0.31035432065726565,"score_spread":0.22706726459887044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347003616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841522,0.000024765595,0.0026766865,0.000017283297,0.00015218055,0.0020206508,0.00006508002,0.0007708703,0.010120277],"genre_scores_gemma":[0.97665393,0.000011141232,0.022643851,0.000119075965,0.000014159754,0.00039273532,0.00000540677,0.000041538377,0.00011815566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928768,0.0019215706,0.0016818425,0.0015983377,0.0011479575,0.00077344896],"domain_scores_gemma":[0.99458563,0.00069495535,0.00089633046,0.0026728497,0.0007790688,0.00037114808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026959744,0.0006684039,0.0018224209,0.000503915,0.0007053841,0.00006687148,0.00240154,0.00021445822,0.00009452861],"category_scores_gemma":[0.00071226765,0.00060007867,0.00046693205,0.001545383,0.00032350703,0.002338127,0.0012119005,0.0008914748,0.00006801839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003146,0.022472417,0.005128177,0.00015567361,0.0030363083,0.00032510876,0.0049991924,0.0004384179,0.057247426,0.7524159,0.000013285703,0.15062208],"study_design_scores_gemma":[0.03954829,0.015476789,0.04905835,0.0004398959,0.0016416387,0.0001108368,0.009331591,0.027773116,0.2887875,0.55809164,0.0034255264,0.006314828],"about_ca_topic_score_codex":0.0008929974,"about_ca_topic_score_gemma":0.00081208296,"teacher_disagreement_score":0.23154007,"about_ca_system_score_codex":0.00044507446,"about_ca_system_score_gemma":0.000048042668,"threshold_uncertainty_score":0.99964505},"labels":[],"label_agreement":null},{"id":"W2351893935","doi":"","title":"Automatic Evaluation of Chinese Summarizations Based on Hybrid Strategy","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Computer science; Key (lock); Point (geometry); Artificial intelligence; Foundation (evidence); Natural language processing; Base (topology); Computer security; Mathematics","score_opus":0.02315909752254468,"score_gpt":0.3441529698475553,"score_spread":0.3209938723250106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2351893935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08311977,0.0000062260665,0.9023571,0.00006740515,0.000021539377,0.00015851259,5.7227163e-7,0.00028401107,0.013984875],"genre_scores_gemma":[0.8558747,4.02043e-7,0.14397082,0.00008701144,0.000007882176,0.0000071936306,0.000006969808,0.000004100917,0.00004092143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875164,0.000061509556,0.00026939376,0.00019159661,0.0006021234,0.00012372859],"domain_scores_gemma":[0.9988528,0.00015631654,0.00012003662,0.0005366501,0.00029536747,0.00003885868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012806222,0.00008654584,0.00011756727,0.00027342114,0.000043176336,0.00002597371,0.0003605175,0.000021429776,0.00011970878],"category_scores_gemma":[0.00017550995,0.00006902421,0.00005340229,0.000713558,0.00002199689,0.00027994614,0.000035091904,0.000047036334,0.000010316051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036208376,0.00037776463,0.006037119,0.00001636099,0.000024830426,0.0000037389982,0.0000783051,0.051717576,0.0038900948,0.053138107,0.00023081577,0.88448167],"study_design_scores_gemma":[0.00014354069,0.00005158793,0.014719057,0.000007002563,0.000010138675,5.115771e-7,0.0000027888732,0.9390938,0.01752326,0.028369017,0.000008096556,0.00007119427],"about_ca_topic_score_codex":0.00001253905,"about_ca_topic_score_gemma":0.000037443606,"teacher_disagreement_score":0.88737625,"about_ca_system_score_codex":0.00006017227,"about_ca_system_score_gemma":0.00008805215,"threshold_uncertainty_score":0.28147256},"labels":[],"label_agreement":null},{"id":"W2366754855","doi":"10.29173/cais375","title":"Convergence and Divergence in Tagging Systems: An Examination of Tagging Practices Over a Four Year Period","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Period (music); Divergence (linguistics); Humanities; Convergence (economics); Library science; Geography; Computer science; Art; Linguistics; Philosophy; Economics","score_opus":0.037532928269416704,"score_gpt":0.2798403217363502,"score_spread":0.2423073934669335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2366754855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933459,0.001099437,0.0017911457,0.0015808162,0.00023268072,0.0006682499,0.000038736976,0.000052755167,0.0011902733],"genre_scores_gemma":[0.9921123,0.0007370785,0.0064892587,0.00006475609,0.000058212056,0.000056484194,0.0000013167114,0.000023569566,0.0004570549],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969479,0.00014082751,0.000980864,0.00065327255,0.000747049,0.00053007447],"domain_scores_gemma":[0.96793336,0.00025888966,0.0033012184,0.000388553,0.02795228,0.00016573003],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001584856,0.00037368128,0.00075534923,0.00039927312,0.00013165336,0.0024870164,0.0022317113,0.00022922947,0.000043024822],"category_scores_gemma":[0.013784526,0.0003417737,0.00012533173,0.0010303269,0.0007783183,0.03691482,0.0012147434,0.00040048055,0.0000025225588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007012923,0.00049706374,0.61525905,0.0028950083,0.00019468869,0.000008303544,0.11619648,0.00010528578,0.092885956,0.1353304,0.00047666565,0.03608096],"study_design_scores_gemma":[0.00087042636,0.00083878747,0.77450037,0.0038458419,0.0002447025,0.00011414081,0.01825695,0.14895958,0.03787733,0.007101206,0.00638371,0.0010069566],"about_ca_topic_score_codex":0.0027263006,"about_ca_topic_score_gemma":0.000055877685,"teacher_disagreement_score":0.1592413,"about_ca_system_score_codex":0.00010900562,"about_ca_system_score_gemma":0.00024516124,"threshold_uncertainty_score":0.99990344},"labels":[],"label_agreement":null},{"id":"W2377349363","doi":"","title":"Internet Popular Topics Extraction of Traffic Content Words Correlation","year":2007,"lang":"en","type":"article","venue":"Xi'an Jiaotong Daxue xuebao","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"The Internet; Computer science; Cluster analysis; DBSCAN; Noise (video); Data mining; Information retrieval; World Wide Web; Artificial intelligence; Fuzzy clustering; Image (mathematics)","score_opus":0.04147398199296873,"score_gpt":0.30684495241127907,"score_spread":0.26537097041831037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2377349363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3071406,0.000077553916,0.69132566,0.00008715549,0.00029643535,0.00019152067,9.246025e-7,0.00028468377,0.0005954911],"genre_scores_gemma":[0.92111754,0.000011897551,0.07681816,0.00008691501,0.000110363864,0.000010997351,0.000020661146,0.000016370052,0.0018070589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981533,0.00007360254,0.00060464616,0.00045200397,0.00039772235,0.0003186782],"domain_scores_gemma":[0.998531,0.000061880484,0.00034802727,0.0007697359,0.00016400115,0.00012536474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007230688,0.00019423346,0.000285642,0.00030216508,0.00006470103,0.00007526755,0.0007002747,0.00014846436,0.000024469153],"category_scores_gemma":[0.0000791566,0.00019455078,0.00013633094,0.00048253703,0.00006495626,0.0012853763,0.00011188135,0.00025940692,0.00001879819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013610891,0.000997879,0.012517515,0.00006919213,0.00019444115,0.00015351134,0.0055113495,0.0077462606,0.028693872,0.14660361,0.0014358378,0.7959404],"study_design_scores_gemma":[0.0019300304,0.0014259722,0.060523257,0.00030683647,0.000201548,0.00019609302,0.00093898387,0.69939464,0.15773937,0.009129512,0.06633925,0.0018745266],"about_ca_topic_score_codex":0.000093058974,"about_ca_topic_score_gemma":0.00021681772,"teacher_disagreement_score":0.7940659,"about_ca_system_score_codex":0.0001555482,"about_ca_system_score_gemma":0.00003081517,"threshold_uncertainty_score":0.79335505},"labels":[],"label_agreement":null},{"id":"W2394448961","doi":"","title":"Concept Search Engine Based on Keywords","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Search engine; Information retrieval; Weighting; Set (abstract data type); Order (exchange); Position (finance); Data mining; Programming language","score_opus":0.007999254089996601,"score_gpt":0.2842298550712716,"score_spread":0.276230600981275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394448961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025537558,0.00004130264,0.99555117,0.0007605018,0.000011162571,0.0004684806,0.000003029796,0.0007782078,0.0021307631],"genre_scores_gemma":[0.17454197,0.0000020173443,0.82366407,0.001370086,0.00013105442,0.00010526731,0.00001785927,0.0000149001135,0.0001527798],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985131,0.000025810405,0.0002793509,0.0005453508,0.0002608897,0.00037548397],"domain_scores_gemma":[0.9985427,0.0001957459,0.00006352474,0.0009279331,0.00013857431,0.00013151974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033839457,0.00017345569,0.00016367198,0.0003189365,0.00017692905,0.00009912006,0.0012526216,0.00006991511,0.00001621345],"category_scores_gemma":[7.645544e-7,0.00017393741,0.00010237824,0.0010586752,0.00006458603,0.00017016569,0.00020103666,0.00021417195,0.00016002376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027996805,0.00022173312,0.00010624151,0.00000592844,0.000013924438,0.0000054638267,0.00014863466,0.0031628862,0.0062331376,0.050953016,0.0020932902,0.93705297],"study_design_scores_gemma":[0.0004905195,0.00011377031,0.0017411779,0.000021981848,0.00001131336,0.00001099675,0.000009427733,0.17131214,0.22666147,0.004497235,0.594583,0.0005469853],"about_ca_topic_score_codex":0.0000075911476,"about_ca_topic_score_gemma":0.0000032944893,"teacher_disagreement_score":0.936506,"about_ca_system_score_codex":0.000102260194,"about_ca_system_score_gemma":0.00004316704,"threshold_uncertainty_score":0.70929617},"labels":[],"label_agreement":null},{"id":"W2395638176","doi":"10.29173/cais888","title":"Ontology-based Indexing Technologies in Information Retrieval: Building a Topic Map (ISO 13250) for a Mathematics Education Database","year":2016,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Search engine indexing; Library science; Computer science; Ontology; Information retrieval; Database; World Wide Web; Philosophy","score_opus":0.028516129917828464,"score_gpt":0.2911053196894261,"score_spread":0.2625891897715976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395638176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6139379,0.001065907,0.3443262,0.036827806,0.0005719555,0.0019322726,0.00025687052,0.00036847184,0.00071261084],"genre_scores_gemma":[0.84576243,0.00014737692,0.15347089,0.00015519884,0.00003966247,0.00010980634,0.000004730309,0.000016980275,0.00029291588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974946,0.000028017645,0.0010540606,0.00040997152,0.0004574253,0.00055592763],"domain_scores_gemma":[0.9711323,0.00046863948,0.0017410127,0.00049012323,0.026097622,0.00007034191],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011954701,0.00035223385,0.00062907854,0.0006913486,0.0001229605,0.0013823068,0.002744098,0.0003647764,0.0000058695114],"category_scores_gemma":[0.0344676,0.00026730116,0.00020156908,0.0009809579,0.00061612274,0.023899065,0.00089242554,0.00031304292,0.000002057582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017279889,0.000590556,0.049421597,0.0036959243,0.00010999392,9.351095e-7,0.020969618,0.000013019761,0.057580873,0.6397887,0.002187573,0.22546841],"study_design_scores_gemma":[0.001851066,0.0006658011,0.0063857185,0.00987531,0.00024091828,0.000039919873,0.0060725287,0.020138986,0.52911407,0.33185342,0.09273759,0.0010246625],"about_ca_topic_score_codex":0.00013910438,"about_ca_topic_score_gemma":0.00004069532,"teacher_disagreement_score":0.4715332,"about_ca_system_score_codex":0.000295683,"about_ca_system_score_gemma":0.0008751107,"threshold_uncertainty_score":0.99997795},"labels":[],"label_agreement":null},{"id":"W2395887233","doi":"","title":"University of Waterloo at TREC 2015 Microblog Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Microblogging; Exploit; Social media; Information retrieval; Relevance (law); Word (group theory); Query expansion; World Wide Web; Mathematics","score_opus":0.0386870167005127,"score_gpt":0.26424134556232476,"score_spread":0.22555432886181206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395887233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32989463,0.00033767198,0.6574223,0.001091771,0.00015200877,0.00028226545,0.000014667981,0.0006629161,0.010141728],"genre_scores_gemma":[0.9489643,0.000048453738,0.041312058,0.00004073548,0.000013489461,2.1819689e-7,0.000006472258,0.00000784057,0.009606437],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985613,0.00010085822,0.0002323469,0.00045425913,0.0003647506,0.00028648946],"domain_scores_gemma":[0.99824816,0.00006069702,0.00020113186,0.0007948011,0.0004918354,0.00020336435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038107837,0.00017303386,0.0003282477,0.0001337738,0.00007255063,0.000039133873,0.0013815901,0.000112687456,0.000116562536],"category_scores_gemma":[0.000077982266,0.00017003858,0.00010151809,0.0005596566,0.00020590842,0.0005204067,0.0005719574,0.00015322697,0.00022337442],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013928054,0.0010467926,0.014063878,0.00017755834,0.00041575477,0.00050789566,0.031775944,0.00022836665,0.5589889,0.16311967,0.06698333,0.16129906],"study_design_scores_gemma":[0.0031688064,0.001276995,0.005170565,0.00015310204,0.00014805951,0.00010679607,0.00085600076,0.028741227,0.83347607,0.044568256,0.080632396,0.0017017171],"about_ca_topic_score_codex":0.00018490972,"about_ca_topic_score_gemma":0.00013264231,"teacher_disagreement_score":0.61906964,"about_ca_system_score_codex":0.00016968032,"about_ca_system_score_gemma":0.00020016303,"threshold_uncertainty_score":0.69339716},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.04780621551233317,"score_gpt":0.32450437745493305,"score_spread":0.2766981619425999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398387993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10023661,0.003671511,0.89393884,0.000061066836,0.000013092533,0.00040321713,0.000006197003,0.0001162711,0.0015531719],"genre_scores_gemma":[0.9219581,0.00045563362,0.07715297,0.000026398442,0.000011814496,0.00013430654,0.000008275831,0.000005897666,0.00024660886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916786,0.000099826386,0.00021791033,0.0002755738,0.00013473723,0.00010406556],"domain_scores_gemma":[0.99896705,0.0002304541,0.00015408054,0.00038201248,0.00021558264,0.00005082064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104608,0.000107765634,0.00016527098,0.00016083174,0.00020896787,0.00003654369,0.00023047005,0.00005215218,0.000018312321],"category_scores_gemma":[0.0000994167,0.00009607228,0.000019286124,0.0002489443,0.00044094637,0.0003775311,0.00028615023,0.00005176086,0.0000026345206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015238961,0.00003082849,0.0011757328,0.000014580086,0.000021092781,1.4000223e-7,0.0014362328,8.77321e-7,0.00093578524,0.8873763,0.000039151077,0.108954035],"study_design_scores_gemma":[0.00025563175,0.000045502944,0.004524725,0.0000042686625,0.00008796801,0.000009244351,0.0003493918,0.0020417364,0.06745026,0.923468,0.0015883624,0.0001749448],"about_ca_topic_score_codex":0.000033313507,"about_ca_topic_score_gemma":0.00002185844,"teacher_disagreement_score":0.8217215,"about_ca_system_score_codex":0.000014323112,"about_ca_system_score_gemma":0.000024481777,"threshold_uncertainty_score":0.3917714},"labels":[],"label_agreement":null},{"id":"W2400722199","doi":"10.31234/osf.io/qs735_v1","title":"The fan effect in overlapping data sets and logical inference","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inference; Computer science; Scope (computer science); Cognition; Cognitive architecture; Logical conjunction; Logical data model; Artificial intelligence; Psychology; Programming language; Data modeling; Database","score_opus":0.026250425279193152,"score_gpt":0.3625813832382834,"score_spread":0.33633095795909024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400722199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011469468,0.00019988089,0.9811171,0.0011291183,0.00002450907,0.000108385975,3.452365e-7,0.000154848,0.0057963026],"genre_scores_gemma":[0.9672509,0.00008696502,0.032155067,0.0003379828,0.000002996558,0.000008331323,0.0000012903697,0.000001170464,0.00015528778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992509,0.00007698584,0.0001245397,0.00031710637,0.00009116124,0.00013932807],"domain_scores_gemma":[0.9982705,0.0007649604,0.000023762947,0.00090857316,0.000013245143,0.000018975941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005128146,0.00006999345,0.000108849395,0.000062902785,0.00008817283,0.00015613965,0.0012776955,0.000029643856,0.0000014925171],"category_scores_gemma":[0.0003028754,0.000040535575,0.000011756483,0.0004269944,0.000052112464,0.0003838044,0.0017134096,0.00011127692,0.000002383459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031895559,0.000014408897,0.025794424,0.000008350721,0.000012540867,0.000007871806,0.000039003135,0.000010271383,0.0006937957,0.36015123,0.00083665346,0.61242825],"study_design_scores_gemma":[0.00040743445,0.00010280844,0.12571092,0.00011286008,0.000012512051,0.0000031184366,0.000025354431,0.56880987,0.0038489806,0.29027772,0.010361954,0.00032646986],"about_ca_topic_score_codex":0.000035388886,"about_ca_topic_score_gemma":0.00019724653,"teacher_disagreement_score":0.95578146,"about_ca_system_score_codex":0.000016346712,"about_ca_system_score_gemma":0.000018772838,"threshold_uncertainty_score":0.23742974},"labels":[],"label_agreement":null},{"id":"W2401653906","doi":"","title":"Textual Entailment - Fitchburg State College.","year":2008,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logical consequence; Textual entailment; Natural language processing; Artificial intelligence; Similarity (geometry); Word (group theory); Computer science; State (computer science); Mathematics; Linguistics; Algorithm; Philosophy","score_opus":0.008736516011412841,"score_gpt":0.2566495886352712,"score_spread":0.24791307262385837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401653906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014822118,0.00034545275,0.9811247,0.00013113968,0.0000049009354,0.00020047359,0.0000102270815,0.00014721217,0.003213805],"genre_scores_gemma":[0.9814936,0.00026657412,0.016787415,0.00006251687,0.0000142866165,0.00014792244,0.000004451289,0.0000046131636,0.0012186529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993419,0.00004431787,0.00018971309,0.00019590081,0.00011723317,0.000110905676],"domain_scores_gemma":[0.9991895,0.00014812472,0.00009723164,0.00044430306,0.00007662669,0.00004424083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023002019,0.00008773475,0.0001423597,0.00008223649,0.0001951343,0.000011653423,0.00038709026,0.000022225622,0.000011473116],"category_scores_gemma":[0.000011025726,0.00007877503,0.00003266595,0.00033436916,0.00032067884,0.0002577777,0.0001452113,0.000051361858,0.000007530362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007149585,0.00003791717,0.00009471434,0.0000050388658,0.000012878515,8.44963e-7,0.0003458794,0.000010441769,0.0008583174,0.981462,0.00016963792,0.01699519],"study_design_scores_gemma":[0.00010518034,0.000040591884,0.00037471345,0.0000028453835,0.0000096066,0.000016651424,0.00033953984,0.0000976757,0.06926068,0.9137495,0.015877813,0.00012518237],"about_ca_topic_score_codex":0.0000059845347,"about_ca_topic_score_gemma":0.0000014829438,"teacher_disagreement_score":0.96667147,"about_ca_system_score_codex":0.000011460258,"about_ca_system_score_gemma":0.00003350075,"threshold_uncertainty_score":0.32123527},"labels":[],"label_agreement":null},{"id":"W2406374727","doi":"","title":"Is paper uncitedness a function of the alphabet","year":2015,"lang":"en","type":"article","venue":"ISSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Citation; Audience measurement; Presentation (obstetrics); Computer science; Information retrieval; Argument (complex analysis); Function (biology); Order (exchange); Visibility; Citation impact; Product (mathematics); Advertising; World Wide Web; Mathematics; Geography; Business","score_opus":0.03159327343030376,"score_gpt":0.2817840549621772,"score_spread":0.2501907815318734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406374727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023520373,0.00020292378,0.96737105,0.0020439131,0.0002509113,0.00009426573,0.0000010149282,0.0002025906,0.0063129473],"genre_scores_gemma":[0.9841164,0.000002407529,0.013905037,0.0010216716,0.000026460637,0.0000059386457,3.0636923e-7,0.000004149766,0.00091768184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993786,0.00003154365,0.0001132848,0.00014580235,0.00024198265,0.0000887448],"domain_scores_gemma":[0.9991551,0.000015651189,0.00007771892,0.00058792083,0.00012545838,0.000038119273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014808978,0.000057065896,0.00008462873,0.00003656775,0.000028907025,0.000020085443,0.00053530076,0.000031198615,0.000014545583],"category_scores_gemma":[0.000038871873,0.000036408495,0.00005718004,0.00046357885,0.00003433134,0.00035129365,0.00017290373,0.00005409355,0.000017299662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040611354,0.00038887386,0.029001154,0.000039333045,0.00019269073,0.000008581739,0.00801475,0.00043818378,0.049180888,0.22628279,0.21805747,0.46835467],"study_design_scores_gemma":[0.0006727345,0.00022712935,0.030503301,0.00007150313,0.000068909736,0.0000089401265,0.00015462116,0.018985743,0.15786378,0.2949487,0.49604854,0.00044608963],"about_ca_topic_score_codex":0.000017818424,"about_ca_topic_score_gemma":0.0000058499327,"teacher_disagreement_score":0.96059597,"about_ca_system_score_codex":0.00002645438,"about_ca_system_score_gemma":0.00004151529,"threshold_uncertainty_score":0.14846954},"labels":[],"label_agreement":null},{"id":"W2406432149","doi":"","title":"Learning Relationship between Authors' Activity and Sentiments: A case study of online medical forums","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Representation (politics); Focus (optics); Class (philosophy); Domain (mathematical analysis); Conditional random field; Support vector machine; Data science; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Mathematics","score_opus":0.08065363470453168,"score_gpt":0.390861903818522,"score_spread":0.3102082691139903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406432149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55279857,0.0000064444343,0.44678205,0.0001258332,0.000008000724,0.00007872388,2.1497223e-7,0.000116059455,0.00008409697],"genre_scores_gemma":[0.9373075,7.008105e-7,0.06238392,0.000010608939,0.000016484231,0.000004309972,0.0000011780309,0.0000045329766,0.00027077144],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987456,0.00020854041,0.00021837327,0.0002562959,0.00044464492,0.00012653736],"domain_scores_gemma":[0.9990518,0.0002643764,0.00011875041,0.00029284914,0.00008583834,0.0001863505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008044245,0.00008514868,0.0001940409,0.00013561232,0.00008045816,0.000026732996,0.00023918302,0.000064389205,0.0000031846084],"category_scores_gemma":[0.0006090438,0.00007201723,0.000024363613,0.0003907183,0.000037710877,0.00047047937,0.00044706196,0.00024957256,0.0000014545749],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027129213,0.00039773117,0.9495851,0.0000040883065,0.000038425333,0.00022754313,0.0031209653,0.000021178717,0.000014517295,0.00086707686,0.000053083364,0.04566759],"study_design_scores_gemma":[0.0061745555,0.0067876056,0.46091974,0.00010987387,0.00035975178,0.0014451119,0.023569051,0.46240386,0.00234499,0.033979576,0.00059143174,0.0013144555],"about_ca_topic_score_codex":0.00045674315,"about_ca_topic_score_gemma":0.00034403472,"teacher_disagreement_score":0.48866534,"about_ca_system_score_codex":0.000028143711,"about_ca_system_score_gemma":0.00004835476,"threshold_uncertainty_score":0.29367775},"labels":[],"label_agreement":null},{"id":"W2407694321","doi":"","title":"SemQuest: University of Houston's Semantics-based Question Answering System.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Question answering; Computer science; Preprocessor; Redundancy (engineering); Natural language processing; Semantics (computer science); Relevance (law); Extractor; Sentence; Artificial intelligence; Information retrieval; Programming language; Engineering","score_opus":0.007996082422250674,"score_gpt":0.22139675349799368,"score_spread":0.213400671075743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407694321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010720207,0.00011381706,0.9869036,0.000017300688,0.00000575907,0.000117164716,0.0000023367184,0.00016918877,0.0019505972],"genre_scores_gemma":[0.94209117,0.00002251475,0.057819337,0.0000035243236,0.000004798838,0.000005009454,0.000001917607,0.0000033273172,0.00004840662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995491,0.000064082305,0.00011543659,0.00014088431,0.00006573749,0.000064755746],"domain_scores_gemma":[0.9992586,0.00006524267,0.00014666437,0.00038662378,0.00011734513,0.000025568166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003467503,0.000062873536,0.00013165835,0.00009027202,0.000084278276,0.0000058665905,0.00032306198,0.000033833825,0.000002791753],"category_scores_gemma":[0.0000070601773,0.0000653061,0.00002939842,0.00024077552,0.00022241645,0.00020246212,0.00006756577,0.00003738243,0.0000012032617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012686113,0.000024594498,0.00020241071,0.00006520511,0.00000862944,4.0451357e-7,0.00036217138,0.00002268167,0.0013960111,0.9920465,0.0000020938853,0.0058566583],"study_design_scores_gemma":[0.00022143085,0.00012544678,0.0017276129,0.000089660614,0.000106314386,0.0000066358734,0.0018221954,0.0034329316,0.38028088,0.61090684,0.0010078674,0.00027219136],"about_ca_topic_score_codex":0.000055476285,"about_ca_topic_score_gemma":0.000005696246,"teacher_disagreement_score":0.931371,"about_ca_system_score_codex":0.000011811803,"about_ca_system_score_gemma":0.000023403638,"threshold_uncertainty_score":0.26631054},"labels":[],"label_agreement":null},{"id":"W2413001881","doi":"10.29173/cais250","title":"A Method for Comparing Large Scale Inter-indexer Consistency Using IR Modeling","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Consistency (knowledge bases); Humanities; Geometry; Philosophy","score_opus":0.05886262153393068,"score_gpt":0.3156789201341757,"score_spread":0.256816298600245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2413001881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3897628,0.0006306852,0.6042246,0.0021918695,0.0002381961,0.0009336302,0.000077148594,0.00010613542,0.0018349059],"genre_scores_gemma":[0.6983088,0.000060034636,0.30057696,0.00021226311,0.00010269311,0.000081410784,0.0000021100384,0.000041884814,0.00061381265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959506,0.000080639904,0.001357529,0.000886816,0.00062748074,0.0010969341],"domain_scores_gemma":[0.9252276,0.00032570638,0.0015967728,0.0005426294,0.072049,0.00025829795],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0016551238,0.000600035,0.0013601469,0.0003822287,0.000378104,0.0045119044,0.0037528859,0.00035966394,0.00003452291],"category_scores_gemma":[0.0071443096,0.0005347161,0.0006535014,0.0009357871,0.0005471719,0.022080665,0.0023229455,0.0005765671,0.000004581647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037110355,0.0021132545,0.12864037,0.0058041317,0.0016862631,0.000005035528,0.18413782,0.0038052145,0.15378349,0.37133244,0.0060051507,0.14231575],"study_design_scores_gemma":[0.0006228177,0.00020173773,0.0007877597,0.0013677801,0.0002971996,0.00005326469,0.0027512095,0.91086626,0.02723973,0.049687665,0.005558267,0.0005663102],"about_ca_topic_score_codex":0.0012222274,"about_ca_topic_score_gemma":0.0000703387,"teacher_disagreement_score":0.90706104,"about_ca_system_score_codex":0.00020508525,"about_ca_system_score_gemma":0.00043771073,"threshold_uncertainty_score":0.99971044},"labels":[],"label_agreement":null},{"id":"W2415886958","doi":"10.29173/cais353","title":"Comparison of the Effectiveness of Related Functions in Web of Science and Scopus","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Scopus; Web of science; Function (biology); Humanities; Philosophy; Political science; MEDLINE; Biology","score_opus":0.023271217397422186,"score_gpt":0.2865563339678965,"score_spread":0.2632851165704743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2415886958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99364305,0.0009333407,0.00043820599,0.0008606718,0.00020300342,0.00078023406,0.00004475715,0.000021929302,0.003074834],"genre_scores_gemma":[0.99795336,0.00009870126,0.0016868571,0.00001542194,0.0000097662705,0.000031313986,4.601532e-7,0.000014031894,0.00019011619],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968115,0.00014970636,0.0011658211,0.00049508194,0.0009420682,0.00043581688],"domain_scores_gemma":[0.9378573,0.0006190034,0.0021533149,0.0005034239,0.058762416,0.00010457206],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0027109343,0.0002992512,0.0010318524,0.00050643616,0.00014525617,0.000527819,0.0032735409,0.00020519613,0.000012570685],"category_scores_gemma":[0.020069094,0.00022062863,0.00020431323,0.0034743662,0.005797258,0.010670738,0.0018040499,0.00044593375,7.9550875e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007594339,0.00042650723,0.5254568,0.0011934943,0.000086668624,1.7024765e-7,0.013556768,0.000073397365,0.3911813,0.060087606,0.000156726,0.007704661],"study_design_scores_gemma":[0.00048698357,0.00044816692,0.42989656,0.0025926107,0.00011956371,0.000011646402,0.0016595992,0.012099999,0.5356587,0.01643258,0.00037407468,0.00021951845],"about_ca_topic_score_codex":0.0010339604,"about_ca_topic_score_gemma":0.00004446814,"teacher_disagreement_score":0.14447741,"about_ca_system_score_codex":0.000115734365,"about_ca_system_score_gemma":0.0009358456,"threshold_uncertainty_score":0.99690837},"labels":[],"label_agreement":null},{"id":"W2460693621","doi":"10.29173/cais401","title":"Inedxing as Problem Solving: A Cognitive Approach to Consistency","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Cognition; Psychology; Humanities; Cognitive psychology; Computer science; Philosophy; Artificial intelligence","score_opus":0.020619320318016783,"score_gpt":0.25436363081794305,"score_spread":0.23374431049992628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460693621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8455329,0.00012567363,0.04308344,0.0028090216,0.00006833939,0.0017448795,0.00002583634,0.00035467293,0.106255226],"genre_scores_gemma":[0.92408144,0.000021902379,0.074651085,0.00049904705,0.00003677043,0.00018276536,0.0000017297167,0.000024375262,0.0005008899],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99734557,0.000032616954,0.00070446444,0.00066574046,0.0006632074,0.00058842776],"domain_scores_gemma":[0.9437836,0.00020161193,0.0009179486,0.0003903451,0.054459397,0.00024712167],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005816294,0.00037314426,0.0006577084,0.00034796188,0.00018877558,0.002853125,0.0035573,0.00015550297,0.00001460768],"category_scores_gemma":[0.01255035,0.0002929573,0.00023596923,0.0011974687,0.00046714497,0.014453533,0.0018245536,0.00034214853,0.00001748048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014017354,0.0013184058,0.06461519,0.0010816918,0.0006700352,0.0000040599875,0.19160378,0.000030102943,0.1373396,0.51434207,0.009690848,0.07916402],"study_design_scores_gemma":[0.0023368122,0.0023589868,0.06595731,0.0031171835,0.0004995032,0.00030632183,0.025598295,0.015820028,0.5109529,0.35266954,0.01716915,0.0032139788],"about_ca_topic_score_codex":0.00029680738,"about_ca_topic_score_gemma":0.0000041474136,"teacher_disagreement_score":0.3736133,"about_ca_system_score_codex":0.00007066436,"about_ca_system_score_gemma":0.00028534152,"threshold_uncertainty_score":0.99995226},"labels":[],"label_agreement":null},{"id":"W2463112553","doi":"10.1145/2911451.2914704","title":"Simple Dynamic Emission Strategies for Microblog Filtering","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Microblogging; Computer science; Social media; Simple (philosophy); Key (lock); Human–computer interaction; World Wide Web; Computer security","score_opus":0.01252131438409449,"score_gpt":0.3000183106035962,"score_spread":0.2874969962195017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463112553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005288783,0.000017124094,0.99264336,0.00044936562,0.000025462035,0.00010306451,0.0000018788054,0.0005410689,0.0009299007],"genre_scores_gemma":[0.6358959,0.000008596487,0.3630192,0.00007667579,0.00000897129,0.000019861154,0.0000010862709,0.0000060174903,0.00096369395],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929017,0.000009793495,0.00015026047,0.00027422037,0.00007353893,0.00020199014],"domain_scores_gemma":[0.9993567,0.00009338453,0.000051320447,0.00040663034,0.000050794868,0.000041166313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096231845,0.0000919448,0.000106221465,0.0000689672,0.000067791196,0.00008398136,0.000532695,0.00003621626,0.000025578971],"category_scores_gemma":[0.000020056108,0.00005557128,0.000066671775,0.00011217932,0.0000212054,0.0007397831,0.00017492691,0.000022355664,0.000011090408],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017417482,0.000009000056,0.000038963477,0.000005560184,0.0000057547436,8.836938e-7,0.00002376453,0.000005051144,0.8777695,0.035451423,0.0013191183,0.08536929],"study_design_scores_gemma":[0.00029074724,0.000096868935,0.00017376684,0.000037601225,0.0000059130716,0.0000058704945,0.000033124117,0.030287705,0.48499337,0.46568504,0.018080646,0.00030933667],"about_ca_topic_score_codex":0.0000059215267,"about_ca_topic_score_gemma":0.000016264936,"teacher_disagreement_score":0.6306071,"about_ca_system_score_codex":0.000041265095,"about_ca_system_score_gemma":0.000027096035,"threshold_uncertainty_score":0.22661309},"labels":[],"label_agreement":null},{"id":"W2470107876","doi":"10.29173/cais728","title":"Using Genetics in Information Filtering","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Parsing; Cognition; Computer science; Cognitive science; Information filtering system; Artificial intelligence; Natural language processing; Information retrieval; Psychology","score_opus":0.02763279480462613,"score_gpt":0.2640034070986742,"score_spread":0.23637061229404807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470107876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9675323,0.000039417155,0.029272012,0.00044458386,0.000046082554,0.00029098924,0.000006837571,0.00006686026,0.002300964],"genre_scores_gemma":[0.9403918,0.0000378506,0.05938503,0.00011433518,0.000016598447,0.000020369529,7.1494406e-7,0.000007361277,0.000025984245],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986069,0.000012693455,0.0005405691,0.00019089338,0.00034850955,0.00030043742],"domain_scores_gemma":[0.9800289,0.000048418806,0.00065814675,0.00024304197,0.018957423,0.00006401855],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00031715046,0.00017588497,0.00030664302,0.0002877753,0.000059768015,0.0020160312,0.0021494203,0.00009618998,0.000008363812],"category_scores_gemma":[0.0030770618,0.00014555966,0.000093917435,0.00066419377,0.00014089784,0.02664631,0.0009515642,0.00018338358,0.000002995837],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003971947,0.00023767416,0.33703473,0.0006867282,0.00012838299,0.0000014572587,0.077600464,0.00072910835,0.36216336,0.07310627,0.0013042346,0.14696787],"study_design_scores_gemma":[0.0007604338,0.00028220017,0.18210098,0.00072766445,0.00005627063,0.000046869474,0.001971389,0.21259642,0.52477705,0.06502316,0.010785296,0.0008722318],"about_ca_topic_score_codex":0.00022735358,"about_ca_topic_score_gemma":0.0000061456108,"teacher_disagreement_score":0.2118673,"about_ca_system_score_codex":0.00006976385,"about_ca_system_score_gemma":0.00010101469,"threshold_uncertainty_score":0.99902},"labels":[],"label_agreement":null},{"id":"W2473169082","doi":"","title":"Fuzziness for classification and visual query interface: platform independent query model with self-adaptive fuzzy capabilities","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Fuzzy logic; Data mining; Classifier (UML); Machine learning; Artificial intelligence; The Internet; Fuzzy set; Interface (matter); Information retrieval; World Wide Web","score_opus":0.04484659630979332,"score_gpt":0.2836074568777472,"score_spread":0.23876086056795387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473169082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07103642,0.000030411626,0.9238967,0.00004533455,0.00003181645,0.00044150546,0.0000024401254,0.0006094963,0.0039059315],"genre_scores_gemma":[0.62919945,0.000010940307,0.37032855,0.000046721474,0.000013900411,0.00014777122,0.0000016630696,0.000012524672,0.00023846552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985801,0.000020886484,0.0002986167,0.00057621236,0.00024298653,0.00028119617],"domain_scores_gemma":[0.9988684,0.00008732685,0.00015909913,0.00040562986,0.0003876229,0.0000919375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026771153,0.00023096483,0.00025922837,0.00019330507,0.000121231154,0.000084054045,0.00041473188,0.00010637663,0.00000352622],"category_scores_gemma":[0.000022909004,0.00017633724,0.00005453556,0.00021075334,0.00010616495,0.0016412982,0.00020684215,0.00013241083,0.000002928723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003681588,0.0006395005,0.0024147267,0.00012049565,0.00026251233,0.0000038245685,0.017497152,0.0003328187,0.0025135952,0.94445544,0.00030897933,0.031082781],"study_design_scores_gemma":[0.00042865958,0.00052823167,0.0015423546,0.000029588582,0.000041612755,0.000009945296,0.0019487117,0.8925918,0.021944478,0.08042609,0.000051545856,0.00045702292],"about_ca_topic_score_codex":0.00008665679,"about_ca_topic_score_gemma":0.0002646856,"teacher_disagreement_score":0.89225894,"about_ca_system_score_codex":0.00013209393,"about_ca_system_score_gemma":0.00010319792,"threshold_uncertainty_score":0.7190824},"labels":[],"label_agreement":null},{"id":"W2495878820","doi":"10.29173/cais858","title":"Information Behavior Research: Where Have We Been, Where Are We Going?","year":2016,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Sociology; Political science; Philosophy","score_opus":0.0691220101564011,"score_gpt":0.3229137776906782,"score_spread":0.2537917675342771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2495878820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6589947,0.015187489,0.021948952,0.2731422,0.0013382719,0.003992988,0.0014754592,0.0007826267,0.023137366],"genre_scores_gemma":[0.97308034,0.01017545,0.0066990377,0.00013872763,0.00020009046,0.0001575986,0.0000023807265,0.00004808989,0.009498294],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948778,0.00014298392,0.0013483401,0.0006443371,0.0017753338,0.0012112187],"domain_scores_gemma":[0.8966934,0.00048014105,0.002203339,0.0007737091,0.09950893,0.00034045443],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0020740167,0.00059961167,0.0009488102,0.0006745619,0.00040287987,0.0053161234,0.0056931474,0.0005451635,0.00011259385],"category_scores_gemma":[0.01310944,0.0004368095,0.0004467275,0.0014187734,0.0018570708,0.05488574,0.0029451314,0.00088991906,0.00005586414],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023872065,0.00067992567,0.19570753,0.0025420592,0.0003050433,0.000012601048,0.08759072,0.000004587176,0.024251023,0.14231814,0.1058692,0.44048044],"study_design_scores_gemma":[0.0009879224,0.0008256314,0.020539377,0.008698791,0.00023220047,0.00009243149,0.008031848,0.00094528607,0.078681804,0.03961861,0.84038895,0.0009571466],"about_ca_topic_score_codex":0.00039473604,"about_ca_topic_score_gemma":0.00024270239,"teacher_disagreement_score":0.7345198,"about_ca_system_score_codex":0.00037232667,"about_ca_system_score_gemma":0.00065004895,"threshold_uncertainty_score":0.9998084},"labels":[],"label_agreement":null},{"id":"W2500612743","doi":"10.4018/978-1-60960-040-2.ch011","title":"Exploring Virtual Communities with the Internet Community Text Analyzer (ICTA)","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; The Internet; World Wide Web; Set (abstract data type); Visualization; Focus (optics); Virtual community; Social network (sociolinguistics); Interface (matter); Data science; Social network analysis; Social media; Data mining","score_opus":0.09994772145408938,"score_gpt":0.2603172478232629,"score_spread":0.1603695263691735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2500612743","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088394375,0.00010846399,0.18185766,0.00006657062,0.00010375504,0.00026125528,0.000019868157,0.00073234225,0.8159661],"genre_scores_gemma":[0.950146,0.000026132486,0.006234077,0.0007514763,0.00008854657,0.00009005475,0.000007376917,0.00006753288,0.042588808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788505,0.00024100012,0.00045343983,0.00037895815,0.0005894314,0.00045214806],"domain_scores_gemma":[0.995656,0.00021116239,0.0004612833,0.0032702596,0.00026175575,0.00013950339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004408842,0.0006883775,0.00069053826,0.00017282726,0.0005008,0.0003134951,0.005019529,0.00021745995,0.000032376138],"category_scores_gemma":[0.000008492039,0.0004831784,0.00030047834,0.000079589794,0.0006665847,0.0005086992,0.002429487,0.0016385769,0.000106871346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001953869,0.000016689355,0.000022753731,0.000008487332,0.00026689176,0.000023279606,0.002591869,0.0000056734,0.0000023010077,0.97647226,0.0008501782,0.019720085],"study_design_scores_gemma":[0.00060294475,0.0014115026,0.00022207851,0.0011055237,0.0005112484,0.00020872137,0.0017683085,0.0005901743,0.0007621526,0.8788654,0.11136917,0.00258278],"about_ca_topic_score_codex":0.0020311994,"about_ca_topic_score_gemma":0.0043093106,"teacher_disagreement_score":0.949262,"about_ca_system_score_codex":0.00028443348,"about_ca_system_score_gemma":0.000107248576,"threshold_uncertainty_score":0.999762},"labels":[],"label_agreement":null},{"id":"W2507709051","doi":"10.1145/2960811.2960813","title":"Relaxing Orthogonality Assumption in Conceptual Text Document Similarity","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Orthogonality; Similarity (geometry); Cosine similarity; Information retrieval; Computer science; Space (punctuation); Measure (data warehouse); Similarity measure; Key (lock); Natural language processing; Artificial intelligence; Data mining; Mathematics; Pattern recognition (psychology)","score_opus":0.01983061498926167,"score_gpt":0.2893450317022357,"score_spread":0.26951441671297405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507709051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052149568,0.000028041028,0.9420997,0.0018329744,0.00004127697,0.00010676708,5.2475883e-7,0.0003810624,0.003360123],"genre_scores_gemma":[0.8826103,0.000025198742,0.116428465,0.00027404766,0.000017690638,0.000016576072,6.014037e-7,0.0000042487895,0.00062287715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860656,0.00011538245,0.00030870663,0.00043119796,0.00028623614,0.00025192363],"domain_scores_gemma":[0.99906963,0.00016092559,0.00009026428,0.00055423455,0.000060329978,0.000064625085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006069969,0.00011740411,0.00016722792,0.00011023394,0.000047803813,0.000044369197,0.00052897993,0.00006755923,0.00015468872],"category_scores_gemma":[0.000102703176,0.000078538,0.000066044544,0.00032651835,0.00008448685,0.0011770264,0.0002874765,0.00009953947,0.00007754451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057943384,0.000072284,0.04029271,0.0000030448402,0.000012787572,0.000014730635,0.00021810703,0.000018904322,0.006933616,0.7827454,0.00053303514,0.16914958],"study_design_scores_gemma":[0.0019648753,0.00022744453,0.21168602,0.0001929372,0.000018240924,0.000016761227,0.00011695539,0.005723301,0.09904514,0.647534,0.032128286,0.0013460448],"about_ca_topic_score_codex":0.00004929285,"about_ca_topic_score_gemma":0.00023576868,"teacher_disagreement_score":0.8304607,"about_ca_system_score_codex":0.00019607287,"about_ca_system_score_gemma":0.000031239982,"threshold_uncertainty_score":0.3202687},"labels":[],"label_agreement":null},{"id":"W251035542","doi":"10.1007/0-306-47542-1_12","title":"Learning Negotiations with Web-Based Systems","year":2006,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; International Institute for Applied Systems Analysis","keywords":"Negotiation; World Wide Web; Computer science; Political science; Law","score_opus":0.011691515903564164,"score_gpt":0.226640238797568,"score_spread":0.21494872289400385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W251035542","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000066279526,0.00032854785,0.3682723,0.00025086978,0.00021060278,0.00046063834,0.0000063630196,0.0019076025,0.62855643],"genre_scores_gemma":[0.023491561,0.000008623656,0.016613027,0.00056904444,0.00046336983,0.00018794015,0.00013221795,0.00022189961,0.95831233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99567634,0.00009192472,0.00090840785,0.0013423368,0.0012483466,0.00073265913],"domain_scores_gemma":[0.9965613,0.00023196718,0.0011014511,0.0013737782,0.00046381162,0.000267725],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00061015796,0.00081258186,0.000855552,0.0011429894,0.00032696806,0.0012011139,0.0027541039,0.0012692136,0.000031017626],"category_scores_gemma":[0.00006207775,0.0007449184,0.0002967015,0.00017858195,0.00026779313,0.0017811124,0.00038528428,0.0036263424,0.00006569751],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027460208,0.000031492385,0.00043315216,0.0002051772,0.0005752682,0.00017775134,0.00032116007,0.0136793135,0.00036123706,0.5547318,0.40384504,0.025611134],"study_design_scores_gemma":[0.000521751,0.00012577105,0.000009924408,0.00044043292,0.0001553506,0.00003162588,0.000012156708,0.023975976,0.00010614606,0.0113359755,0.96212333,0.0011615624],"about_ca_topic_score_codex":0.000055469274,"about_ca_topic_score_gemma":0.000015331922,"teacher_disagreement_score":0.55827826,"about_ca_system_score_codex":0.0004993347,"about_ca_system_score_gemma":0.000720145,"threshold_uncertainty_score":0.9998357},"labels":[],"label_agreement":null},{"id":"W2512574971","doi":"10.1002/9781119159704.ch2","title":"The Nature‐Science Approach: Some Further Consequences","year":2016,"lang":"en","type":"other","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Emera (Canada)","funders":"","keywords":"Natural (archaeology); Cognitive dissonance; Natural science; Energy (signal processing); Characterization (materials science); Set (abstract data type); Natural organic matter; Epistemology; Computer science; Psychology; Environmental science; Mathematics; Physics; Geography; Philosophy; Social psychology","score_opus":0.010198594719120541,"score_gpt":0.28774775309113343,"score_spread":0.2775491583720129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512574971","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2300966e-7,0.001420679,0.377347,0.0012233946,0.00022776391,0.00017241716,0.0000016301491,0.0010246658,0.6185823],"genre_scores_gemma":[0.0008248833,0.0007041496,0.14884615,0.0006782447,0.00023311976,0.00005755763,6.3561384e-7,0.000110660476,0.8485446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975882,0.00005930755,0.00021450868,0.00085492776,0.00076450454,0.000518527],"domain_scores_gemma":[0.99752575,0.00012795179,0.00028789203,0.0018745327,0.0000805855,0.00010331085],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005926843,0.00030682966,0.0002715268,0.00035825,0.0002495747,0.00037115105,0.005567855,0.0002844428,0.00021718418],"category_scores_gemma":[0.00007511214,0.00014297856,0.00012117521,0.0005798954,0.0020403196,0.00050027337,0.0006891476,0.00035475352,0.0003938716],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.032163e-7,0.000009991471,0.000002764754,0.0000031178645,0.000023335157,0.0000028579834,0.000017835471,1.0235161e-7,0.00031272307,0.78401357,0.19225644,0.02335686],"study_design_scores_gemma":[0.000052885352,0.000013380255,0.0000028322736,0.00003384298,0.000007366081,0.000010620998,0.00001392355,0.00020981104,0.002251479,0.09438753,0.9026604,0.00035588114],"about_ca_topic_score_codex":0.00002727918,"about_ca_topic_score_gemma":0.00002767075,"teacher_disagreement_score":0.71040404,"about_ca_system_score_codex":0.00007480077,"about_ca_system_score_gemma":0.0002540336,"threshold_uncertainty_score":0.9998125},"labels":[],"label_agreement":null},{"id":"W2521029362","doi":"10.1045/september2016-atanassova","title":"Temporal Properties of Recurring In-text References","year":2016,"lang":"en","type":"article","venue":"D-Lib Magazine","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Section (typography); Rhetorical question; Computer science; Linguistics; History; Philosophy","score_opus":0.028875440863421056,"score_gpt":0.25641390908519507,"score_spread":0.227538468221774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521029362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6675607,0.00078784424,0.31509125,0.0028715243,0.00015578307,0.00032843105,0.0000028214472,0.0006775002,0.012524169],"genre_scores_gemma":[0.9596669,0.000074454365,0.039150514,0.00003797287,0.000019188283,0.000015591599,3.7269413e-7,0.0000074330937,0.0010275784],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989047,0.00004819535,0.00032704615,0.00030111152,0.00021186007,0.00020708115],"domain_scores_gemma":[0.99920154,0.000033364217,0.00013953377,0.00050187873,0.000085024854,0.00003868419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023826273,0.00011769051,0.0002305236,0.00021564506,0.000022052212,0.000022826569,0.0007057793,0.00004169554,0.000022498773],"category_scores_gemma":[0.000092563765,0.0000712857,0.000049148788,0.00047681818,0.0000852431,0.0007069067,0.00025197314,0.000065839886,0.00006218285],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003372322,0.0001828588,0.0382367,0.00007012911,0.000029789004,0.000027391261,0.0006102582,0.000007246617,0.37347034,0.062431578,0.0010483866,0.52385163],"study_design_scores_gemma":[0.001133696,0.00041850307,0.026326776,0.0013919735,0.000016111486,0.000017843544,0.000040374704,0.0025483551,0.87357175,0.052238446,0.041389808,0.00090635306],"about_ca_topic_score_codex":0.000021612781,"about_ca_topic_score_gemma":0.0000903882,"teacher_disagreement_score":0.5229452,"about_ca_system_score_codex":0.000035933634,"about_ca_system_score_gemma":0.000035029327,"threshold_uncertainty_score":0.29069465},"labels":[],"label_agreement":null},{"id":"W2523945865","doi":"10.18438/b8r90p","title":"Determining Gate Count Reliability in a Library Setting","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Turnstile; Reliability (semiconductor); Computer science; Data collection; Set (abstract data type); Statistics; Mathematics; Physics","score_opus":0.008833506208491802,"score_gpt":0.25854027912697075,"score_spread":0.24970677291847895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523945865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010887185,0.00022896324,0.8382325,0.1444849,0.00008177717,0.0003524924,0.0000047105564,0.000999797,0.004727673],"genre_scores_gemma":[0.53892124,0.0014296694,0.41810146,0.04135274,0.000033648597,0.000054546046,0.000005736046,0.000010154885,0.0000907935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845296,0.00027882098,0.0005472029,0.00025415135,0.00025013104,0.00021675462],"domain_scores_gemma":[0.9957621,0.0031739182,0.00042020337,0.0005179135,0.000034425662,0.000091445],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007772224,0.0001389614,0.0001448914,0.00028120942,0.00010157158,0.00050013774,0.0005213927,0.00006794408,0.0000564429],"category_scores_gemma":[0.0020659403,0.00010332353,0.00003539453,0.00069191883,0.000054373246,0.58242893,0.00035248557,0.0001653585,0.00003672399],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002310507,0.00007975181,0.027845286,0.00018966086,0.000012886581,0.000040379487,0.0006930625,0.0004235831,0.00059644214,0.3767528,0.0016174847,0.5915176],"study_design_scores_gemma":[0.0010457153,0.00034822786,0.042322855,0.002575715,0.000024849387,0.00006781114,0.00023216274,0.17833927,0.036632236,0.010301696,0.7272109,0.0008985796],"about_ca_topic_score_codex":0.0000013411687,"about_ca_topic_score_gemma":1.8391145e-8,"teacher_disagreement_score":0.7255934,"about_ca_system_score_codex":0.0000187861,"about_ca_system_score_gemma":0.000186006,"threshold_uncertainty_score":0.48228398},"labels":[],"label_agreement":null},{"id":"W2526489827","doi":"10.7202/1028615ar","title":"L’analyse de références bibliographiques assistée par ordinateur","year":2015,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.055436402563918165,"score_gpt":0.37142323677003247,"score_spread":0.3159868342061143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2526489827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012702374,0.035894495,0.91527486,0.018698372,0.00081542955,0.0004347049,0.0000270989,0.0013294131,0.014823237],"genre_scores_gemma":[0.5666644,0.061949175,0.35467187,0.005067917,0.00039152103,0.00019064448,0.00008059761,0.00008263596,0.01090127],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945374,0.0013336765,0.0009799512,0.0010421718,0.0011770704,0.00092972815],"domain_scores_gemma":[0.9960826,0.0003750185,0.00072134857,0.0009559503,0.0011704833,0.00069461524],"candidate_categories":["metaepi_narrow","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["bibliometrics","scholarly_communication"],"category_scores_codex":[0.0030113687,0.0005881524,0.0006434014,0.019275067,0.00024288229,0.010819186,0.0014473309,0.00029730244,0.0010121291],"category_scores_gemma":[0.00040373678,0.0006086631,0.0004047208,0.04136677,0.0005072518,0.035114687,0.0004397726,0.00047275214,0.00019853035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007162209,0.00084073626,0.13005994,0.00016142505,0.0007578682,0.0002755408,0.006265291,0.0011575494,0.0017366005,0.3571417,0.4535924,0.047939327],"study_design_scores_gemma":[0.0014176632,0.001092047,0.021587078,0.0004722792,0.0005632174,0.00016002779,0.0015046082,0.014609455,0.058003787,0.594419,0.3042474,0.0019234417],"about_ca_topic_score_codex":0.0051776804,"about_ca_topic_score_gemma":0.0008415872,"teacher_disagreement_score":0.560603,"about_ca_system_score_codex":0.00035990585,"about_ca_system_score_gemma":0.00072282006,"threshold_uncertainty_score":0.99990106},"labels":[],"label_agreement":null},{"id":"W2530746622","doi":"10.1016/b978-0-12-804412-4.00011-5","title":"Opinion Summarization and Visualization","year":2016,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of the Fraser Valley","funders":"","keywords":"Automatic summarization; Visualization; Computer science; Variety (cybernetics); Social media; Data science; Data visualization; Information retrieval; Multi-document summarization; World Wide Web; Information visualization; Artificial intelligence","score_opus":0.013690071245827141,"score_gpt":0.2738064960185678,"score_spread":0.26011642477274066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530746622","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.7532187e-7,0.00040253095,0.32464,0.000056378412,0.00012393773,0.0002034815,0.00000307519,0.00029787197,0.6742724],"genre_scores_gemma":[0.0002277947,0.0007210638,0.013201441,0.00019987284,0.00019282162,0.000020807915,0.000022601524,0.0000526691,0.9853609],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986061,0.00002600017,0.00033841297,0.00056645606,0.0002930263,0.00017001643],"domain_scores_gemma":[0.9987751,0.000048640093,0.00031517557,0.0006403498,0.00014304419,0.00007765073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016794061,0.00028779637,0.00031383903,0.00027941007,0.00010112952,0.00010685415,0.00042673192,0.00024732226,0.000020052657],"category_scores_gemma":[0.00001816833,0.00024427948,0.00008720119,0.000024877616,0.000080057755,0.00027687507,0.00034425274,0.00012260707,0.000044774104],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.330501e-7,0.000001056777,0.0000025981258,0.000011600123,0.000012647102,0.0000010997713,0.000026915352,6.998893e-8,0.00004384451,0.38587508,0.000033817087,0.61399066],"study_design_scores_gemma":[0.00008349532,0.00003217804,0.000006174768,0.0002695234,0.00001670988,0.0000051819356,2.3539124e-7,0.00028139327,0.0002392445,0.23404069,0.76473284,0.00029232877],"about_ca_topic_score_codex":7.9616704e-8,"about_ca_topic_score_gemma":0.0000025474349,"teacher_disagreement_score":0.76469904,"about_ca_system_score_codex":0.00007642039,"about_ca_system_score_gemma":0.00004596017,"threshold_uncertainty_score":0.9961428},"labels":[],"label_agreement":null},{"id":"W2534966764","doi":"10.22374/cjgim.v11i2.142","title":"Inadequate Presentation of Evidence in an Internal Medicine Conference","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of General Internal Medicine","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Presentation (obstetrics); Number needed to treat; Absolute (philosophy); Relative risk; Frequency; Family medicine; Internal medicine; Statistics; Epistemology; Mathematics; Surgery; Philosophy","score_opus":0.12257900290233292,"score_gpt":0.37820517653575025,"score_spread":0.25562617363341733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2534966764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24691476,0.0009071243,0.7345245,0.016265556,0.00066800084,0.00009869631,0.0000018203392,0.000013128658,0.0006064101],"genre_scores_gemma":[0.9894552,0.00020434598,0.008679593,0.00040870585,0.00047228026,0.0000025069733,5.2403936e-7,0.000010460496,0.0007663459],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975385,0.00021736596,0.0011336786,0.00025896466,0.00052574615,0.0003257368],"domain_scores_gemma":[0.997045,0.0002391054,0.0008182495,0.0003961744,0.00083923864,0.0006622736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011100192,0.00018833509,0.0005406649,0.0012000956,0.000029716262,0.000023776118,0.0017539848,0.000065284585,0.00026351746],"category_scores_gemma":[0.001149273,0.0001034872,0.00006795156,0.00045721172,0.0004784423,0.0015138522,0.00005897534,0.00026998145,0.0000028707173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002140637,0.00005271935,0.09888381,0.00005688296,0.00014149,0.001651748,0.0063338843,0.00014636145,0.27881104,0.030350417,0.009433927,0.57392365],"study_design_scores_gemma":[0.0142185185,0.026253788,0.30546582,0.06294937,0.00038300117,0.005272803,0.0017030443,0.04593698,0.27953082,0.24448651,0.01157809,0.002221241],"about_ca_topic_score_codex":0.024465393,"about_ca_topic_score_gemma":0.040410817,"teacher_disagreement_score":0.7425405,"about_ca_system_score_codex":0.00031622252,"about_ca_system_score_gemma":0.00047632537,"threshold_uncertainty_score":0.98203075},"labels":[],"label_agreement":null},{"id":"W2536295050","doi":"10.1109/fskd.2016.7603424","title":"Chinese term extraction from web pages based on expected point-wise mutual information","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Term (time); Lexicon; Point (geometry); Computer science; Information retrieval; Word (group theory); Mutual information; Information extraction; Artificial intelligence; Natural language processing; Precision and recall; Data mining; Mathematics","score_opus":0.006995051740656491,"score_gpt":0.26561186888879185,"score_spread":0.25861681714813534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536295050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059601516,0.0000042818683,0.9331543,0.0012872006,0.00009555187,0.00012191382,0.0000054657403,0.0011248607,0.0046049464],"genre_scores_gemma":[0.90599793,0.000011685553,0.09320685,0.000489858,0.000051362513,0.000027585795,0.000016171436,0.0000061715705,0.00019235631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890167,0.00005042791,0.00028702136,0.00025859164,0.00032576112,0.00017651399],"domain_scores_gemma":[0.9987248,0.00024610822,0.00016394575,0.00069684803,0.00009650767,0.00007175076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113568814,0.0001656626,0.00014788772,0.0002900863,0.00007034841,0.0001185575,0.0004663804,0.000071602706,0.0002260687],"category_scores_gemma":[0.00015165673,0.00009877518,0.00008261931,0.00035592582,0.000026264537,0.0037499624,0.000081864986,0.00007770789,0.00031808217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086482505,0.0002489036,0.009641188,0.0000066723483,0.000039939147,0.000014073582,0.0004921716,0.00008236211,0.20891117,0.0051649283,0.008231066,0.767081],"study_design_scores_gemma":[0.0037212563,0.0005923754,0.16059928,0.00020789856,0.000036509362,0.000008873915,0.00008590762,0.4629696,0.33408576,0.025586914,0.010533963,0.0015716541],"about_ca_topic_score_codex":0.000017174581,"about_ca_topic_score_gemma":0.00003252285,"teacher_disagreement_score":0.84639645,"about_ca_system_score_codex":0.000095425385,"about_ca_system_score_gemma":0.00003371105,"threshold_uncertainty_score":0.40884086},"labels":[],"label_agreement":null},{"id":"W2547897442","doi":"10.1017/s0140525x15001302","title":"But is it social? How to tell when groups are more than the sum of their members","year":2016,"lang":"en","type":"article","venue":"Behavioral and Brain Sciences","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Perspective (graphical); Cognition; Function (biology); Psychology; Group (periodic table); Social group; Social cognition; Social psychology; Computer science; Artificial intelligence; Biology; Neuroscience","score_opus":0.06809330254961272,"score_gpt":0.33284239905683144,"score_spread":0.26474909650721873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547897442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8606046,0.00005777566,0.025072647,0.11381592,0.000051037867,0.00016592066,0.000016641037,0.00007822405,0.00013723542],"genre_scores_gemma":[0.98956007,0.000011313897,0.008098957,0.001150757,0.000035400662,0.00001730693,1.9679484e-7,0.0000041163444,0.0011218893],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985924,0.000060825776,0.00016357705,0.0004537725,0.0004401145,0.0002893529],"domain_scores_gemma":[0.9992093,0.00013648995,0.00016108206,0.0003274848,0.00008692891,0.000078707475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005995356,0.00014684474,0.00020379503,0.00010921955,0.00037316856,0.00018028378,0.0014496872,0.00004777795,0.000020923486],"category_scores_gemma":[0.000030298734,0.00006680815,0.000094080475,0.00055703666,0.00080672855,0.0007205095,0.00045218391,0.000055134602,0.000002900164],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017271659,0.00031192802,0.13993831,0.000022595457,0.000033437587,0.00001767231,0.046223935,0.000002273603,0.1628269,0.019964619,0.074941225,0.5556998],"study_design_scores_gemma":[0.0011274617,0.0019376868,0.30323485,0.0004771203,0.00013380799,0.00005976863,0.04363577,0.0014158569,0.4900168,0.09502766,0.06025307,0.0026801738],"about_ca_topic_score_codex":0.00012031526,"about_ca_topic_score_gemma":0.00020862471,"teacher_disagreement_score":0.55301964,"about_ca_system_score_codex":0.00001838748,"about_ca_system_score_gemma":0.000033256478,"threshold_uncertainty_score":0.2972425},"labels":[],"label_agreement":null},{"id":"W2551248486","doi":"10.5539/jmr.v8n6p105","title":"Discovery of Similarity and Dissimilarity","year":2016,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Span (engineering); Life span; Biology; Structural engineering","score_opus":0.09644546394271507,"score_gpt":0.4204893969750795,"score_spread":0.3240439330323644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551248486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12531294,0.00014622476,0.87240976,0.0016149803,0.000019508907,0.000060976632,0.0000018569101,0.000010438063,0.00042332907],"genre_scores_gemma":[0.76622856,0.00033882546,0.23322402,0.000006896633,0.000024209174,9.750219e-7,2.3617579e-8,0.0000051879388,0.00017127987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998081,0.00014015654,0.0004988819,0.000119550125,0.0009589422,0.00020145669],"domain_scores_gemma":[0.99739426,0.0011334086,0.0003271821,0.0004470176,0.00061641895,0.00008171972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035100176,0.00007360036,0.00029949643,0.00034346094,0.000057973444,0.000081284066,0.00088882045,0.000051048573,0.000005637494],"category_scores_gemma":[0.0012538868,0.000040687275,0.000092213384,0.0003328024,0.00022245842,0.001054157,0.00047701132,0.00025363528,0.0000012994984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045060577,0.0015399833,0.0077278325,0.0005768837,0.00025685097,0.00014408163,0.0022628605,0.0000046196405,0.28335187,0.608772,0.00400682,0.09131116],"study_design_scores_gemma":[0.00038441326,0.00033887278,0.0024553428,0.000455886,0.000014715951,0.00009805666,0.00013368813,0.0017709279,0.14393981,0.849866,0.00041909324,0.00012323273],"about_ca_topic_score_codex":0.0000021097246,"about_ca_topic_score_gemma":0.0000028282054,"teacher_disagreement_score":0.64091563,"about_ca_system_score_codex":0.000053457414,"about_ca_system_score_gemma":0.000095290365,"threshold_uncertainty_score":0.16591789},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Square root; Mathematics; Inverse; Statistics; Sample size determination; Multivariate statistics; Monte Carlo method; Exponential function; Applied mathematics; Mean squared error; Mathematical optimization; Mathematical analysis","score_opus":0.017003286307939583,"score_gpt":0.31361786399664715,"score_spread":0.2966145776887076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561541699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01774475,0.000054856864,0.9806929,0.0007228454,0.00030271447,0.0002045123,0.0000029228872,0.00008499324,0.00018946097],"genre_scores_gemma":[0.78173125,0.00003122324,0.21800062,0.00010032364,0.00006696827,0.000026885127,0.0000010555863,0.0000049109512,0.00003675043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981467,0.00034580883,0.00080468593,0.000107789696,0.00038224005,0.00021274881],"domain_scores_gemma":[0.9978858,0.0008788225,0.00061795284,0.00032050323,0.00020979001,0.00008709372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021681841,0.00012982433,0.00019628485,0.0002990386,0.00019872471,0.00053350185,0.00048007685,0.00007368105,0.000009210449],"category_scores_gemma":[0.00096204766,0.000074249816,0.000061812054,0.0003711214,0.00004768301,0.0055227494,0.00012866642,0.00016816941,0.000024035526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006603969,0.000052211544,0.010679274,0.00012822692,0.00012281214,0.000013772926,0.015888907,0.0098707955,0.003192819,0.027726376,0.0066015986,0.92565715],"study_design_scores_gemma":[0.0026731617,0.0001987228,0.01854604,0.0006870316,0.000040848754,0.0011885582,0.0012588694,0.87886053,0.0025671648,0.032494783,0.060773484,0.00071081036],"about_ca_topic_score_codex":0.00005050493,"about_ca_topic_score_gemma":0.000022978034,"teacher_disagreement_score":0.92494637,"about_ca_system_score_codex":0.00015092958,"about_ca_system_score_gemma":0.00006379608,"threshold_uncertainty_score":0.51445705},"labels":[],"label_agreement":null},{"id":"W2572433599","doi":"","title":"Weak Links and Strong Meaning: The Complex Phenomenon of Negational Citations","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Phenomenon; Meaning (existential); Computer science; Epistemology; Philosophy","score_opus":0.02508943377444567,"score_gpt":0.26274232746240656,"score_spread":0.2376528936879609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572433599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029866046,0.00034888875,0.9307786,0.016195672,0.00005691814,0.00032011833,0.000034017645,0.00022267028,0.049056478],"genre_scores_gemma":[0.72318435,0.00018527868,0.27495435,0.00006223636,0.000017639934,0.000058631867,0.00008302856,0.000019503253,0.0014349981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958232,0.0022035541,0.00056704466,0.00066452567,0.00049155665,0.00025013252],"domain_scores_gemma":[0.9927844,0.0021248003,0.0007827213,0.0022534085,0.0019529271,0.00010175261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029534486,0.0002594147,0.00033872444,0.00022835228,0.00037931118,0.00030998388,0.0022545406,0.0002071643,0.000039408835],"category_scores_gemma":[0.00074348407,0.0002069668,0.00015371336,0.00040365636,0.00042563156,0.00028649464,0.0024493136,0.0005631672,0.0000072905905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001524785,0.00009098058,0.00037846717,0.000031377604,0.00006433008,3.0726991e-7,0.0033074324,0.000056283072,0.0029145854,0.9671286,0.000373018,0.025653126],"study_design_scores_gemma":[0.00070416,0.0000016203927,0.012165558,0.0017615911,0.000114127535,0.0000109889825,0.0002514288,0.17931552,0.029638918,0.7617975,0.013355701,0.0008828813],"about_ca_topic_score_codex":0.00011934786,"about_ca_topic_score_gemma":0.0002951269,"teacher_disagreement_score":0.72019774,"about_ca_system_score_codex":0.0000872962,"about_ca_system_score_gemma":0.00020041132,"threshold_uncertainty_score":0.8439861},"labels":[],"label_agreement":null},{"id":"W2574545922","doi":"","title":"Extracting Discriminative Keyphrases with Learned Semantic Hierarchies.","year":2016,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Discriminative model; Information retrieval; Salient; Set (abstract data type); Key (lock); Natural language processing; Artificial intelligence","score_opus":0.020903224723474022,"score_gpt":0.2792802311944043,"score_spread":0.2583770064709303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574545922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019113543,0.000015476528,0.96257627,0.002910947,0.000022784481,0.00009724513,8.1840494e-7,0.00046309744,0.014799819],"genre_scores_gemma":[0.76547575,0.000018743998,0.23320651,0.00007312064,0.000025702298,0.000019690937,3.653723e-7,0.000010986121,0.0011690984],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987649,0.000067544024,0.00015931438,0.0004207914,0.0002916579,0.00029584166],"domain_scores_gemma":[0.9988284,0.00033001357,0.0001255088,0.000559565,0.00008135718,0.00007514815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016287556,0.00014778088,0.00017966413,0.00014565175,0.0001270225,0.00007075931,0.00061196554,0.000029492618,0.00006049528],"category_scores_gemma":[0.00014386358,0.00008414279,0.000052567048,0.0003451738,0.000134757,0.00096061715,0.00019546048,0.00010504682,0.000040893818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015415475,0.00006954891,0.0011250768,0.000009625527,0.00003977209,0.00006383728,0.00073822367,0.0000041214944,0.13583307,0.13955487,0.00034948016,0.72219694],"study_design_scores_gemma":[0.0008348171,0.00046172162,0.003831162,0.0003910117,0.000052398897,0.000077619254,0.00021996594,0.0038917246,0.34677997,0.6385217,0.0040965206,0.00084143376],"about_ca_topic_score_codex":0.000006205097,"about_ca_topic_score_gemma":0.00001872617,"teacher_disagreement_score":0.7463622,"about_ca_system_score_codex":0.000051973944,"about_ca_system_score_gemma":0.000037330312,"threshold_uncertainty_score":0.34312433},"labels":[],"label_agreement":null},{"id":"W2575085358","doi":"","title":"The Quantum Chess Story.","year":2016,"lang":"en","type":"article","venue":"International journal of unconventional computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hollywood; Quantum; Art; Aesthetics; Visual arts; Art history; Physics; Quantum mechanics","score_opus":0.013343688286291164,"score_gpt":0.30244636608169106,"score_spread":0.2891026777953999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575085358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01450659,0.0002447389,0.9711524,0.011911851,0.0017995801,0.000030645297,9.4686555e-7,0.000047625697,0.0003055887],"genre_scores_gemma":[0.97420853,0.000042310246,0.02469355,0.00015903231,0.00057873613,7.3546965e-7,3.5045952e-7,0.0000068547674,0.00030989698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810404,0.00012272301,0.00053555175,0.00015203409,0.0009171075,0.00016854721],"domain_scores_gemma":[0.9968717,0.00087147055,0.00078785664,0.00019644824,0.0012080702,0.00006442362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013971337,0.000102819235,0.00013780351,0.00018317586,0.00018665123,0.00016444805,0.0021751125,0.00003012919,0.000013953465],"category_scores_gemma":[0.00034791045,0.000056756944,0.00025930567,0.00014621149,0.00009028455,0.00068972044,0.000311528,0.0001790465,0.000019849438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029415496,0.000067811925,0.0019444918,0.0000016004323,0.0003115141,0.00006898332,0.00007302593,0.00015402575,0.003984449,0.67903537,0.00310652,0.31122282],"study_design_scores_gemma":[0.0024030518,0.0003070705,0.01674392,0.0006959157,0.00003844024,0.00126465,0.00009744829,0.028697858,0.013262257,0.6794772,0.25644386,0.0005683097],"about_ca_topic_score_codex":0.0000012763571,"about_ca_topic_score_gemma":0.0000022670338,"teacher_disagreement_score":0.95970196,"about_ca_system_score_codex":0.00020577841,"about_ca_system_score_gemma":0.00012440959,"threshold_uncertainty_score":0.40419364},"labels":[],"label_agreement":null},{"id":"W2576201175","doi":"","title":"Discovering Relevant Hashtags for Health Concepts: A Case Study of Twitter","year":2016,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Search engine indexing; Baseline (sea); Cluster analysis; Information retrieval; Social media; Word (group theory); Natural language processing; Artificial intelligence; Data science; World Wide Web; Linguistics","score_opus":0.19415731578588039,"score_gpt":0.45427406322844993,"score_spread":0.2601167474425695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576201175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06189565,0.000010142505,0.9343851,0.0027321556,0.00009617804,0.00056535454,0.000017207401,0.000103589,0.00019460195],"genre_scores_gemma":[0.9769977,0.00001134715,0.022382686,0.0003330643,0.00004897033,0.00012775135,0.0000013461324,0.000009900367,0.000087242246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777085,0.000101159574,0.0006963488,0.0005522319,0.0006092938,0.00027012386],"domain_scores_gemma":[0.99778485,0.0005587689,0.00036816002,0.00040615367,0.000792928,0.00008911957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064942054,0.00017634791,0.00029601916,0.00023993451,0.0001621133,0.000077745426,0.0006293086,0.00004680061,0.000032840697],"category_scores_gemma":[0.00044464023,0.00012947763,0.00008590865,0.0003704631,0.00011374012,0.00048172585,0.00012739576,0.00009761561,0.000021193251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046724846,0.00059498375,0.000077541285,0.000012879685,0.000034106703,0.000032954675,0.0027195124,0.0003018763,0.0038336231,0.71176356,0.00014830814,0.2804339],"study_design_scores_gemma":[0.0004267312,0.0046157106,0.00019652597,0.00040444915,0.000021362632,0.00013344934,0.006349756,0.121142924,0.13171117,0.7332522,0.0008353141,0.0009103942],"about_ca_topic_score_codex":0.00012547297,"about_ca_topic_score_gemma":0.00042057154,"teacher_disagreement_score":0.91510206,"about_ca_system_score_codex":0.0001713363,"about_ca_system_score_gemma":0.0002867841,"threshold_uncertainty_score":0.52799445},"labels":[],"label_agreement":null},{"id":"W2576351195","doi":"","title":"Text Classification of Student Self-Explanations in College Physics Questions.","year":2016,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dawson College; John Abbott College; Polytechnique Montréal","funders":"","keywords":"Mathematics education; Computer science; Physics; Data science; Psychology","score_opus":0.013873316587529461,"score_gpt":0.27014708374965,"score_spread":0.2562737671621206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576351195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033215374,0.00017545304,0.9606944,0.003761161,0.00004235199,0.0005701912,0.000029681249,0.0010320938,0.00047933953],"genre_scores_gemma":[0.718341,0.00020596686,0.280671,0.00017042508,0.00002945561,0.00041998277,0.000004152795,0.000020983634,0.00013702526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976604,0.00018401213,0.0006877444,0.0005339022,0.0004886252,0.00044532336],"domain_scores_gemma":[0.9976033,0.00025104784,0.00040597515,0.0013331516,0.0002660867,0.00014042264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006123511,0.00025755464,0.00037224966,0.0006695069,0.00011597146,0.000058164867,0.0012753417,0.00017465245,0.0000075576204],"category_scores_gemma":[0.00010775661,0.00021830786,0.00014068588,0.0016402208,0.00008630166,0.001045088,0.0003032323,0.00019585548,0.000015325497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008201331,0.00070727605,0.0724407,0.000012469576,0.00003906416,0.000012760065,0.00026835836,0.00026132428,0.031831432,0.8561082,0.00070813094,0.037602108],"study_design_scores_gemma":[0.0011733014,0.0002563411,0.6735523,0.00025273615,0.000053555726,0.00003442968,0.00013686217,0.15163529,0.06489491,0.105102934,0.0020242739,0.0008830976],"about_ca_topic_score_codex":0.00047355634,"about_ca_topic_score_gemma":0.0009987578,"teacher_disagreement_score":0.75100523,"about_ca_system_score_codex":0.000814718,"about_ca_system_score_gemma":0.00023171936,"threshold_uncertainty_score":0.89023364},"labels":[],"label_agreement":null},{"id":"W2580236052","doi":"10.29173/cais647","title":"Tags, Homonyms, and the Manifestation of Intentionality","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Intentionality; Recall; Relevance (law); Humanities; Philosophy; Psychology; Epistemology; Cognitive psychology; Political science","score_opus":0.022850301315147908,"score_gpt":0.25644568886519725,"score_spread":0.23359538755004935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580236052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96338725,0.0018864525,0.007505446,0.02071876,0.00021282221,0.00093000196,0.00009817001,0.00005857135,0.0052025015],"genre_scores_gemma":[0.988928,0.00077913253,0.008155603,0.00019931508,0.000055468347,0.000057076162,0.0000026379926,0.000016089461,0.0018066592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975408,0.00009371055,0.0009104287,0.00042403105,0.0006492842,0.0003817669],"domain_scores_gemma":[0.9359423,0.00039743553,0.0018075719,0.00038006066,0.06136243,0.00011021176],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001314199,0.00030956257,0.0006754394,0.00015897788,0.00015729072,0.002126778,0.0024662772,0.00017589949,0.00004638213],"category_scores_gemma":[0.012020853,0.0002124739,0.00027918798,0.0006824984,0.0024048777,0.015488368,0.0013451261,0.0003556654,0.000003573915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097607415,0.00024697292,0.042784702,0.0007977888,0.00025557732,7.139585e-7,0.029023182,0.0000065969293,0.00951742,0.86788386,0.003277145,0.04610846],"study_design_scores_gemma":[0.0016459144,0.00046581938,0.28358015,0.001423131,0.0004684055,0.00010813762,0.0046270676,0.017851185,0.06519333,0.60582054,0.018165482,0.0006508326],"about_ca_topic_score_codex":0.0018393855,"about_ca_topic_score_gemma":0.000030973242,"teacher_disagreement_score":0.2620633,"about_ca_system_score_codex":0.000054740525,"about_ca_system_score_gemma":0.00019373088,"threshold_uncertainty_score":0.9989091},"labels":[],"label_agreement":null},{"id":"W2581505073","doi":"10.1109/icdim.2016.7829792","title":"Extracting keyword and keyphrase from online privacy policies","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Taxonomy (biology); Keyword extraction; Domain (mathematical analysis); Annotation; Artificial intelligence; Natural language processing; Rake; Information retrieval; Variety (cybernetics); Key (lock)","score_opus":0.021159089162077555,"score_gpt":0.2985420800903012,"score_spread":0.27738299092822366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2581505073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23416494,0.000078640325,0.761447,0.0029928104,0.000016703943,0.00004298966,0.0000029200862,0.000476264,0.0007777343],"genre_scores_gemma":[0.6191167,0.0000711041,0.3792782,0.000329653,0.000059535185,0.0000027660515,9.090967e-7,0.0000058154187,0.0011352802],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912,0.000025066623,0.00018243973,0.00033425025,0.00014276868,0.00019548772],"domain_scores_gemma":[0.9989087,0.00033394297,0.00008408782,0.0005521346,0.000040806808,0.00008033494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008288051,0.000112691836,0.00014017246,0.000092701135,0.0000674388,0.000077550125,0.00051035633,0.000037341146,0.00004443329],"category_scores_gemma":[0.00015808287,0.00006963377,0.00003808728,0.00018089458,0.000048461618,0.00086933415,0.00044751394,0.000056866007,0.00001940523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043631717,0.00008453704,0.016381072,0.000002177273,0.000030246722,0.000013697067,0.00044432352,8.9785937e-7,0.08378189,0.031344067,0.0009988509,0.86691386],"study_design_scores_gemma":[0.0018842146,0.00021740304,0.15473598,0.00027565242,0.0000659407,0.000045392728,0.00024978907,0.01995733,0.30663309,0.41610813,0.09804302,0.0017840799],"about_ca_topic_score_codex":0.0002383327,"about_ca_topic_score_gemma":0.00007726946,"teacher_disagreement_score":0.86512977,"about_ca_system_score_codex":0.000026685555,"about_ca_system_score_gemma":0.000015251954,"threshold_uncertainty_score":0.28395826},"labels":[],"label_agreement":null},{"id":"W2586790131","doi":"10.4236/jilsa.2017.91002","title":"Text-Based Intelligent Learning Emotion System","year":2017,"lang":"en","type":"article","venue":"Journal of Intelligent Learning Systems and Applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Meaning (existential); Feeling; Experiential learning; Social media; Emotion recognition; Human–computer interaction; Artificial intelligence; World Wide Web; Psychology; Social psychology","score_opus":0.02001367212382593,"score_gpt":0.297721264805105,"score_spread":0.2777075926812791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586790131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004610818,0.00086682645,0.992724,0.00025310362,0.0001572393,0.0002713997,4.175756e-7,0.0001558825,0.000960284],"genre_scores_gemma":[0.9859206,0.00021909189,0.012929733,0.000012832285,0.00026327718,0.0000435051,0.0000015382266,0.00001840346,0.0005909815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980549,0.00017056109,0.00084080297,0.0003022007,0.0004044129,0.00022707184],"domain_scores_gemma":[0.9964522,0.00016128588,0.002054565,0.0006205947,0.00054485875,0.00016649553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012516403,0.00019150671,0.00040459182,0.0003070241,0.0010521426,0.0008258392,0.0010603971,0.000096331525,0.0000033145268],"category_scores_gemma":[0.00019469803,0.00016205457,0.00018077191,0.00018744248,0.000084123414,0.0005236214,0.00016337179,0.0005942753,0.000029244216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025997344,0.0002693487,0.01847218,0.0005393321,0.00030696805,0.000043261778,0.0010499904,0.20269893,0.0052881,0.31439686,0.00030921915,0.4565998],"study_design_scores_gemma":[0.00040131467,0.0006303016,0.0022556437,0.0015994486,0.00015126861,0.00046472903,0.00311726,0.6699818,0.010329229,0.0008896817,0.30947834,0.0007010213],"about_ca_topic_score_codex":0.000046411536,"about_ca_topic_score_gemma":0.0000019193928,"teacher_disagreement_score":0.98130983,"about_ca_system_score_codex":0.00017376356,"about_ca_system_score_gemma":0.00006718212,"threshold_uncertainty_score":0.80923367},"labels":[],"label_agreement":null},{"id":"W2587261082","doi":"10.29173/cais456","title":"Adaptation of a Key Phrase Extractor for Japanese Text","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Extractor; Phrase; Key (lock); Adaptation (eye); Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.024650770768542413,"score_gpt":0.2595055367525164,"score_spread":0.234854765983974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587261082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97040117,0.000114621085,0.026106933,0.0009206307,0.000060169386,0.00081924757,0.00005021886,0.000104451174,0.0014225357],"genre_scores_gemma":[0.9578515,0.000038504877,0.04160482,0.00006985996,0.000033251687,0.00013204847,0.0000026690984,0.000018277862,0.0002490574],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998123,0.000022229693,0.00065598503,0.00038233394,0.0004672479,0.00034922027],"domain_scores_gemma":[0.95526916,0.0002560624,0.0011863451,0.00034894323,0.04283209,0.000107405984],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00053997815,0.00025384544,0.00053944916,0.00023089048,0.000081572965,0.0010008222,0.0026315295,0.00013560637,0.000016420767],"category_scores_gemma":[0.009853369,0.00019721538,0.000259477,0.0005802641,0.00028747416,0.01402277,0.00050160877,0.0001628298,0.0000027605365],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024395753,0.0008170222,0.028589642,0.0013950876,0.00033902982,9.36854e-7,0.103907846,0.00007276414,0.6136154,0.14134145,0.004185645,0.10549122],"study_design_scores_gemma":[0.002032207,0.0015823431,0.07492476,0.0010764514,0.00028395603,0.000039371665,0.0082308855,0.068413764,0.71552795,0.10470065,0.02190024,0.0012874169],"about_ca_topic_score_codex":0.0003157951,"about_ca_topic_score_gemma":0.000011271238,"teacher_disagreement_score":0.104203805,"about_ca_system_score_codex":0.000044117227,"about_ca_system_score_gemma":0.00015790363,"threshold_uncertainty_score":0.9997676},"labels":[],"label_agreement":null},{"id":"W2587364723","doi":"10.29173/cais440","title":"In Search of the Perfect Filter: Indexing Theory Implications for Internet Blocking and Rating Software Products","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Blocking (statistics); The Internet; Legislature; Search engine indexing; Globe; Politics; Government (linguistics); Software; Control (management); Filter (signal processing); Internet access; Business; Public relations; Political science; Computer science; World Wide Web; Artificial intelligence","score_opus":0.02440889892602804,"score_gpt":0.2713012996301007,"score_spread":0.24689240070407265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587364723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9792551,0.000114532966,0.016551737,0.0029113062,0.000032770695,0.0008083484,0.000016566395,0.000043682612,0.0002659693],"genre_scores_gemma":[0.9791872,0.000015070033,0.020402148,0.00010241238,0.000024250046,0.00011065969,5.8556276e-7,0.000013065516,0.00014463569],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986105,0.000042607073,0.00046022848,0.00036021348,0.0002332055,0.00029325412],"domain_scores_gemma":[0.9808696,0.00040577407,0.0006170484,0.00033350696,0.017728494,0.000045599274],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00093089364,0.00017666603,0.0003421716,0.00017621934,0.00010722222,0.00085925293,0.002265585,0.00007906834,0.0000029514924],"category_scores_gemma":[0.01294784,0.00012018963,0.00010352351,0.0006267563,0.00033100872,0.006230807,0.0013202169,0.00023888222,1.9119125e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040562143,0.00015799064,0.49732876,0.00079138775,0.00011137094,1.3759842e-7,0.057221014,0.00003125316,0.18109547,0.20701571,0.0008029892,0.055403363],"study_design_scores_gemma":[0.00047683538,0.00025680044,0.23773931,0.0008720119,0.000056996254,0.000025702357,0.0014349181,0.007556904,0.61326915,0.13703646,0.00088583207,0.0003891154],"about_ca_topic_score_codex":0.00012449888,"about_ca_topic_score_gemma":0.000009469199,"teacher_disagreement_score":0.43217367,"about_ca_system_score_codex":0.000040348204,"about_ca_system_score_gemma":0.00013668029,"threshold_uncertainty_score":0.9953665},"labels":[],"label_agreement":null},{"id":"W2588009921","doi":"10.29173/cais305","title":"Deriving an Ontology of Reader Authored Markings Made on Electronic Documents","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Reading (process); Ontology; Information retrieval; World Wide Web; Humanities; Library science; Art; Linguistics; Philosophy; Epistemology","score_opus":0.024635255279582817,"score_gpt":0.2773505347787903,"score_spread":0.25271527949920747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588009921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808968,0.00069015176,0.0032537098,0.0074360147,0.00023839451,0.0007779317,0.00003398644,0.00012062429,0.0065524383],"genre_scores_gemma":[0.98558265,0.00037005887,0.010673318,0.00035783675,0.00008883326,0.00007135661,0.0000034548384,0.000046348225,0.002806169],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958159,0.0001212789,0.0011824656,0.0008548782,0.00085622654,0.0011692946],"domain_scores_gemma":[0.96083164,0.0002457976,0.002190913,0.0006735824,0.035813104,0.00024497014],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0010170097,0.00057654805,0.0011157431,0.00042796024,0.00016973123,0.0021130624,0.0047429847,0.00044011234,0.00012352977],"category_scores_gemma":[0.0076980065,0.00050309254,0.0003629517,0.000989175,0.0011007835,0.021447869,0.0012893446,0.000754663,0.000010152529],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025259238,0.0012541433,0.093545735,0.0010821854,0.0007318135,0.00000471595,0.062290598,0.0000282721,0.23191436,0.44636473,0.0044345595,0.15809628],"study_design_scores_gemma":[0.0014184125,0.004139407,0.16621833,0.0027206757,0.0005594218,0.00016096242,0.003614525,0.014008474,0.4950467,0.2663799,0.044083983,0.0016492041],"about_ca_topic_score_codex":0.0017119537,"about_ca_topic_score_gemma":0.00007536555,"teacher_disagreement_score":0.26313233,"about_ca_system_score_codex":0.00023611085,"about_ca_system_score_gemma":0.00047010553,"threshold_uncertainty_score":0.9997421},"labels":[],"label_agreement":null},{"id":"W2588137444","doi":"10.29173/cais356","title":"Integrating Knowledge from Different Sources for Automatic Back-of-the-book Indexing","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Indexation; Search engine indexing; Computer science; Valuation (finance); Humanities; Information retrieval; Library science; Art; Business","score_opus":0.026891346411433786,"score_gpt":0.2663705937485865,"score_spread":0.23947924733715273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588137444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96700954,0.0028988908,0.020046374,0.004423315,0.0005015666,0.0015327996,0.00012634673,0.000114190305,0.0033469992],"genre_scores_gemma":[0.96903425,0.000099287456,0.026965782,0.00017845936,0.00015344581,0.00014943411,0.0000027828416,0.000045611272,0.003370916],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996591,0.000088897985,0.0013454385,0.0006508578,0.0006137469,0.000710089],"domain_scores_gemma":[0.95581615,0.00095935224,0.0027149657,0.0006305786,0.03969712,0.0001818241],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00060301204,0.0005844702,0.0011549037,0.0002322299,0.00027478187,0.0029066987,0.005325914,0.00032441082,0.00010502825],"category_scores_gemma":[0.013029263,0.00040105835,0.0006780757,0.00072500453,0.0011081105,0.012991056,0.0023737538,0.00054875994,0.000007934474],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078715886,0.0012326286,0.18349047,0.0042449636,0.0011482773,6.25154e-7,0.21106623,0.00002619185,0.16704169,0.1389814,0.0155276535,0.27716115],"study_design_scores_gemma":[0.0010754119,0.00064613036,0.051685162,0.007616541,0.0005789681,0.000017141863,0.004128232,0.100137495,0.6814165,0.12192176,0.029687654,0.0010890091],"about_ca_topic_score_codex":0.0007904338,"about_ca_topic_score_gemma":0.00007441595,"teacher_disagreement_score":0.5143748,"about_ca_system_score_codex":0.00015488052,"about_ca_system_score_gemma":0.00035930285,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W2588474510","doi":"10.29173/cais596","title":"Facets of Serendipity in Everyday Chance Encounters: Content Analysis of Social Media Accounts","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Serendipity; Humanities; Sociology; Art; Epistemology; Philosophy","score_opus":0.05236118604178577,"score_gpt":0.2774246457792693,"score_spread":0.2250634597374835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588474510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992948,0.0007210903,0.0015281637,0.0021913906,0.00024669603,0.0005758542,0.00043785822,0.000040725492,0.0013101972],"genre_scores_gemma":[0.9962112,0.0004067277,0.002716929,0.00010853451,0.000061407634,0.000058201542,0.000007967188,0.000025251296,0.00040380866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99531895,0.00010141101,0.0018220368,0.0007296599,0.0012642696,0.00076367514],"domain_scores_gemma":[0.9345765,0.00043552104,0.0035939058,0.0005094052,0.060730625,0.00015401427],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001305904,0.00054544985,0.0020371953,0.0010463251,0.00009323946,0.0010183579,0.0044579515,0.00040887552,0.00012859033],"category_scores_gemma":[0.011118868,0.00048009434,0.00076498295,0.0035702966,0.0014686843,0.01784847,0.0015484011,0.00051997707,0.0000035213077],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024416158,0.001595345,0.48022994,0.0017299841,0.0032675406,0.0000032258988,0.2570199,0.00009365278,0.15082358,0.06373709,0.0022517215,0.03900387],"study_design_scores_gemma":[0.00094584853,0.0003410431,0.7795554,0.0011683307,0.001352475,0.000007061951,0.007177216,0.012233944,0.1829752,0.011280011,0.0021903496,0.0007731119],"about_ca_topic_score_codex":0.0025225326,"about_ca_topic_score_gemma":0.00055458746,"teacher_disagreement_score":0.29932547,"about_ca_system_score_codex":0.00020711694,"about_ca_system_score_gemma":0.00037908944,"threshold_uncertainty_score":0.9997651},"labels":[],"label_agreement":null},{"id":"W2588863515","doi":"10.29173/cais505","title":"Assessing Intra and Extra Web-based Automatic Indexing Tools","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre de Développement du Porc du Québec; University of Toronto","funders":"","keywords":"Search engine indexing; Extractor; Information retrieval; Computer science; Representation (politics); Automatic indexing; World Wide Web; Engineering","score_opus":0.027889095759107196,"score_gpt":0.2721698050000837,"score_spread":0.2442807092409765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588863515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97526324,0.0000842265,0.01928568,0.0018275419,0.00004829208,0.00039372375,0.0000068797053,0.00024662068,0.0028437995],"genre_scores_gemma":[0.9414659,0.000021006023,0.058112174,0.00024802802,0.000027897555,0.000053487554,8.5106973e-7,0.000018027633,0.00005258445],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99798423,0.000033002554,0.0006029593,0.00043800144,0.0005117997,0.00043001396],"domain_scores_gemma":[0.9793474,0.00029431662,0.0009021329,0.00034739115,0.018967632,0.0001411427],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00062645465,0.00029471566,0.0005314105,0.00027492872,0.00016090428,0.008257886,0.0024017114,0.00014734452,0.00001880848],"category_scores_gemma":[0.008049487,0.0002302006,0.00014077067,0.0006824564,0.0003983717,0.031725287,0.0008212426,0.00030961935,0.000002353987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002011305,0.00031149999,0.15692414,0.0009598153,0.00019603182,0.0000036600698,0.016809829,0.00002794875,0.2780764,0.0703868,0.0017547507,0.474529],"study_design_scores_gemma":[0.0013728256,0.00046133864,0.3058216,0.001834923,0.00018592803,0.000070625065,0.002241429,0.24807006,0.35514513,0.07797055,0.0054995003,0.0013260937],"about_ca_topic_score_codex":0.00007010294,"about_ca_topic_score_gemma":0.0000032260643,"teacher_disagreement_score":0.4732029,"about_ca_system_score_codex":0.000060645092,"about_ca_system_score_gemma":0.00025754125,"threshold_uncertainty_score":0.9927716},"labels":[],"label_agreement":null},{"id":"W25922597","doi":"10.4110/in.2015.15.2.83","title":"Using Subjective Adjectives in Opinion Retrieval from Blogs.","year":2007,"lang":"en","type":"article","venue":"Immune Network","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Relevance (law); Information retrieval; Point (geometry); Event (particle physics); Sentiment analysis; Product (mathematics); Subject (documents); Psychology; Natural language processing; World Wide Web; Political science; Mathematics","score_opus":0.025391575791442293,"score_gpt":0.32161483975794497,"score_spread":0.29622326396650267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W25922597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12446362,0.00249801,0.87116987,0.00003007362,0.00047974222,0.00015288133,5.4629766e-7,0.00025333033,0.0009519217],"genre_scores_gemma":[0.8138894,0.00006341,0.18566519,0.00005634374,0.00029142617,0.0000018138337,0.000003946464,0.00001316126,0.000015343745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983317,0.00011088956,0.00039986827,0.00045754368,0.00023114453,0.00046880424],"domain_scores_gemma":[0.9987929,0.00030101143,0.00018315637,0.00060189405,0.000073952564,0.000047075275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007998551,0.00017195981,0.00029445265,0.00017302038,0.000111801426,0.00005637658,0.00067354157,0.0001182246,0.0000072990247],"category_scores_gemma":[0.00007256622,0.00017790493,0.00009747836,0.0016241237,0.00006143404,0.0005402713,0.00032912986,0.00029508208,0.000008616192],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014067343,0.0011243399,0.31214216,0.000030110667,0.0007642243,0.00043609453,0.011364986,0.072569005,0.1881995,0.11711883,0.00079379644,0.29405022],"study_design_scores_gemma":[0.0014206556,0.00025823477,0.5401666,0.00044828164,0.00003119259,0.000017573058,0.00024089363,0.11319966,0.10188856,0.23890401,0.002127894,0.0012964474],"about_ca_topic_score_codex":0.00035140227,"about_ca_topic_score_gemma":0.00008400378,"teacher_disagreement_score":0.68942577,"about_ca_system_score_codex":0.00021849456,"about_ca_system_score_gemma":0.000040611485,"threshold_uncertainty_score":0.72547525},"labels":[],"label_agreement":null},{"id":"W2593550342","doi":"10.1371/journal.pone.0184188","title":"Multi-level computational methods for interdisciplinary research in the HathiTrust Digital Library","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Hospitality and Tourism Research Centre, Hong Kong Polytechnic University; National Endowment for the Humanities","keywords":"Computer science; Digital library; Argument (complex analysis); Reading (process); Information retrieval; Domain (mathematical analysis); Zoom; Set (abstract data type); Resource (disambiguation); Data science; Identification (biology); Library classification; World Wide Web; Linguistics","score_opus":0.4036673539531947,"score_gpt":0.49515156111194014,"score_spread":0.09148420715874545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593550342","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045860843,0.000059248745,0.9864294,0.0070559746,0.00001608051,0.0004282803,0.000021351389,0.00011965579,0.0012839474],"genre_scores_gemma":[0.2975683,0.0000040578575,0.7019054,0.000076996,0.000043072137,0.0001222052,0.0000136127655,0.000009594679,0.0002567545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859494,0.00017963574,0.0002178753,0.00036886818,0.0003691378,0.0002695579],"domain_scores_gemma":[0.997693,0.0010681424,0.00010527202,0.0009742926,0.000115288596,0.00004402167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011734614,0.00009960437,0.00018451257,0.0002113167,0.00058338256,0.0010249567,0.0028460782,0.00005228709,0.000003786292],"category_scores_gemma":[0.00031103435,0.00007559631,0.000071474366,0.00023489763,0.00019099939,0.0022238556,0.0021800268,0.00029181922,0.000018166265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009486365,0.0071305986,0.008554856,0.00020728387,0.0003400273,0.00007180876,0.005703124,0.00015512502,0.0036108622,0.09506862,0.0031473208,0.8759155],"study_design_scores_gemma":[0.0004091125,0.00013795996,0.015234164,0.00016260106,0.00001042748,0.000003374196,0.00011253045,0.50857264,0.005096145,0.46976358,0.00029707613,0.00020039642],"about_ca_topic_score_codex":0.0000017603288,"about_ca_topic_score_gemma":0.000002826684,"teacher_disagreement_score":0.87571514,"about_ca_system_score_codex":0.000029750725,"about_ca_system_score_gemma":0.00005500389,"threshold_uncertainty_score":0.9883681},"labels":[],"label_agreement":null},{"id":"W2594482583","doi":"10.7202/1038906ar","title":"Analyse statistique des évangiles synoptiques : une étude de la paternité des textes par l’analyse des correspondances du taxi","year":2017,"lang":"fr","type":"article","venue":"Revue de l’Université de Moncton","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Humanities; Philosophy; Art","score_opus":0.017957825344564495,"score_gpt":0.2706624048675394,"score_spread":0.2527045795229749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594482583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61334604,0.005666367,0.37785634,0.00055180513,0.00005353429,0.00018613398,0.000064421714,0.0003069093,0.0019684655],"genre_scores_gemma":[0.7232544,0.01495654,0.2581966,0.0000703461,0.0001382654,0.000019500583,0.000015329091,0.00006214472,0.0032868865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952245,0.0012803002,0.0006034301,0.0011037388,0.00037546502,0.0014125811],"domain_scores_gemma":[0.99496955,0.001032752,0.0010092104,0.0017527504,0.0005610676,0.00067468564],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0014144549,0.0007481786,0.0009748564,0.00058667525,0.0027773979,0.0010810312,0.002957104,0.000496531,0.00019011938],"category_scores_gemma":[0.001041921,0.0008481639,0.0005655811,0.000891595,0.003405613,0.0026219902,0.0013458824,0.00062550406,0.00004536295],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023875963,0.0003449384,0.72636104,0.0004941683,0.000795383,0.005671483,0.023861803,0.0047851875,0.02071117,0.008697446,0.0008014144,0.20723721],"study_design_scores_gemma":[0.00069067185,0.0003983193,0.7619647,0.0014232388,0.0011628292,0.0006209425,0.0014586982,0.06608721,0.099935934,0.05959307,0.005437002,0.0012273858],"about_ca_topic_score_codex":0.017434472,"about_ca_topic_score_gemma":0.02551768,"teacher_disagreement_score":0.20600982,"about_ca_system_score_codex":0.00265612,"about_ca_system_score_gemma":0.0003386027,"threshold_uncertainty_score":0.99995595},"labels":[],"label_agreement":null},{"id":"W2594787554","doi":"10.19173/irrodl.v18i1.2646","title":"Social Web Content Enhancement in a Distance Learning Environment: Intelligent Metadata Generation for Resources","year":2017,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Comisión de Operación y Fomento de Actividades Académicas, Instituto Politécnico Nacional; Instituto Politécnico Nacional","keywords":"Metadata; Computer science; World Wide Web; Information retrieval; Classifier (UML); Class (philosophy); Metadata repository; Multimedia; Artificial intelligence","score_opus":0.23984678601347464,"score_gpt":0.47129335270847894,"score_spread":0.2314465666950043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594787554","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033161625,0.014919849,0.9258015,0.022845566,0.000056592522,0.0019025044,0.00003264746,0.000021316686,0.0012583724],"genre_scores_gemma":[0.9667849,0.028815348,0.0034586578,0.000059642785,0.000040300067,0.00029035626,0.000101926395,0.00000587142,0.0004429909],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998029,0.00039432623,0.00042967568,0.0003485064,0.00057873543,0.00021975626],"domain_scores_gemma":[0.99875695,0.00033304177,0.00035229707,0.00036289674,0.0001616594,0.00003318198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059443065,0.00009540141,0.00026079424,0.000106359104,0.0004809473,0.000598544,0.0025161859,0.000027185588,0.000018125531],"category_scores_gemma":[0.0018596004,0.00007248542,0.000054399155,0.00014238941,0.00017467831,0.0007947136,0.0017390534,0.00040831612,0.000002220352],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003016068,0.0005980038,0.038813177,0.0015093324,0.0002587169,0.00002746348,0.0015883731,0.001080783,0.018087756,0.36951312,0.0024337973,0.56578785],"study_design_scores_gemma":[0.0018524814,0.00036197077,0.007253697,0.0075152884,0.000028783628,0.0000056944878,0.0012895312,0.26070192,0.010680844,0.012004083,0.6978208,0.0004849203],"about_ca_topic_score_codex":0.00015551195,"about_ca_topic_score_gemma":0.0000739764,"teacher_disagreement_score":0.93362325,"about_ca_system_score_codex":0.00018399241,"about_ca_system_score_gemma":0.000050244344,"threshold_uncertainty_score":0.57717735},"labels":[],"label_agreement":null},{"id":"W2601411009","doi":"10.29173/cais254","title":"A Pilot Study of Enhancing Subject Discovery of Textual Web Resources","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Subject (documents); World Wide Web; Computer science; Web page; Search engine indexing; Information retrieval; Library science; Humanities; Art","score_opus":0.028707232483256913,"score_gpt":0.26272599576058425,"score_spread":0.23401876327732735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601411009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921894,0.0008220744,0.0012665835,0.0008844775,0.00017035397,0.0010633903,0.000096489464,0.00007084561,0.0034364078],"genre_scores_gemma":[0.9943106,0.00020188311,0.0034826319,0.000057113415,0.00009709765,0.00006798535,0.0000011924368,0.00004119877,0.0017402614],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99537075,0.00013220147,0.0017701439,0.00076729007,0.0012292791,0.0007303685],"domain_scores_gemma":[0.9440171,0.00058464,0.0032652353,0.00072439277,0.051246442,0.0001621748],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0012950293,0.00057545473,0.0014891876,0.00052035216,0.00015198812,0.002289275,0.0049539213,0.00016138093,0.000037729544],"category_scores_gemma":[0.014009777,0.0004731809,0.00036434672,0.0016394173,0.0013169918,0.023996277,0.0025598307,0.00054974144,0.0000037443638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036597232,0.0043956614,0.19155043,0.0017916346,0.0008137929,0.0000037290197,0.13411282,0.00003898371,0.61781687,0.031558383,0.0019572352,0.015594493],"study_design_scores_gemma":[0.0022474276,0.015250043,0.16013303,0.0040669227,0.00084671966,0.00005681876,0.039226156,0.004803023,0.7505832,0.01777744,0.0036223987,0.0013868692],"about_ca_topic_score_codex":0.0047615855,"about_ca_topic_score_gemma":0.0004319852,"teacher_disagreement_score":0.13276628,"about_ca_system_score_codex":0.000098043,"about_ca_system_score_gemma":0.00049120246,"threshold_uncertainty_score":0.999772},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.022776585487954894,"score_gpt":0.33508661123122313,"score_spread":0.3123100257432682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603222250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051419355,0.10362444,0.8928441,0.0017491428,0.00029040728,0.0007374853,6.351911e-7,0.0000910705,0.00014856635],"genre_scores_gemma":[0.8454099,0.049604695,0.10244721,0.00016459305,0.00012308778,0.000633939,9.667364e-7,0.000071938164,0.0015436416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990218,0.00006408245,0.00040125963,0.00017306893,0.0001217837,0.0002179688],"domain_scores_gemma":[0.9969714,0.0006470021,0.0002988218,0.0019800595,0.00008037101,0.000022287342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012426403,0.0001366069,0.00035000153,0.000027965323,0.00026009322,0.00007912945,0.0028634046,0.00003117141,7.011637e-7],"category_scores_gemma":[0.001270604,0.000065160406,0.00016324909,0.00031648244,0.00007800072,0.0001434472,0.00045150536,0.00029844107,0.000015284058],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000083271025,0.00015452196,0.0005333703,0.0045618615,0.00019485947,0.0000024404299,0.0024008804,0.0040058703,0.00033821992,0.27146488,0.0048223888,0.7115124],"study_design_scores_gemma":[0.0002707999,0.00006191943,0.0057962965,0.027573379,0.00017469561,0.000009746751,0.000009370128,0.5686952,0.0031814864,0.08032832,0.31335473,0.00054406235],"about_ca_topic_score_codex":0.0000024341239,"about_ca_topic_score_gemma":0.000020504127,"teacher_disagreement_score":0.8448957,"about_ca_system_score_codex":0.000037788534,"about_ca_system_score_gemma":0.000028206387,"threshold_uncertainty_score":0.53209656},"labels":[],"label_agreement":null},{"id":"W2605327093","doi":"","title":"Laval University at TREC Dynamic Domain 2016: Subtopic extraction focused on Named Entities.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Lakehead University","funders":"","keywords":"Computer science; Domain (mathematical analysis); Extraction (chemistry); Information extraction; Named-entity recognition; Artificial intelligence; Engineering; Systems engineering; Chemistry; Mathematics; Chromatography","score_opus":0.014616333478574932,"score_gpt":0.25083006232655075,"score_spread":0.2362137288479758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605327093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24300139,0.000041948966,0.7491952,0.001091679,0.00019977483,0.00021673054,0.000011988861,0.0006456585,0.005595607],"genre_scores_gemma":[0.96712935,0.00025052333,0.0101763485,0.000059592276,0.000026787568,0.0000018987945,0.000004463973,0.0000137430625,0.022337321],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99793196,0.0001835838,0.0002566145,0.0007109216,0.0004985273,0.0004184163],"domain_scores_gemma":[0.9982097,0.00028698103,0.00023521112,0.0009259339,0.00018935358,0.00015279184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029636206,0.000257487,0.0002990914,0.00027946377,0.00022813694,0.00008320731,0.0010766358,0.00015639591,0.00032334772],"category_scores_gemma":[0.000102072234,0.00020602187,0.00014532471,0.00053361355,0.0001934676,0.00088663114,0.00032923243,0.0001950574,0.00039974536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009363952,0.0003102421,0.0019871462,0.000034405493,0.00014271907,0.00025503783,0.0008759425,0.000005183613,0.33119053,0.32028866,0.002429631,0.3415441],"study_design_scores_gemma":[0.009006059,0.0027146447,0.07055749,0.0009908323,0.00019901914,0.00011639533,0.00030041044,0.012700791,0.5190481,0.18096638,0.19916394,0.004235967],"about_ca_topic_score_codex":0.000052232663,"about_ca_topic_score_gemma":0.0001864591,"teacher_disagreement_score":0.73901886,"about_ca_system_score_codex":0.0007857753,"about_ca_system_score_gemma":0.00018208154,"threshold_uncertainty_score":0.84013283},"labels":[],"label_agreement":null},{"id":"W2605475111","doi":"10.1007/978-3-319-57351-9_23","title":"Learning Physical Properties of Objects Using Gaussian Mixture Models","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; WordNet; Taxonomy (biology); Artificial intelligence; Classifier (UML); Inference; Gaussian; Machine learning; Data mining","score_opus":0.033495551435880865,"score_gpt":0.27873265143962406,"score_spread":0.24523710000374319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605475111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008733693,0.00043536894,0.99489117,0.000097557364,0.00026686737,0.00028433718,0.0000010693459,0.00022467374,0.0029255718],"genre_scores_gemma":[0.66408515,0.00002394262,0.3353189,0.00007325388,0.00020751143,0.0000036647868,7.055818e-7,0.00003086689,0.0002559892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996294,0.000048328387,0.00047619897,0.0014527612,0.0011191237,0.00060959486],"domain_scores_gemma":[0.99667567,0.00011276184,0.00074144057,0.001972776,0.00036653123,0.00013080581],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050352514,0.0005841164,0.00090849405,0.00082438975,0.00044798423,0.00044693632,0.0044698888,0.00030365319,0.0000018393167],"category_scores_gemma":[0.00011183007,0.00048531248,0.0002555582,0.0003174855,0.00118856,0.0015720812,0.0019915951,0.0011355457,0.0000040889254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008787974,0.000050448296,0.00002896606,0.00013132006,0.000040168004,0.00007685285,0.005594716,0.44133222,0.015994119,0.0207602,0.000001989773,0.51598024],"study_design_scores_gemma":[0.00007907837,0.0001033949,0.0000047759813,0.0007812266,0.00001550702,0.000024700023,3.382549e-7,0.77305657,0.027461996,0.19798452,0.00003206231,0.00045582504],"about_ca_topic_score_codex":0.000042680706,"about_ca_topic_score_gemma":0.00003169166,"teacher_disagreement_score":0.6632118,"about_ca_system_score_codex":0.0002449363,"about_ca_system_score_gemma":0.0005210958,"threshold_uncertainty_score":0.99975985},"labels":[],"label_agreement":null},{"id":"W2612942342","doi":"","title":"Contextualisation de messages courts :l’importance des métadonnées","year":2013,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Political science","score_opus":0.027389263088150966,"score_gpt":0.2603885544003364,"score_spread":0.23299929131218547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612942342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0730025,0.0044133756,0.8701525,0.015945282,0.00020616576,0.0007430154,0.0000325964,0.000851434,0.034653153],"genre_scores_gemma":[0.52790505,0.0032191756,0.44218293,0.00028811453,0.000045760185,0.00023867693,0.00018449573,0.000072460236,0.025863342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985486,0.0095047755,0.0013095177,0.0017747874,0.00090553466,0.0010194209],"domain_scores_gemma":[0.98459333,0.00277083,0.0016363233,0.0045089363,0.005989104,0.00050148787],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009614024,0.0008148848,0.00089967187,0.00035189485,0.0009757674,0.001714658,0.004068364,0.0006355943,0.0004182253],"category_scores_gemma":[0.0036604973,0.0009218036,0.0004978383,0.0008603588,0.0013840143,0.0015794362,0.0026634454,0.001112638,0.00020401333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048948764,0.00050632947,0.007046859,0.00017186209,0.0001483756,0.000017713157,0.014654298,0.00021753828,0.0038381005,0.8409042,0.0020921957,0.13039765],"study_design_scores_gemma":[0.00074134796,0.0000018751175,0.03028304,0.0050637336,0.00021489999,0.000090999834,0.00031122236,0.17720154,0.13255902,0.6015572,0.050172452,0.001802696],"about_ca_topic_score_codex":0.0038476312,"about_ca_topic_score_gemma":0.0036941757,"teacher_disagreement_score":0.45490256,"about_ca_system_score_codex":0.0007320701,"about_ca_system_score_gemma":0.0006741003,"threshold_uncertainty_score":0.99932325},"labels":[],"label_agreement":null},{"id":"W2616321189","doi":"","title":"An Information System to Prevent Adverse Frug-Food Interactions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Business","score_opus":0.008127253224558947,"score_gpt":0.2819615928587966,"score_spread":0.27383433963423764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616321189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076471255,0.0000014231464,0.98019975,0.00045211703,0.000060337872,0.0001743798,7.6316053e-7,0.0009957921,0.0104683265],"genre_scores_gemma":[0.7675531,3.361969e-7,0.2317765,0.00055360835,0.000015301333,0.000013394849,0.0000023790178,0.0000013339198,0.00008405542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932706,0.000024678751,0.00022085644,0.0001431167,0.00015926117,0.00012503835],"domain_scores_gemma":[0.99917907,0.000009210463,0.000067943096,0.00055223366,0.00009282091,0.00009872036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103977596,0.000078903846,0.0000890236,0.00021531878,0.00006810075,0.00008238106,0.000486209,0.000020694837,0.000009379451],"category_scores_gemma":[0.00001155594,0.000070040995,0.000046546702,0.00041288228,0.0000033140966,0.0035263347,0.00005303503,0.00005756949,0.00017123485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006547933,0.00023654841,0.00005505908,0.000013378805,0.000029663408,0.0000026993912,0.0027211693,0.0053674094,0.0020291153,0.619777,0.0030303234,0.36673108],"study_design_scores_gemma":[0.00054832845,0.003046812,0.009748365,0.00023109643,0.00005849021,0.00009662516,0.0026894656,0.7537204,0.13258672,0.011744265,0.08404257,0.0014868465],"about_ca_topic_score_codex":0.000008101291,"about_ca_topic_score_gemma":0.000018091492,"teacher_disagreement_score":0.759906,"about_ca_system_score_codex":0.00011918817,"about_ca_system_score_gemma":0.000015525773,"threshold_uncertainty_score":0.2856189},"labels":[],"label_agreement":null},{"id":"W2620680811","doi":"10.5220/0006294904210431","title":"A LRAAM-based Partial Order Function for Ontology Matching in the Context of Service Discovery","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Ontology; Computer science; Context (archaeology); Matching (statistics); Information retrieval; Function (biology); Order (exchange); Service (business); Service discovery; World Wide Web; Web service; Mathematics; Epistemology; History; Business; Statistics","score_opus":0.027764242982738947,"score_gpt":0.31544474870273176,"score_spread":0.2876805057199928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620680811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033655327,0.000009149424,0.9605582,0.004939128,0.00006427915,0.00020826535,0.0000010716238,0.000044887907,0.00051970506],"genre_scores_gemma":[0.9483013,6.6374264e-7,0.04895124,0.0026026182,0.000020190811,0.000064373526,0.0000019672902,0.0000036350455,0.00005400733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992911,0.000050068065,0.00019120889,0.00020769959,0.00011514828,0.00014473357],"domain_scores_gemma":[0.9987099,0.00019281969,0.00018814497,0.0007975453,0.000099544646,0.000012018357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035061323,0.00007790055,0.00015995424,0.000055720706,0.0001407195,0.00012562491,0.0009752711,0.00004124033,0.0000040283257],"category_scores_gemma":[0.00007165083,0.000051255374,0.000057372923,0.00011371862,0.000038298538,0.0007909338,0.000100913334,0.00006498107,0.0000019367683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001713679,0.00027355948,0.0055906,0.000061863204,0.00004869179,0.0000045576794,0.0019229761,0.0007511954,0.0074784886,0.9188078,0.00044773423,0.06444113],"study_design_scores_gemma":[0.0039024726,0.00076899363,0.03735023,0.00011767932,0.000108528715,0.000007743386,0.0017200949,0.59563535,0.06341626,0.28741583,0.008786908,0.0007698879],"about_ca_topic_score_codex":0.0011948962,"about_ca_topic_score_gemma":0.010496617,"teacher_disagreement_score":0.91464597,"about_ca_system_score_codex":0.000016193742,"about_ca_system_score_gemma":0.000040937342,"threshold_uncertainty_score":0.5857359},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09530499901207543,"score_gpt":0.3885107134879918,"score_spread":0.29320571447591637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621499279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898168,0.0005793973,0.007969677,0.0006035087,0.0001889668,0.00008056129,9.9764215e-8,0.000052289688,0.00070874364],"genre_scores_gemma":[0.9947664,0.00010818636,0.004795257,0.0001898637,0.00009522943,0.000012443999,2.5505364e-7,0.0000075223547,0.000024811643],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869967,0.0005482541,0.00024423577,0.00020696552,0.0001535133,0.00014735691],"domain_scores_gemma":[0.998625,0.0005036257,0.00049963675,0.00024146843,0.000060304174,0.0000699692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550594,0.00012243696,0.0001934847,0.00012127515,0.000818793,0.00021578753,0.00033601906,0.0000438121,0.000004207895],"category_scores_gemma":[0.00045714006,0.00008744654,0.000060154835,0.00006031756,0.00016491431,0.0012643107,0.0001410782,0.0004127598,0.000002475369],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018985748,0.00022408867,0.0024568115,0.000015178,0.00021574445,0.0003280238,0.010566239,0.00008456237,0.7246523,0.00032108286,0.00011102028,0.2591264],"study_design_scores_gemma":[0.0062828963,0.008794182,0.08923363,0.0006024441,0.00024404311,0.0039795334,0.0044649765,0.006958601,0.8749256,0.002829205,0.00088416634,0.00080072554],"about_ca_topic_score_codex":0.0000012613626,"about_ca_topic_score_gemma":2.8922176e-7,"teacher_disagreement_score":0.25832567,"about_ca_system_score_codex":0.000021458862,"about_ca_system_score_gemma":0.0000125336755,"threshold_uncertainty_score":0.62975764},"labels":[],"label_agreement":null},{"id":"W2696068122","doi":"10.18653/v1/w17-2407","title":"Extract with Order for Coherent Multi-Document Summarization","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; University of Lethbridge","keywords":"Automatic summarization; Readability; Computer science; Coherence (philosophical gambling strategy); Rank (graph theory); Natural language processing; Key (lock); Artificial intelligence; Information retrieval; Selection (genetic algorithm); Sentence; Multi-document summarization; Mathematics","score_opus":0.02839285591499323,"score_gpt":0.3345133148343654,"score_spread":0.3061204589193722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2696068122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004225254,0.000009299714,0.99695075,0.0005699566,0.00003583214,0.00033243006,4.7431524e-7,0.00022709642,0.0014516225],"genre_scores_gemma":[0.23394823,0.0000059384165,0.762968,0.00008243172,0.000013844776,0.00007974889,0.0000031861227,0.000006670347,0.0028919608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992926,0.000008832717,0.000119345736,0.0002800512,0.00014431315,0.00015485795],"domain_scores_gemma":[0.9987231,0.000028765011,0.0001523586,0.0008737561,0.00017883755,0.000043184267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011894734,0.00009629025,0.00010928697,0.00004289887,0.00028058793,0.00033231537,0.0007631347,0.000027959577,0.000018934486],"category_scores_gemma":[0.00005098231,0.000068063455,0.000033307326,0.00006157786,0.000032736807,0.00094535993,0.00014200724,0.000037347327,0.000007990232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003554674,0.00037573912,0.014153871,0.000030863943,0.00013686031,0.000009915485,0.00023192032,0.0006040573,0.0051260027,0.27635083,0.0024194121,0.700525],"study_design_scores_gemma":[0.0025272614,0.00054415636,0.015954625,0.00006635104,0.00006139726,0.0000073007927,0.000030058673,0.7975342,0.11097078,0.025974603,0.045402512,0.00092672836],"about_ca_topic_score_codex":0.00004207155,"about_ca_topic_score_gemma":0.0002373632,"teacher_disagreement_score":0.7969302,"about_ca_system_score_codex":0.00003391502,"about_ca_system_score_gemma":0.000028329907,"threshold_uncertainty_score":0.32045248},"labels":[],"label_agreement":null},{"id":"W2716951971","doi":"10.1109/ccece.2017.7946724","title":"Keyword and Keyphrase Extraction using Newton's Law of Universal Gravitation","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Automatic summarization; Word (group theory); Keyword extraction; Newton's law of universal gravitation; Character (mathematics); Weighting; Artificial intelligence; Information retrieval; Text generation; Natural language processing; Word lists by frequency; Task (project management); Gravitation; Sentence; Linguistics","score_opus":0.02751827136155425,"score_gpt":0.3366664469700549,"score_spread":0.3091481756085006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2716951971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090426005,0.000010892478,0.90622294,0.0002066712,0.000033304423,0.000045132863,2.6418647e-7,0.000059128342,0.002995638],"genre_scores_gemma":[0.7520138,0.0000073159704,0.24775562,0.000020486248,0.0000084101985,4.0614518e-7,3.8483603e-7,0.000002368396,0.00019122317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99954265,0.000016163805,0.000097048935,0.00016536539,0.00010330215,0.00007546575],"domain_scores_gemma":[0.9992588,0.000026930666,0.00018034985,0.00043431038,0.00006805044,0.000031566724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009720246,0.00005679776,0.000089596506,0.000063988664,0.00019819182,0.00009595143,0.00027989468,0.000030393512,0.000003445174],"category_scores_gemma":[0.000020013571,0.000054805274,0.000026625516,0.000056926292,0.00008918479,0.0016296055,0.00012492966,0.000041779313,9.333038e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053632816,0.000026857379,0.0010349018,0.000007004135,0.000013032368,0.000007275234,0.00015377782,0.00007973626,0.0981168,0.8611365,0.00004487653,0.03937386],"study_design_scores_gemma":[0.0007428645,0.00013570311,0.015158071,0.00006328524,0.00007102818,0.00003055369,0.00020031954,0.2750707,0.4516612,0.2525297,0.0038403054,0.00049625704],"about_ca_topic_score_codex":0.0006623885,"about_ca_topic_score_gemma":0.00014426334,"teacher_disagreement_score":0.6615878,"about_ca_system_score_codex":0.000023620556,"about_ca_system_score_gemma":0.000012147176,"threshold_uncertainty_score":0.22348942},"labels":[],"label_agreement":null},{"id":"W272747895","doi":"10.1353/ils.2014.0016","title":"Information Behaviour Research: Where Have We Been, Where Are We Going? / La recherche en comportement informationnel : D’où nous venons, vers quoi nous nous dirigeons?","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nous; Field (mathematics); Humanities; Computer science; Mathematics; Philosophy","score_opus":0.09874961997334779,"score_gpt":0.32889974048400283,"score_spread":0.23015012051065503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W272747895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05588395,0.016704964,0.64531124,0.21222785,0.0037491985,0.0025797533,0.00040036527,0.00046431905,0.06267836],"genre_scores_gemma":[0.8528961,0.016311267,0.12595083,0.0031568336,0.00029508234,0.000026729795,0.000061226325,0.000034602916,0.0012673475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99467146,0.00075314514,0.0018262638,0.00021527725,0.0014444488,0.0010894111],"domain_scores_gemma":[0.99374217,0.0007726797,0.0017519853,0.00064013264,0.0013274213,0.0017656281],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.008493838,0.00037134474,0.00048030776,0.0029631774,0.0013137099,0.0040004733,0.00230486,0.00044161582,0.00013635082],"category_scores_gemma":[0.0013719768,0.000367872,0.00015484936,0.002628236,0.0012277458,0.06504081,0.00034062634,0.0019002652,0.00014584741],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005108578,0.00008263447,0.018107152,0.00065069814,0.00006801367,0.000060921437,0.14254119,0.003112648,0.000016194434,0.05753758,0.08091949,0.6968524],"study_design_scores_gemma":[0.00070946047,0.00050376623,0.008059273,0.001638956,0.000031420554,0.00059356634,0.02385927,0.03684554,0.00019710738,0.0032355683,0.9237839,0.0005421863],"about_ca_topic_score_codex":0.0015969778,"about_ca_topic_score_gemma":0.003084345,"teacher_disagreement_score":0.8428644,"about_ca_system_score_codex":0.0010794947,"about_ca_system_score_gemma":0.007898903,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W2736357342","doi":"10.3934/bdia.2017001","title":"First steps in the investigation of automated text annotation with pictures","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Computer graphics (images)","score_opus":0.0545208875358242,"score_gpt":0.2972021565263602,"score_spread":0.24268126899053596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736357342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04637691,0.000020030893,0.9497119,0.0023196382,0.00003333533,0.0002257778,0.000035510766,0.00014134953,0.0011355495],"genre_scores_gemma":[0.98064476,0.000058144007,0.018843364,0.00029439232,0.000008645055,0.0000027998628,0.00014270468,0.0000012950604,0.00000388764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993725,0.000019019479,0.00024671823,0.000088019115,0.00020587783,0.0000679071],"domain_scores_gemma":[0.99840426,0.00004155015,0.0003787983,0.0010594872,0.00009680167,0.000019114992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003433328,0.000063796746,0.00008865106,0.0001524964,0.00016562246,0.0003230604,0.0010228701,0.000030349438,4.735706e-7],"category_scores_gemma":[0.00014516282,0.000040639123,0.000008035832,0.00022786736,0.000090047026,0.005547599,0.0001976025,0.000055472025,0.0000019229037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006274159,0.00011075445,0.14823961,0.00048231133,0.00017662812,0.000008481132,0.029302575,0.007711764,0.00019104796,0.2216241,0.019471485,0.5726185],"study_design_scores_gemma":[0.00017463637,0.000031515545,0.18842876,0.000030202737,0.000011689412,0.0000028779643,0.00014963966,0.80556655,0.00019140312,0.00085831323,0.0044878176,0.00006661746],"about_ca_topic_score_codex":0.000051498544,"about_ca_topic_score_gemma":0.00020546633,"teacher_disagreement_score":0.9342679,"about_ca_system_score_codex":0.000009519614,"about_ca_system_score_gemma":0.00003155703,"threshold_uncertainty_score":0.40218753},"labels":[],"label_agreement":null},{"id":"W2740737347","doi":"10.5539/ibr.v10n9p1","title":"An Integrated Methodology for Approaching Sentiment Analysis in Business Domain","year":2017,"lang":"en","type":"article","venue":"International Business Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sentiment analysis; Computer science; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Data science; Data mining; Mathematics","score_opus":0.19898083347813106,"score_gpt":0.5018635052710343,"score_spread":0.30288267179290324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740737347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03754325,0.000019546922,0.9561562,0.0049227867,0.00018618072,0.00032656544,0.000010353815,0.00009484438,0.00074029795],"genre_scores_gemma":[0.56083715,0.000016516617,0.43858263,0.00003138213,0.000081660735,0.00017909684,0.000058298247,0.000011493471,0.00020175645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99695325,0.00050605537,0.0004149167,0.0008060263,0.00085285294,0.0004669121],"domain_scores_gemma":[0.99491686,0.00052876066,0.00022037287,0.0014381579,0.0028139446,0.00008190851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049164165,0.0001721408,0.00038167788,0.002382996,0.0004557715,0.0009909574,0.004521281,0.00011302052,0.000031104835],"category_scores_gemma":[0.0018959423,0.00015624742,0.000113757655,0.002515596,0.0002181147,0.0017752432,0.00084042427,0.0003116835,0.000008577118],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060638785,0.0023296715,0.1875792,0.00011831349,0.0025585843,0.0003066926,0.0020980425,0.03617733,0.05377971,0.37342465,0.00066085765,0.34036055],"study_design_scores_gemma":[0.0010344798,0.00004983631,0.58067054,0.00006486173,0.000046848763,0.000011413482,0.00016277244,0.29249635,0.005369811,0.11128573,0.008331295,0.00047607883],"about_ca_topic_score_codex":0.0016522829,"about_ca_topic_score_gemma":0.000957066,"teacher_disagreement_score":0.5232939,"about_ca_system_score_codex":0.00031256033,"about_ca_system_score_gemma":0.00015611814,"threshold_uncertainty_score":0.9555825},"labels":[],"label_agreement":null},{"id":"W2746131889","doi":"10.1016/j.jpain.2004.02.573","title":"Other","year":2004,"lang":"en","type":"article","venue":"Journal of Pain","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Chronic pain; Cognition; Salient; Multidimensional scaling; Medicine; Psychology; Cognitive psychology; Clinical psychology; Applied psychology; Physical therapy; Psychiatry; Artificial intelligence; Computer science; Machine learning","score_opus":0.009906544577876932,"score_gpt":0.27415197258420504,"score_spread":0.2642454280063281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2746131889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023868615,0.00010752057,0.99538124,0.0014746414,0.000038292055,0.000012866909,4.1444544e-8,0.00003066172,0.0005678734],"genre_scores_gemma":[0.4885231,0.000006999958,0.51046133,0.00086324906,0.00007618636,2.7425827e-7,1.1656178e-8,0.0000034483053,0.0000653765],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994514,0.000052409032,0.00018885279,0.000053083637,0.00017458874,0.00007967974],"domain_scores_gemma":[0.9994984,0.000040349634,0.00018610178,0.00015820212,0.000074602685,0.00004229642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000981056,0.000042193504,0.000098284276,0.000108522094,0.000019363062,0.00002906227,0.00046056602,0.000019021636,0.000008541391],"category_scores_gemma":[0.00009927575,0.000031759453,0.000085264524,0.00019041571,0.000012441048,0.00033746983,0.00003016699,0.000092930946,0.000008763171],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013634868,0.00038275777,0.002424059,0.000013714973,0.00015699536,0.0004665478,0.001704275,0.004802137,0.042650778,0.43784714,0.008901653,0.5006363],"study_design_scores_gemma":[0.0006495964,0.0004578729,0.00088527816,0.000103928025,0.000014522202,0.00017220933,0.000043340773,0.0018699081,0.035996668,0.89314294,0.066441365,0.00022236607],"about_ca_topic_score_codex":0.0000029112489,"about_ca_topic_score_gemma":0.0000029089856,"teacher_disagreement_score":0.50041395,"about_ca_system_score_codex":0.000050305352,"about_ca_system_score_gemma":0.00003896607,"threshold_uncertainty_score":0.12951128},"labels":[],"label_agreement":null},{"id":"W2752756221","doi":"10.3233/aac-170027","title":"Ontological representations of rhetorical figures for argument mining","year":2017,"lang":"en","type":"article","venue":"Argument & Computation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Science and Engineering Research Board; University of Waterloo","keywords":"Rhetorical question; Argument (complex analysis); Computer science; Linguistics; Epistemology; Natural language processing; Philosophy; Medicine","score_opus":0.06141192465762198,"score_gpt":0.3821481057053004,"score_spread":0.3207361810476784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752756221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033361603,0.000040158597,0.96358263,0.0010112672,0.0001456751,0.00033137816,0.0000021016137,0.0001349112,0.0013902812],"genre_scores_gemma":[0.6450034,0.000008140262,0.35474694,0.000039970684,0.00002975151,0.00006156222,0.000010088288,0.0000041639473,0.000095969175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872434,0.00004445487,0.00036913445,0.00038393665,0.0002871422,0.0001909672],"domain_scores_gemma":[0.9984565,0.00024579043,0.0004681062,0.0005918239,0.00018183306,0.000055954824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026048275,0.0001191249,0.00022403935,0.00009968263,0.00037198883,0.00015644805,0.0007090706,0.000051198178,0.000005463393],"category_scores_gemma":[0.00020569176,0.00011083646,0.00012647755,0.000090895366,0.000064333566,0.000563846,0.00022133214,0.000053079286,0.000004244533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063085616,0.00088892854,0.016927341,0.00008992162,0.0002603325,0.000015694339,0.0022558009,0.012879133,0.01016124,0.46638876,0.008313111,0.48175666],"study_design_scores_gemma":[0.0014132587,0.0006686781,0.04984435,0.00009313107,0.00008458897,0.000007708832,0.00013702136,0.71813244,0.032456703,0.19358343,0.0030740835,0.0005045844],"about_ca_topic_score_codex":0.0000227126,"about_ca_topic_score_gemma":0.000010117508,"teacher_disagreement_score":0.7052533,"about_ca_system_score_codex":0.000071856484,"about_ca_system_score_gemma":0.000027001934,"threshold_uncertainty_score":0.45197797},"labels":[],"label_agreement":null},{"id":"W2765761355","doi":"10.1007/978-3-319-67837-5_11","title":"Opinions Sandbox: Turning Emotions on Topics into Actionable Analytics","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Sandbox (software development); Computer science; Sentiment analysis; Analytics; sort; Product (mathematics); Service (business); Plan (archaeology); Data science; World Wide Web; Operations research; Artificial intelligence; Information retrieval; Engineering; Marketing; Business; Software engineering","score_opus":0.028024601738707862,"score_gpt":0.2834433201999242,"score_spread":0.25541871846121633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765761355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020779236,0.00011339311,0.9930056,0.0018781072,0.00039882865,0.00029837634,0.000024871895,0.0001065489,0.004153502],"genre_scores_gemma":[0.0071820943,0.00014583525,0.992012,0.00014874831,0.00018044737,0.000017479008,0.000042675172,0.000014002504,0.00025671552],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988279,0.00000852122,0.0005101171,0.00018244637,0.00026985613,0.00020121284],"domain_scores_gemma":[0.997797,0.0002411228,0.0006165457,0.0011002884,0.00019622044,0.000048818336],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002702265,0.00026146838,0.00035965734,0.00029629815,0.0019876158,0.00034718306,0.0026529117,0.00020008562,8.0678194e-7],"category_scores_gemma":[0.00011610671,0.00021715318,0.00024352797,0.00015125371,0.00037251104,0.00054940843,0.00092053117,0.00048286997,7.636448e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.023695e-7,0.000011802868,0.0000019649829,0.00006982903,0.00007977105,6.854545e-8,0.0006636541,0.68194175,0.0000055266737,0.28736994,0.000128867,0.029726338],"study_design_scores_gemma":[0.00012445809,0.00007077815,0.000042963504,0.0003015483,0.000055344764,0.0000062511367,0.0000025834481,0.8605307,0.00013203721,0.019123955,0.11927478,0.00033460362],"about_ca_topic_score_codex":0.000023924247,"about_ca_topic_score_gemma":0.0000611893,"teacher_disagreement_score":0.26824597,"about_ca_system_score_codex":0.0001083008,"about_ca_system_score_gemma":0.00016045694,"threshold_uncertainty_score":0.9993117},"labels":[],"label_agreement":null},{"id":"W2767742613","doi":"10.5406/amerjpsyc.130.4.0401","title":"S. S. Stevens’s Invariant Legacy: Scale Types and the Power Law","year":2017,"lang":"en","type":"article","venue":"The American Journal of Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Sketch; Perception; Power (physics); Psychophysics; Epistemology; Cognitive psychology; Cognitive science; Computer science; Philosophy; Algorithm","score_opus":0.013219934637145946,"score_gpt":0.3316426457040686,"score_spread":0.31842271106692266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767742613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29911104,0.00097242044,0.52664405,0.15079506,0.0006090459,0.00018520604,9.521338e-7,0.00005919369,0.02162301],"genre_scores_gemma":[0.9709869,0.00012737012,0.0237564,0.0049989754,0.00007304773,0.0000016726777,2.2169829e-8,0.0000063083457,0.00004932105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898714,0.0002795317,0.00026251137,0.00014607144,0.00015881505,0.00016594047],"domain_scores_gemma":[0.9975114,0.00017070479,0.0010433618,0.0011183236,0.00010295865,0.000053239964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011615664,0.00009373215,0.0003344389,0.00005345502,0.00034171587,0.00019724615,0.0022667928,0.000018369856,0.000007695758],"category_scores_gemma":[0.00007314078,0.000045059693,0.000097730386,0.00010367164,0.00231424,0.00044208602,0.0002700328,0.00028224237,0.000008063431],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007215875,0.00014595491,0.0017609298,0.0000022873523,0.00048228205,0.00014042233,0.004116508,0.000020337604,0.003804314,0.6733053,0.005656205,0.3098439],"study_design_scores_gemma":[0.0044687195,0.0027678506,0.1269003,0.000077597026,0.00026472338,0.0053666444,0.0007476792,0.0007458997,0.0020300732,0.79456425,0.06142097,0.0006452665],"about_ca_topic_score_codex":0.00007063101,"about_ca_topic_score_gemma":0.000029171022,"teacher_disagreement_score":0.67187583,"about_ca_system_score_codex":0.0000096196645,"about_ca_system_score_gemma":0.000021042992,"threshold_uncertainty_score":0.85269135},"labels":[],"label_agreement":null},{"id":"W2770119650","doi":"10.1002/asi.23980","title":"Improving interpretations of topic modeling in microblogs","year":2017,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; McGill University; Ontario Tech University; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; CRC Health Group","keywords":"Computer science; Perplexity; Topic model; Information retrieval; Microblogging; WordNet; Social media; Process (computing); Latent Dirichlet allocation; Coherence (philosophical gambling strategy); Natural language processing; Artificial intelligence; Data science; World Wide Web; Language model","score_opus":0.010995341567729244,"score_gpt":0.2826981526934637,"score_spread":0.27170281112573447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770119650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21303453,0.000020493399,0.7801721,0.0059825503,0.00018969989,0.00013372929,0.0000010622433,0.0000175327,0.00044827603],"genre_scores_gemma":[0.97254705,0.000011364433,0.027374215,0.000049187285,0.000004120643,0.000002558912,4.825371e-8,6.403827e-7,0.000010808246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999216,0.0000067266765,0.0003930732,0.000047160585,0.0002421658,0.00009487521],"domain_scores_gemma":[0.9970284,0.000038590293,0.0015312847,0.00024302915,0.0011470172,0.000011655621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015918779,0.00003464235,0.00010871063,0.0006369776,0.000262754,0.00014350307,0.0012104916,0.000052275664,9.258675e-8],"category_scores_gemma":[0.0035354542,0.00002515818,0.00003527306,0.0004966231,0.00009514194,0.004375622,0.00024312768,0.0001025793,1.8607193e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000896883,0.00004396843,0.060426056,0.00003798161,0.00003506683,2.2870202e-7,0.0032229316,0.0017868701,0.039212212,0.44358447,0.00008665003,0.45155457],"study_design_scores_gemma":[0.0007635803,0.000115870644,0.006845902,0.00009038963,0.000020209767,0.00001662283,0.00048366463,0.79245526,0.061320726,0.13684006,0.00092180463,0.00012593974],"about_ca_topic_score_codex":0.000007798694,"about_ca_topic_score_gemma":0.000009973252,"teacher_disagreement_score":0.79066837,"about_ca_system_score_codex":0.0001616152,"about_ca_system_score_gemma":0.00013882073,"threshold_uncertainty_score":0.4232524},"labels":[],"label_agreement":null},{"id":"W2783735091","doi":"10.1109/bigdata.2017.8258529","title":"Big data in psychology: Using word embeddings to study theory-of-mind","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Concreteness; Word (group theory); Reliability (semiconductor); Reading (process); Big data; Computer science; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognitive science; Linguistics; Data mining; Philosophy","score_opus":0.19015671293255137,"score_gpt":0.4556427411724217,"score_spread":0.26548602823987033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783735091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29139984,0.000009821739,0.70683205,0.00016645828,0.00007637561,0.00016343137,7.6877774e-7,0.00004092482,0.0013103323],"genre_scores_gemma":[0.68531686,0.00000184922,0.31449413,0.00010676899,0.000017947543,0.000003223981,3.3662855e-7,0.000004767909,0.0000540998],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99867254,0.00007335848,0.00026989778,0.0006077938,0.00017785658,0.00019856935],"domain_scores_gemma":[0.99513465,0.00006128731,0.00017690285,0.004531631,0.00004562562,0.00004987734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011834248,0.000108941334,0.00023199887,0.00025763363,0.00012072131,0.000117990945,0.004918281,0.000037878413,0.000016482965],"category_scores_gemma":[0.00024793603,0.000093806324,0.000024277493,0.00031900711,0.000058752532,0.00073419284,0.002720291,0.000100007324,0.000012390745],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010490496,0.00027297912,0.04173683,0.0000013519078,0.000026488655,0.00002263155,0.0008305985,0.000010523212,0.002552411,0.0038298,0.00006783591,0.95063806],"study_design_scores_gemma":[0.003091435,0.00094258215,0.513028,0.00020954647,0.00014344798,0.000035856483,0.0013631255,0.0715404,0.0456213,0.35721385,0.0047319136,0.0020785043],"about_ca_topic_score_codex":0.000080556325,"about_ca_topic_score_gemma":0.0002124237,"teacher_disagreement_score":0.9485596,"about_ca_system_score_codex":0.000015995965,"about_ca_system_score_gemma":0.000018776966,"threshold_uncertainty_score":0.9139471},"labels":[],"label_agreement":null},{"id":"W2784269545","doi":"10.1007/s10115-017-1147-9","title":"Localized user-driven topic discovery via boosted ensemble of nonnegative matrix factorization","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea","keywords":"Matrix decomposition; Computer science; Factorization; Matrix (chemical analysis); Non-negative matrix factorization; Mathematics; Artificial intelligence; Algorithm; Physics","score_opus":0.009477174681492609,"score_gpt":0.27222000813632263,"score_spread":0.26274283345483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784269545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008855678,0.00012224691,0.98438627,0.000015741414,0.00025055773,0.00026616032,0.0000040465006,0.0001296512,0.005969643],"genre_scores_gemma":[0.99416596,0.00002827914,0.00522039,0.000018021148,0.000072750074,0.00001907101,0.000018231027,0.0000038393664,0.00045345858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990214,0.0000616472,0.00049897237,0.00012355116,0.00016759874,0.00012683329],"domain_scores_gemma":[0.9987667,0.000052858122,0.00033687556,0.000302989,0.00049613643,0.00004443526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015434873,0.00011462625,0.00023264493,0.00022900292,0.00009510397,0.00015631893,0.00025008322,0.00007590473,0.0000026841956],"category_scores_gemma":[0.00003804567,0.00009677953,0.000041324336,0.00048589995,0.000057744586,0.006133218,0.00012677854,0.000049158127,0.00005639518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074589494,0.00018656041,0.009965869,0.0011208307,0.00028577296,0.0000013972071,0.049601134,0.00036865307,0.02266013,0.7827153,0.004224543,0.12879518],"study_design_scores_gemma":[0.001671128,0.0006605422,0.00333431,0.000424275,0.00005095641,0.000021778565,0.0008624777,0.66804457,0.122110076,0.002384871,0.19969285,0.00074217445],"about_ca_topic_score_codex":0.0000356293,"about_ca_topic_score_gemma":0.000011701871,"teacher_disagreement_score":0.98531026,"about_ca_system_score_codex":0.000050832383,"about_ca_system_score_gemma":0.000038194154,"threshold_uncertainty_score":0.4446435},"labels":[],"label_agreement":null},{"id":"W2786269463","doi":"10.3390/jrfm11010008","title":"Estimation of Cross-Lingual News Similarities Using Text-Mining Methods","year":2018,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Similarity (geometry); Natural language processing; Artificial intelligence; Word (group theory); Information retrieval; Task (project management); The Internet; World Wide Web; Image (mathematics); Linguistics","score_opus":0.0254576792545957,"score_gpt":0.3778261132054529,"score_spread":0.3523684339508572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786269463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15738414,0.00023278686,0.8419334,0.000014492524,0.0001521258,0.000045229004,5.777319e-7,0.000014863673,0.00022233753],"genre_scores_gemma":[0.41990063,0.00017091965,0.57979894,0.000029048322,0.00008609795,3.7557655e-7,6.602797e-8,0.0000030606643,0.0000108711965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989481,0.00007282992,0.0004946773,0.00013608887,0.0002163718,0.00013196336],"domain_scores_gemma":[0.99885774,0.00008014857,0.00064142817,0.0001790681,0.0002032001,0.000038406903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009561155,0.00009603518,0.00025296834,0.00030456166,0.00014596299,0.00009625952,0.0003127494,0.000041027713,0.0000025066843],"category_scores_gemma":[0.00022834474,0.00008458168,0.000084885185,0.00033055793,0.0001235279,0.00062364794,0.000219029,0.00010280232,2.785089e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016400581,0.000023196766,0.0016391041,0.000018721385,0.000015366708,0.000010363237,0.00084051467,0.0014252947,0.0001056478,0.008804823,0.00003421377,0.9870663],"study_design_scores_gemma":[0.0021635136,0.0017322475,0.08229946,0.00078519835,0.00061199063,0.00012608018,0.0010355362,0.485156,0.04695399,0.35402954,0.024185892,0.00092055777],"about_ca_topic_score_codex":0.000017378365,"about_ca_topic_score_gemma":0.0000061989385,"teacher_disagreement_score":0.9861458,"about_ca_system_score_codex":0.000032690088,"about_ca_system_score_gemma":0.00002727646,"threshold_uncertainty_score":0.3449141},"labels":[],"label_agreement":null},{"id":"W2786731957","doi":"10.18653/v1/w17-5532","title":"Generating and Evaluating Summaries for Partial Email Threads: Conversational Bayesian Surprise and Silver Standards","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Automatic summarization; Surprise; Thread (computing); Annotation; Redundancy (engineering); Information retrieval; Bayesian probability; Natural language processing; Artificial intelligence; Machine learning; Programming language","score_opus":0.03591123173986498,"score_gpt":0.3603061999791383,"score_spread":0.32439496823927333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786731957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04586593,0.000118583215,0.9526403,0.0007014276,0.000047958845,0.00019909907,0.000016005133,0.00011326428,0.00029743533],"genre_scores_gemma":[0.51934975,0.00001841301,0.48030367,0.00010102503,0.00006165842,0.000027436197,0.0000038137566,0.000005924931,0.00012827755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887323,0.000034113425,0.00019990088,0.00037185996,0.0003304732,0.0001903964],"domain_scores_gemma":[0.9988605,0.00019588151,0.00017194609,0.0004255806,0.0002749322,0.00007117276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001012201,0.0001204763,0.00017791665,0.000046739136,0.000886096,0.0007466176,0.00029399636,0.000045776156,0.000015957216],"category_scores_gemma":[0.0006452099,0.00010540018,0.000036920716,0.000033159402,0.00016627372,0.0010838007,0.0003084065,0.0000533427,2.95091e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007067459,0.00005160378,0.08376414,0.00009268186,0.00018959337,0.000009282322,0.0026854053,0.0003003713,0.013592048,0.37904423,0.0025663055,0.5176337],"study_design_scores_gemma":[0.0005714644,0.000104385705,0.0016596065,0.000018157612,0.00002727066,0.0000039704864,0.00005374595,0.9512197,0.011677869,0.033420693,0.0010127937,0.00023038728],"about_ca_topic_score_codex":0.00006399939,"about_ca_topic_score_gemma":0.00022818803,"teacher_disagreement_score":0.9509193,"about_ca_system_score_codex":0.00003341265,"about_ca_system_score_gemma":0.00009940865,"threshold_uncertainty_score":0.7199651},"labels":[],"label_agreement":null},{"id":"W2792698203","doi":"10.3115/v1/w14-21","title":"Proceedings of the First Workshop on Argumentation Mining","year":2014,"lang":"en","type":"paratext","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Joint Information Systems Committee; European Commission; National Science Foundation","keywords":"Argumentation theory; Computer science; Data science; Epistemology; Philosophy","score_opus":0.016015825415811577,"score_gpt":0.28411471498866686,"score_spread":0.26809888957285527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792698203","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093328505,0.00006260176,0.44378456,0.0015208068,0.0005948666,0.0004245927,0.0000014676723,0.00018827144,0.5524896],"genre_scores_gemma":[0.16469768,0.00026374217,0.28842047,0.0035301934,0.0005138473,0.00022323843,0.000017419708,0.00008672072,0.5422467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863416,0.000009039412,0.00032752161,0.00044040362,0.00041074413,0.00017815098],"domain_scores_gemma":[0.99872184,0.000108633685,0.00053090183,0.00045026463,0.00016089743,0.000027473443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017112734,0.00021615643,0.00030165352,0.00017629455,0.00010485551,0.00011207915,0.001645354,0.00016057673,0.00011653359],"category_scores_gemma":[0.000042836185,0.0001415911,0.00015744193,0.00060135213,0.000050506485,0.0002414719,0.00036582103,0.00021230128,0.00025531038],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036762674,0.00004667329,0.00007317426,0.00008498894,0.00004970133,1.2220644e-7,0.00042810978,0.00020475494,0.00023891771,0.026799487,0.95117986,0.020890541],"study_design_scores_gemma":[0.00038374966,0.00021064478,0.00045794042,0.0021695883,0.00009193437,0.000004882429,0.0001640887,0.017904794,0.112874225,0.004787755,0.85983646,0.0011139357],"about_ca_topic_score_codex":0.000005500419,"about_ca_topic_score_gemma":0.000009474869,"teacher_disagreement_score":0.1637644,"about_ca_system_score_codex":0.00007503418,"about_ca_system_score_gemma":0.000025204094,"threshold_uncertainty_score":0.57739174},"labels":[],"label_agreement":null},{"id":"W2793407730","doi":"10.5220/0006664405520559","title":"Modeling a Tool for Conducting Systematic Reviews Iteratively","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Systems engineering; Engineering","score_opus":0.17384002596433243,"score_gpt":0.3854992197691817,"score_spread":0.2116591938048493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793407730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009799381,0.0002163618,0.99658644,0.00009559607,0.00005355181,0.0010895114,2.1259154e-7,0.00033163524,0.0006467669],"genre_scores_gemma":[0.24800636,0.0000090982285,0.7508248,0.00033311395,0.00006706814,0.00027385514,4.03223e-7,0.0000060593798,0.00047922597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988212,0.00008734462,0.00048617696,0.00031072408,0.00011231134,0.00018227288],"domain_scores_gemma":[0.9989216,0.0001374939,0.00013642208,0.00051523576,0.00026052076,0.000028773047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009998969,0.00011735991,0.0003757915,0.000080793856,0.00014646348,0.00014428415,0.0005282834,0.000028160026,0.000007342603],"category_scores_gemma":[0.00062264956,0.00008219418,0.0001157637,0.00026512967,0.000019141991,0.0007878225,0.00011525655,0.00004144885,0.000044433727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008112885,0.00010610402,0.000022793909,0.01382266,0.00016316827,0.0000033638298,0.005913152,0.0006758953,0.035812814,0.90827036,0.0028562346,0.032345336],"study_design_scores_gemma":[0.00005732772,0.000047896203,5.966247e-8,0.0007427329,0.0000133477915,0.000004370535,0.000023777438,0.9819033,0.0071054613,0.009659491,0.00030915573,0.00013308763],"about_ca_topic_score_codex":0.0000034590166,"about_ca_topic_score_gemma":0.0000059283507,"teacher_disagreement_score":0.9812274,"about_ca_system_score_codex":0.000032980424,"about_ca_system_score_gemma":0.000014974346,"threshold_uncertainty_score":0.33517814},"labels":[],"label_agreement":null},{"id":"W2802218424","doi":"10.14288/1.0365983","title":"Multimodal human brain connectivity analysis based on graph theory","year":2018,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Graph theory; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.007363979779461453,"score_gpt":0.21290133771178843,"score_spread":0.20553735793232697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802218424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48362648,0.0000054505394,0.51487875,0.00007514727,0.000020905318,0.00009183435,0.00001940688,0.00022870813,0.001053341],"genre_scores_gemma":[0.9794292,0.0000021280232,0.020055734,0.00021095408,0.000020016323,6.4056843e-7,0.000010413124,0.000008813519,0.0002621324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982698,0.00024890635,0.00013600894,0.00070285244,0.0003633989,0.00027903687],"domain_scores_gemma":[0.9982165,0.00022531941,0.00019813764,0.00094438385,0.00029346198,0.00012219916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060331123,0.000068658024,0.00038646656,0.00032502136,0.0004977676,0.0001349781,0.0011394335,0.00010624646,0.00012631727],"category_scores_gemma":[0.0000743541,0.00022923634,0.0003862985,0.001999672,0.0005516964,0.0005453367,0.00024119794,0.00014774947,0.00001643959],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033791268,0.00096481957,0.05018034,0.00003333773,0.00087455387,0.0002631592,0.000702321,0.00045709463,0.0036725113,0.0014369477,0.0027187737,0.93866235],"study_design_scores_gemma":[0.000532858,0.00023939686,0.9530738,0.00003160579,0.00014079071,0.0000028419638,0.00012143988,0.033167627,0.00003499701,0.012326058,0.00006174699,0.0002668301],"about_ca_topic_score_codex":0.026546981,"about_ca_topic_score_gemma":0.22668584,"teacher_disagreement_score":0.9383955,"about_ca_system_score_codex":0.000088677196,"about_ca_system_score_gemma":0.00004726718,"threshold_uncertainty_score":0.97993535},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.017873356744103102,"score_gpt":0.3525913017325484,"score_spread":0.33471794498844526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806157614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16567513,0.00023244876,0.8201202,0.010348824,0.0004292305,0.00028860132,0.0000071626396,0.000101370475,0.0027970336],"genre_scores_gemma":[0.84467584,0.0003840783,0.15445937,0.00016513087,0.00026496584,0.000018842225,0.000011573842,0.000006773431,0.0000134360325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985374,0.00014219846,0.0007138874,0.00020817346,0.00021327862,0.00018505791],"domain_scores_gemma":[0.99814904,0.00046473072,0.0005160295,0.00044714188,0.00037503746,0.00004800059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060242804,0.00014003705,0.00035717984,0.0003288777,0.00008711033,0.000080124686,0.0016849117,0.00014429042,0.000080163634],"category_scores_gemma":[0.00025447522,0.00012379469,0.000078631514,0.00014843312,0.00095879263,0.00031020684,0.00036619455,0.0002519523,0.000006065185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013655005,0.00011873439,0.00013759585,0.0000027044857,0.000043296888,0.000005261978,0.00030676895,0.0000023083676,0.0024844247,0.8884551,0.00021148364,0.10809581],"study_design_scores_gemma":[0.001113732,0.00020753958,0.0028352048,0.00004614548,0.0000251635,0.0001857371,0.000081138474,0.0066979537,0.022125585,0.95673627,0.009782816,0.0001627232],"about_ca_topic_score_codex":0.0000026679463,"about_ca_topic_score_gemma":0.000006330364,"teacher_disagreement_score":0.6790007,"about_ca_system_score_codex":0.00011396564,"about_ca_system_score_gemma":0.000027081483,"threshold_uncertainty_score":0.50482005},"labels":[],"label_agreement":null},{"id":"W2810540096","doi":"10.3233/aac-180037","title":"An annotation scheme for Rhetorical Figures","year":2018,"lang":"en","type":"article","venue":"Argument & Computation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; University of Waterloo","keywords":"Rhetorical question; Annotation; Scheme (mathematics); Computer science; Natural language processing; Linguistics; Artificial intelligence; Mathematics; Philosophy","score_opus":0.028278597947934452,"score_gpt":0.35779315040429455,"score_spread":0.3295145524563601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810540096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030295463,0.000017333923,0.9681867,0.00033302634,0.00014537993,0.00025600832,9.824892e-7,0.00044576026,0.00031939187],"genre_scores_gemma":[0.55429685,0.0000016083359,0.44532683,0.00016711596,0.00011340418,0.000033965403,0.000025250345,0.0000055556566,0.000029437466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989659,0.00004223447,0.00021701488,0.00036677145,0.00022529085,0.00018278185],"domain_scores_gemma":[0.9991711,0.00007073621,0.00012366995,0.0002751189,0.00029836336,0.00006103329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020594736,0.00010738741,0.000111902,0.000127184,0.00018008622,0.00013184025,0.00034010987,0.00004268655,0.000005531365],"category_scores_gemma":[0.000029159788,0.00010745275,0.000051065894,0.00032555687,0.000032992473,0.0009289562,0.000045699275,0.00004175532,0.00003344668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039426268,0.00044416066,0.00094623666,0.000027533919,0.000062485,0.0000023595537,0.0018171795,0.002604613,0.037807196,0.31277138,0.008235228,0.6352422],"study_design_scores_gemma":[0.0002707397,0.0005445107,0.0013369258,0.000009707084,0.000008439741,0.0000014744552,0.000016519398,0.88526136,0.023161767,0.08541729,0.0037954405,0.0001758198],"about_ca_topic_score_codex":0.0000053163844,"about_ca_topic_score_gemma":0.000004712946,"teacher_disagreement_score":0.88265675,"about_ca_system_score_codex":0.00008235838,"about_ca_system_score_gemma":0.000024048604,"threshold_uncertainty_score":0.4381796},"labels":[],"label_agreement":null},{"id":"W2810801822","doi":"10.3390/s18072117","title":"Using Stigmergy to Distinguish Event-Specific Topics in Social Discussions","year":2018,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stigmergy; Event (particle physics); Computer science; Data science; Psychology; Human–computer interaction; Cognitive science; Communication; Artificial intelligence; Physics","score_opus":0.05025072984723933,"score_gpt":0.3580322272384279,"score_spread":0.3077814973911886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810801822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37121964,0.000014779538,0.62457496,0.0013407536,0.00024983234,0.0001246279,0.0000019394047,0.00023405401,0.0022394075],"genre_scores_gemma":[0.84255177,0.000002614577,0.15629047,0.00012543207,0.00051504385,0.0000036195293,8.6285115e-7,0.0000097978855,0.00050036947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890405,0.000063110405,0.00021797023,0.0003425972,0.00019103414,0.00028124166],"domain_scores_gemma":[0.99941313,0.00002201192,0.000060473034,0.00035270688,0.00008016092,0.00007153472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011999782,0.0001103097,0.00015599064,0.00013875205,0.00024629253,0.00005924848,0.0004448868,0.000048567174,0.000015626814],"category_scores_gemma":[0.00008058047,0.00009671343,0.000058450893,0.0008665342,0.000061626735,0.00012496229,0.00025554775,0.00009882499,0.000029709276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034643977,0.00043159683,0.009850702,0.000020867556,0.000059302165,0.000213786,0.02196936,0.003421783,0.0349044,0.4597363,0.0129939485,0.45636332],"study_design_scores_gemma":[0.0010602152,0.00040439688,0.075423904,0.00031522856,0.00003863058,0.00002916059,0.0014760994,0.24044025,0.054891314,0.12617289,0.49692976,0.0028181325],"about_ca_topic_score_codex":0.000032015003,"about_ca_topic_score_gemma":0.00014559906,"teacher_disagreement_score":0.48393583,"about_ca_system_score_codex":0.00010428715,"about_ca_system_score_gemma":0.000018805411,"threshold_uncertainty_score":0.39438593},"labels":[],"label_agreement":null},{"id":"W2826552311","doi":"","title":"Real-time Change Point Detection using On-line Topic Models.","year":2018,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Change detection; Line (geometry); Computer science; Point (geometry); Bayesian probability; Social media; Topic model; Data mining; Artificial intelligence; Mathematics; World Wide Web","score_opus":0.07014499979451327,"score_gpt":0.31555338110763737,"score_spread":0.2454083813131241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2826552311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05644544,0.000003662443,0.9311918,0.00028896055,0.00008682533,0.00011398997,4.522008e-7,0.00045853655,0.011410343],"genre_scores_gemma":[0.757795,0.0000111778645,0.241539,0.00019934191,0.00026215706,0.000012069795,5.136837e-7,0.000008518224,0.00017227064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991158,0.000034160297,0.00014206315,0.00031361904,0.00019181536,0.00020252237],"domain_scores_gemma":[0.9991983,0.000020385472,0.00007249675,0.00055728084,0.00009911207,0.00005238585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014671849,0.00010549783,0.00013073023,0.00014576367,0.000114771385,0.000043581338,0.00036287357,0.00005244607,0.000050961407],"category_scores_gemma":[0.000014248938,0.000098429184,0.00005320694,0.00034521485,0.00004119909,0.0005756358,0.0001513545,0.00007685091,0.00007665023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014564584,0.00008526596,0.000014102765,0.0000071524305,0.000022806766,0.000012251703,0.0007919516,0.00025143515,0.4737149,0.03707502,0.0001614665,0.4878491],"study_design_scores_gemma":[0.00006363783,0.00016265901,0.00003319182,0.000014192211,0.0000051400557,0.000004946262,0.0000018599002,0.7622749,0.12101965,0.11613286,0.00018142081,0.00010549767],"about_ca_topic_score_codex":0.000051574087,"about_ca_topic_score_gemma":0.000016333091,"teacher_disagreement_score":0.7620235,"about_ca_system_score_codex":0.000099066514,"about_ca_system_score_gemma":0.000012179757,"threshold_uncertainty_score":0.40138254},"labels":[],"label_agreement":null},{"id":"W2883250117","doi":"10.6084/m9.figshare.c.4174325.v1","title":"Supplementary material from \"Appetitive information seeking behaviour reveals robust daily rhythmicity for Internet-based food-related keyword searches\"","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The Internet; Behaviour change; Internet privacy; Computer science; Advertising; Psychology; World Wide Web; Business","score_opus":0.03570539376612959,"score_gpt":0.2759296156537625,"score_spread":0.24022422188763293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883250117","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019478466,0.000008052929,0.46941128,0.00028591455,0.00018804718,0.0011170187,0.50868595,0.00060984335,0.00021543294],"genre_scores_gemma":[0.6746741,2.9606414e-7,0.09954136,0.00048278127,0.00014850595,0.0003291875,0.22476922,0.000018443994,0.00003609911],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838215,0.000075387914,0.00046484306,0.0003912138,0.00030710152,0.00037931668],"domain_scores_gemma":[0.99859065,0.00015421402,0.00031509556,0.00048471792,0.0003620245,0.00009328183],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015430356,0.00022286114,0.00024749912,0.00019179584,0.0001479227,0.00030997026,0.0008286551,0.00013041486,0.03203077],"category_scores_gemma":[0.00021747561,0.000230413,0.00012729455,0.0002864436,0.000022431663,0.001317715,0.0004620845,0.00015595324,0.00019419826],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027584683,0.00029150367,0.0033431195,0.00039972784,0.00050548185,0.00002807971,0.0057571433,0.00031783816,0.0055871983,0.0029483547,0.9304977,0.050048023],"study_design_scores_gemma":[0.004243543,0.0027205274,0.026356163,0.0049454803,0.00014968764,0.000017036957,0.00029690284,0.38864037,0.43406513,0.009718105,0.12627168,0.0025753698],"about_ca_topic_score_codex":0.00012703889,"about_ca_topic_score_gemma":0.00013873613,"teacher_disagreement_score":0.804226,"about_ca_system_score_codex":0.0001921663,"about_ca_system_score_gemma":0.000074932046,"threshold_uncertainty_score":0.96885407},"labels":[],"label_agreement":null},{"id":"W2884251704","doi":"10.46867/ijcp.2018.31.00.01","title":"Erratum: How and Why Does Category Learning Cause Categorical Perception?","year":2018,"lang":"en","type":"erratum","venue":"International Journal of Comparative Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"","keywords":"Perception; Categorical variable; Psychology; Cognitive psychology; Communication; Computer science; Neuroscience; Machine learning","score_opus":0.04067674895692886,"score_gpt":0.3931664117920442,"score_spread":0.35248966283511535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884251704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014689537,0.0014381154,0.9356154,0.01344634,0.030779129,0.00014792025,0.0000062953204,0.000121963516,0.016975865],"genre_scores_gemma":[0.8291336,0.006155614,0.06683511,0.004451544,0.011927304,0.000037069723,0.000120220975,0.00010139927,0.08123811],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99681723,0.00050801854,0.0008020994,0.00064338057,0.00090405665,0.00032523967],"domain_scores_gemma":[0.99514544,0.00018447355,0.001694489,0.00041943727,0.0023713605,0.0001847759],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005345865,0.00044186352,0.0009240938,0.0008674007,0.00013147612,0.00039603584,0.0025552064,0.00043760132,0.00011493332],"category_scores_gemma":[0.00011371002,0.00033216062,0.00027893315,0.0002964894,0.00047671754,0.0009998049,0.00042076575,0.002173545,0.000028617858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006360844,0.00012421412,0.00040698372,0.000005915184,0.00070711423,0.0002536086,0.0014471216,0.000009797325,0.0003755164,0.004108521,0.9900957,0.0024019103],"study_design_scores_gemma":[0.00071171485,0.0008336253,0.004806375,0.000103749764,0.000106617736,0.0019006869,0.0002449759,0.0016070013,0.00006609675,0.074370146,0.91468966,0.00055935734],"about_ca_topic_score_codex":0.000012375466,"about_ca_topic_score_gemma":0.00005474006,"teacher_disagreement_score":0.8687803,"about_ca_system_score_codex":0.00023478104,"about_ca_system_score_gemma":0.0001882422,"threshold_uncertainty_score":0.99991304},"labels":[],"label_agreement":null},{"id":"W2889229100","doi":"","title":"NLP for Conversations: Sentiment, Summarization, and Group Dynamics","year":2018,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of the Fraser Valley","funders":"","keywords":"Automatic summarization; Computer science; Natural language processing; Sentiment analysis; Artificial intelligence; Dynamics (music); Information retrieval; Group (periodic table); Psychology","score_opus":0.029641051308958492,"score_gpt":0.33400512286884554,"score_spread":0.30436407155988704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889229100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022873981,0.0000059121244,0.98510706,0.0013288442,0.0008410563,0.00020433999,0.00006772694,0.00018254119,0.012033785],"genre_scores_gemma":[0.65475446,0.000009998177,0.34360698,0.0005893228,0.00037410198,0.000025323567,0.00033500182,0.000009663789,0.0002951428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869466,0.000027507103,0.00032474627,0.00041571647,0.00038352763,0.00015383662],"domain_scores_gemma":[0.99665546,0.0003312222,0.00020108136,0.00019566862,0.0025463144,0.00007025339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018226441,0.00015513077,0.0001368855,0.0002340172,0.00020372542,0.00026942889,0.00052764855,0.000058399735,0.00003166263],"category_scores_gemma":[0.0008596759,0.00016914503,0.00004835144,0.00017620935,0.00015853466,0.00014379172,0.00014838426,0.00008526821,0.000023379867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012493152,0.000053810403,0.00046468852,0.0000042665556,0.000045242447,0.000001169833,0.00007284122,0.0004951333,0.000017612201,0.99399006,0.0006902702,0.0041523976],"study_design_scores_gemma":[0.00020775186,0.000094772724,0.0003544072,0.000017917757,0.000007680129,0.0000019088413,0.000012703083,0.6216614,0.00006746326,0.3717184,0.0057367496,0.0001187825],"about_ca_topic_score_codex":0.000009104454,"about_ca_topic_score_gemma":0.000026833899,"teacher_disagreement_score":0.6545257,"about_ca_system_score_codex":0.00012969351,"about_ca_system_score_gemma":0.00008732676,"threshold_uncertainty_score":0.6897534},"labels":[],"label_agreement":null},{"id":"W2890039419","doi":"10.1007/978-3-030-00066-0_11","title":"Venue Classification of Research Papers in Scholarly Digital Libraries","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Canadian Institute for Advanced Research","keywords":"Computer science; Digital library; Information retrieval; Library science; World Wide Web; Art","score_opus":0.04333766805299147,"score_gpt":0.318591590279443,"score_spread":0.2752539222264515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890039419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056297594,0.00030295044,0.9887537,0.00039249402,0.0002347293,0.00027895844,0.0000049822565,0.00013019484,0.0093390085],"genre_scores_gemma":[0.6725947,0.000044432752,0.3266309,0.00013203245,0.00021824689,0.000013922372,0.0000070325086,0.000030285113,0.0003284248],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961579,0.000058170303,0.0005641473,0.0012555106,0.0014265673,0.0005377078],"domain_scores_gemma":[0.99685913,0.0006225824,0.00029241032,0.0016225353,0.0005044533,0.00009889018],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013914749,0.00029886054,0.00043974866,0.0021169956,0.00015820588,0.0012257218,0.0041255667,0.0003173799,0.000013623518],"category_scores_gemma":[0.0005067818,0.00028857577,0.00009614809,0.0018515169,0.0021529219,0.0032150147,0.0016183967,0.0011215347,0.000025590338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000108594395,0.000055460554,0.00087303604,0.000046937937,0.000010262847,0.000046771216,0.0016285144,0.00058592163,0.0018622873,0.07794938,0.000029378913,0.9169012],"study_design_scores_gemma":[0.00018137723,0.00031451246,0.0020196454,0.0008794534,0.0000036871152,0.00001462128,0.0000012674489,0.07647056,0.0062254076,0.9088324,0.0044987747,0.00055833894],"about_ca_topic_score_codex":0.00000792151,"about_ca_topic_score_gemma":0.00004176205,"teacher_disagreement_score":0.91634285,"about_ca_system_score_codex":0.0003091139,"about_ca_system_score_gemma":0.0006029132,"threshold_uncertainty_score":0.99995667},"labels":[],"label_agreement":null},{"id":"W2892333563","doi":"10.1108/jarhe-03-2018-0047","title":"Digital library keyword analysis for visualization education research","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Research in Higher Education","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Visualization; Computer science; Digital library; Information retrieval; Relevance (law); Information visualization; Thesaurus; World Wide Web; Selection (genetic algorithm); Data science; Data mining; Artificial intelligence","score_opus":0.11472020053815307,"score_gpt":0.4795430512056294,"score_spread":0.36482285066747633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892333563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11733507,0.001416161,0.7051954,0.021481877,0.0023682623,0.0032120477,0.000011545822,0.00028675757,0.14869282],"genre_scores_gemma":[0.93622005,0.00007743347,0.058585957,0.000111433066,0.0013882502,0.00016272788,0.00003268633,0.000022989314,0.003398466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99696505,0.00023289394,0.0006838894,0.00039830603,0.0012629878,0.00045690002],"domain_scores_gemma":[0.995964,0.0005964996,0.00032234058,0.000590978,0.0023378627,0.00018831414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032925212,0.00012205619,0.0002741662,0.0051948894,0.00025509202,0.0007430623,0.0013355952,0.00012291956,0.000087266315],"category_scores_gemma":[0.00014969087,0.00011096189,0.00013019779,0.009740383,0.00021730585,0.0021735637,0.00023692251,0.0005102337,0.000030279769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002526855,0.0022161081,0.008220997,0.00007713809,0.00022197429,0.0000015212435,0.0012541484,0.0001098667,0.002243932,0.5928175,0.058831748,0.3337524],"study_design_scores_gemma":[0.00043248406,0.0006706358,0.019153018,0.00015942862,0.000053801585,0.0000056805557,0.00079490856,0.0027412784,0.014758294,0.6282034,0.3326916,0.0003354803],"about_ca_topic_score_codex":0.0000064179962,"about_ca_topic_score_gemma":0.000003642076,"teacher_disagreement_score":0.81888497,"about_ca_system_score_codex":0.00040739737,"about_ca_system_score_gemma":0.0020510987,"threshold_uncertainty_score":0.7165367},"labels":[],"label_agreement":null},{"id":"W2894138074","doi":"10.1167/18.10.971","title":"The Impact of Self-Relevance and Valence on Word Processing: an ERP study","year":2018,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Psychology; Valence (chemistry); Trait; Cognition; Cognitive psychology; Recall; Emotional valence; Event-related potential; Cognitive bias; Developmental psychology; Neuroscience","score_opus":0.014434976634239921,"score_gpt":0.3768346529064032,"score_spread":0.3623996762721633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894138074","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9259539,0.00029870478,0.07341977,0.00010336113,0.00004386538,0.00009061128,1.4405927e-7,0.000031678737,0.000057930305],"genre_scores_gemma":[0.9670505,0.0001483944,0.03269908,0.000014257063,0.00007091228,5.645379e-7,1.863503e-8,0.000004954864,0.0000113007945],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99887323,0.00009818338,0.000346527,0.00015103028,0.0004060684,0.00012493184],"domain_scores_gemma":[0.998406,0.00013261722,0.0005944679,0.00035230175,0.0004418993,0.00007269712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008846875,0.00009474979,0.00018248646,0.000120097015,0.00017007209,0.00011294825,0.0007161202,0.000024416591,0.0000011800546],"category_scores_gemma":[0.000115709954,0.00004985696,0.000066880726,0.00035879103,0.00007514568,0.00092242646,0.00010605178,0.00015485659,9.52046e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018024839,0.0012310866,0.009755622,0.00000967071,0.00007671501,0.000020370853,0.003565035,0.000115154624,0.01893832,0.00028458066,0.0005161163,0.96530706],"study_design_scores_gemma":[0.0017831433,0.05600247,0.77263963,0.0008543271,0.00011425726,0.00020813578,0.0006097437,0.11556566,0.017533105,0.03316583,0.00095991173,0.0005637731],"about_ca_topic_score_codex":0.0000038117225,"about_ca_topic_score_gemma":0.0000039041456,"teacher_disagreement_score":0.9647433,"about_ca_system_score_codex":0.00004951857,"about_ca_system_score_gemma":0.00006582128,"threshold_uncertainty_score":0.20331079},"labels":[],"label_agreement":null},{"id":"W2895058937","doi":"","title":"Multiple In-text Reference Phenomenon","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Phenomenon; Computer science; Epistemology; Philosophy","score_opus":0.019466237835809606,"score_gpt":0.25161854705288045,"score_spread":0.23215230921707083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895058937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007920034,0.00061684893,0.9042158,0.006226459,0.00011513769,0.00040255545,0.00002109292,0.0007000825,0.07978195],"genre_scores_gemma":[0.74282926,0.0005539814,0.2516401,0.000091776,0.000017564093,0.00013625761,0.00007792122,0.000036912417,0.0046162205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933781,0.0034020692,0.0007306476,0.0014099943,0.00054214196,0.00053701724],"domain_scores_gemma":[0.99140984,0.0016674283,0.0006677893,0.0045743384,0.0014935347,0.00018706675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0041049756,0.00043948265,0.000544101,0.0005017788,0.00019990232,0.00044564446,0.0044316077,0.00034760727,0.000071234295],"category_scores_gemma":[0.0013234168,0.00042035704,0.00019406609,0.0006966033,0.00020274245,0.0004944375,0.0046124067,0.00080222974,0.00011220455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009654879,0.00070519425,0.004850063,0.00012212073,0.000074082476,0.000020755318,0.0057348316,0.000066422144,0.00857731,0.6471839,0.00080126,0.33185443],"study_design_scores_gemma":[0.0020943335,0.0000018014125,0.013436503,0.0075612883,0.000062203486,0.00002012662,0.000087282904,0.11836077,0.2180932,0.5654461,0.07173056,0.0031058588],"about_ca_topic_score_codex":0.00054487726,"about_ca_topic_score_gemma":0.0019529046,"teacher_disagreement_score":0.73490924,"about_ca_system_score_codex":0.00032819714,"about_ca_system_score_gemma":0.0002797388,"threshold_uncertainty_score":0.9998248},"labels":[],"label_agreement":null},{"id":"W2895115809","doi":"10.1145/3209280.3229100","title":"Automatic Term Extraction in Technical Domain using Part-of-Speech and Common-Word Features","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Terminology; Term (time); Domain (mathematical analysis); Confusion; Technical documentation; Documentation; Key (lock); Natural language processing; Ambiguity; Artificial intelligence; Information retrieval; Word (group theory); Speech recognition; Programming language; Linguistics","score_opus":0.02079483283180173,"score_gpt":0.3401692492987932,"score_spread":0.3193744164669915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895115809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.504366,0.00003941881,0.49393797,0.00015618166,0.00003786834,0.00012896722,2.2675208e-7,0.00028941056,0.0010439975],"genre_scores_gemma":[0.5537058,0.0000055828586,0.44620535,0.000032979184,0.000022948936,0.0000038493704,2.9144448e-7,0.0000037950442,0.000019388843],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901444,0.000061417246,0.0002944831,0.0002740418,0.00018029455,0.0001753481],"domain_scores_gemma":[0.9992344,0.00009859985,0.00012446729,0.0004575785,0.00004331729,0.00004163996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003239706,0.000109821645,0.00021941248,0.00022061003,0.00006121784,0.00005296579,0.0003516468,0.00008716277,0.000019254632],"category_scores_gemma":[0.000030024888,0.00009397733,0.000036101766,0.0005180302,0.00015335905,0.00049333466,0.00021566852,0.00013594591,0.0000021338997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008574971,0.00015141768,0.013684557,0.000033818058,0.000019203204,0.000035193967,0.0004189313,0.000006514137,0.12010962,0.03577922,0.0003763963,0.8293766],"study_design_scores_gemma":[0.0009401056,0.00047106112,0.25785625,0.0005145289,0.000049638384,0.00065137935,0.00012551404,0.178467,0.32632223,0.23150183,0.0020106426,0.001089802],"about_ca_topic_score_codex":0.000078633864,"about_ca_topic_score_gemma":0.0004925153,"teacher_disagreement_score":0.82828677,"about_ca_system_score_codex":0.000055171593,"about_ca_system_score_gemma":0.000018894798,"threshold_uncertainty_score":0.38322842},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12209439307154113,"score_gpt":0.4211929597768534,"score_spread":0.29909856670531226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895553377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011868847,0.00031770952,0.98672014,0.0006576189,0.000044449458,0.0002658181,0.000056577588,0.0000347991,0.00003406258],"genre_scores_gemma":[0.64467174,0.000058554044,0.35473102,0.00030315077,0.00009062464,0.00000362435,0.000012390804,0.000017559087,0.00011130951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805045,0.0003504214,0.00065171183,0.0002475818,0.00047868764,0.00022111775],"domain_scores_gemma":[0.9930553,0.0021770555,0.0012661167,0.0024792515,0.00094765244,0.00007461584],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0041675353,0.0001558396,0.00054126995,0.00026838607,0.00039183596,0.00024028521,0.012544175,0.00004375356,0.000030245286],"category_scores_gemma":[0.0011052488,0.000079633144,0.00020940264,0.0016938156,0.00037502608,0.0018510488,0.0019458694,0.0002174175,0.0000034805732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002890169,0.0017756255,0.015323426,0.00007572374,0.031980265,0.000033986267,0.09723904,0.013109,0.011623624,0.07515208,0.059273254,0.6915238],"study_design_scores_gemma":[0.0027604839,0.008019617,0.022756515,0.00033439655,0.016968448,0.00019231469,0.032106183,0.8089886,0.017922973,0.03450182,0.053988695,0.0014599977],"about_ca_topic_score_codex":0.0001627808,"about_ca_topic_score_gemma":0.00041856154,"teacher_disagreement_score":0.79587954,"about_ca_system_score_codex":0.000029910827,"about_ca_system_score_gemma":0.00012144141,"threshold_uncertainty_score":0.99279845},"labels":[],"label_agreement":null},{"id":"W2901340518","doi":"10.3389/fpsyg.2018.02185","title":"Concise, Simple, and Not Wrong: In Search of a Short-Hand Interpretation of Statistical Significance","year":2018,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Interpretation (philosophy); Simple (philosophy); Meaning (existential); Psychology; Relevance (law); Cognitive psychology; Computer science; Epistemology","score_opus":0.02158321688355779,"score_gpt":0.3669483879343335,"score_spread":0.3453651710507757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901340518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063578375,0.000114108465,0.9354854,0.00009941198,0.00011436753,0.00013662911,0.000006938189,0.000013560166,0.0004512076],"genre_scores_gemma":[0.71280354,0.000044251123,0.28703785,0.00008913522,0.0000066126013,0.000009006392,0.0000017440398,0.000003841884,0.000003995352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877906,0.00014547243,0.00039457972,0.0003574002,0.00013318191,0.00019029477],"domain_scores_gemma":[0.99935484,0.0001045264,0.00007680967,0.00033900427,0.00008920609,0.00003559428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039491837,0.00008456363,0.00031971402,0.00038985087,0.000013254065,0.000008430947,0.00038158972,0.00007881847,0.000007229038],"category_scores_gemma":[0.00007705532,0.00008731927,0.000019120711,0.0004835164,0.0007011546,0.00015491455,0.00008994962,0.00012978227,5.205231e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041532656,0.00017350094,0.21559575,0.000052328982,0.000037707552,0.000023672736,0.0034025363,0.00003899761,0.01852248,0.014292305,0.0040492886,0.7433961],"study_design_scores_gemma":[0.0018766616,0.0018626392,0.311762,0.00012082136,0.000021408907,0.000015130579,0.00039943898,0.3931825,0.042549897,0.24688318,0.0008307332,0.0004956224],"about_ca_topic_score_codex":0.000029854704,"about_ca_topic_score_gemma":0.00007647821,"teacher_disagreement_score":0.7429005,"about_ca_system_score_codex":0.000028433858,"about_ca_system_score_gemma":0.000027469776,"threshold_uncertainty_score":0.35607764},"labels":[],"label_agreement":null},{"id":"W2903706655","doi":"","title":"Personalization of an Environmental Message: Developing a Measure","year":2018,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Personalization; Measure (data warehouse); Computer science; Internet privacy; World Wide Web; Data mining","score_opus":0.010902697356835066,"score_gpt":0.25053837038483,"score_spread":0.23963567302799493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903706655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013107429,0.000025679488,0.98551947,0.0002178783,0.00042758678,0.00020513369,0.000006849963,0.000017417911,0.00047257973],"genre_scores_gemma":[0.98427224,0.0000040893483,0.015441543,0.000080410304,0.00009928628,0.0000048027346,0.0000028835693,0.0000030025317,0.000091720256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844927,0.000099400764,0.00066309236,0.000041675954,0.0006606031,0.00008598085],"domain_scores_gemma":[0.9962964,0.000056838846,0.0027771273,0.00015939157,0.0006860719,0.00002418957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016619334,0.00006120669,0.00015688306,0.00015071046,0.00013439034,0.000108899876,0.00050022826,0.00006159297,7.261261e-7],"category_scores_gemma":[0.00026195822,0.000044104323,0.00011065944,0.00026355617,0.00001412958,0.0026425815,0.00004178687,0.000057565878,0.0000028291104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003018716,0.00046078,0.09060278,0.0007902602,0.0024350076,9.021786e-7,0.1096127,0.010827169,0.048707757,0.61226356,0.018057473,0.10593973],"study_design_scores_gemma":[0.005989035,0.0015866939,0.07333269,0.0011673147,0.00043488148,0.0002180296,0.008512687,0.4383488,0.1437755,0.012643996,0.31269875,0.0012916311],"about_ca_topic_score_codex":0.0000023998834,"about_ca_topic_score_gemma":0.0000013119025,"teacher_disagreement_score":0.9711648,"about_ca_system_score_codex":0.0005022898,"about_ca_system_score_gemma":0.0000781677,"threshold_uncertainty_score":0.19158079},"labels":[],"label_agreement":null},{"id":"W2907738398","doi":"10.1016/j.eswa.2018.12.054","title":"Ranking résumés automatically using only résumés: A method free of job offers","year":2018,"lang":"fr","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Consejo Nacional de Ciencia y Tecnología; Association Nationale de la Recherche et de la Technologie","keywords":"Ranking (information retrieval); Computer science; Relevance (law); Rank (graph theory); Information retrieval; Similarity (geometry); Job analysis; Vocabulary; Selection (genetic algorithm); Process (computing); Learning to rank; Resource (disambiguation); Artificial intelligence; Machine learning; Mathematics; Linguistics; Job satisfaction","score_opus":0.05402005072200111,"score_gpt":0.37502874975065953,"score_spread":0.3210086990286584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907738398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040282335,0.0035773374,0.98667026,0.0012942759,0.00029116438,0.001763818,0.000026900872,0.000563134,0.005410284],"genre_scores_gemma":[0.07703396,0.000051980234,0.9195022,0.00020632197,0.00069782534,0.00074429985,0.00000516738,0.00007448134,0.0016837456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575496,0.00043505442,0.0012320669,0.0010332371,0.00085963163,0.00068502536],"domain_scores_gemma":[0.99418765,0.00045449557,0.00079802953,0.003153383,0.0011349362,0.00027147646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009810503,0.00048247824,0.0009222518,0.00040230175,0.0005113172,0.00026452861,0.0021761649,0.00027436236,0.00007138464],"category_scores_gemma":[0.00009944557,0.0004447196,0.00021022858,0.0019452579,0.00074552774,0.00085353694,0.0004977758,0.00027189378,0.00012585334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027723712,0.0004194276,0.00059900025,0.0004202595,0.00056211243,0.000010768357,0.006492673,0.0007461566,0.0270065,0.917497,0.0051318603,0.041086547],"study_design_scores_gemma":[0.0010320718,0.00045485666,0.00025306648,0.0019660501,0.00030628903,0.00051090244,0.0009770464,0.80976754,0.016552107,0.012883691,0.1540585,0.0012378984],"about_ca_topic_score_codex":0.0022824504,"about_ca_topic_score_gemma":0.00021658768,"teacher_disagreement_score":0.90461326,"about_ca_system_score_codex":0.00034730937,"about_ca_system_score_gemma":0.00059441273,"threshold_uncertainty_score":0.99980044},"labels":[],"label_agreement":null},{"id":"W2908347907","doi":"10.4000/books.aaccademia.4620","title":"UNIBA - Integrating distributional semantics features in a supervised approach for detecting irony in Italian tweets","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Task (project management); Irony; Computer science; Artificial intelligence; Constraint (computer-aided design); Natural language processing; Representation (politics); Semantics (computer science); Polarity (international relations); Distributional semantics; Machine learning; Information retrieval; Semantic similarity; Linguistics; Mathematics; Engineering","score_opus":0.025360972556899394,"score_gpt":0.24859290899076839,"score_spread":0.223231936433869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908347907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000708804,0.00011981551,0.7479243,0.00006166791,0.00007105458,0.0011199377,0.00010483026,0.0003944078,0.24949518],"genre_scores_gemma":[0.18718724,0.00007745314,0.4602839,0.00019092207,0.00035221825,0.000030368621,0.00044900613,0.00015112074,0.35127777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977802,0.000072759016,0.0003984075,0.0009297648,0.00033728676,0.0004815534],"domain_scores_gemma":[0.99846816,0.00025566496,0.00035026588,0.00064781285,0.0001735134,0.00010459161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041157714,0.00045266387,0.00057838886,0.00055949716,0.00019530182,0.00009274439,0.0018648724,0.0008314977,0.0000030056021],"category_scores_gemma":[0.00008884267,0.00051708036,0.00022924259,0.00007675538,0.0001910899,0.0004464707,0.0010033889,0.0012405792,7.580271e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073975774,0.0000429437,0.00027672504,0.00019410525,0.00013143003,0.00010089091,0.0019483679,0.000114125105,0.00037919512,0.9851597,0.0009501399,0.010628409],"study_design_scores_gemma":[0.009979054,0.0008860788,0.0012750381,0.005195924,0.0009019024,0.00015442171,0.0023407848,0.22635274,0.023771327,0.18038152,0.5388933,0.009867919],"about_ca_topic_score_codex":0.00015790942,"about_ca_topic_score_gemma":0.00020414407,"teacher_disagreement_score":0.80477816,"about_ca_system_score_codex":0.0006636884,"about_ca_system_score_gemma":0.00013120906,"threshold_uncertainty_score":0.9997281},"labels":[],"label_agreement":null},{"id":"W2908681319","doi":"10.17821/srels/2018/v55i6/132490","title":"The Accuracy of Newspaper Citation Count Reported and Actual Citation Found in Web of Science Citation Database","year":2018,"lang":"en","type":"article","venue":"SRELS Journal of Information Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Citation; Newspaper; Scopus; Citation database; Web of science; Computer science; Information retrieval; Citation analysis; Database; World Wide Web; Library science; Political science; MEDLINE","score_opus":0.0229233944683186,"score_gpt":0.315035029832838,"score_spread":0.2921116353645194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908681319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16646251,0.000048531816,0.83146226,0.00032181368,0.00017893579,0.0002579025,0.0000014511157,0.000013815717,0.0012527772],"genre_scores_gemma":[0.8972208,0.00023183592,0.10242965,0.00008449337,0.000013630311,0.000004256606,0.000003798433,0.0000020987109,0.000009475673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771655,0.000048951788,0.0011445282,0.00009326474,0.00086545956,0.0001312593],"domain_scores_gemma":[0.9957676,0.00020786616,0.00210985,0.0003153731,0.0015600262,0.000039298357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031235807,0.00008426386,0.00014307142,0.0011001476,0.00014445225,0.00015600126,0.00051875995,0.000021814296,0.0000029546882],"category_scores_gemma":[0.0009882372,0.0000636812,0.00003276445,0.0018163214,0.00032539468,0.007444729,0.00015566293,0.00008447551,0.0000018428659],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002440938,0.0001489276,0.0020816042,0.00031529955,0.00020924075,0.000008720746,0.019736586,0.0041688657,0.01823973,0.25337324,0.0016584834,0.6998152],"study_design_scores_gemma":[0.0061384463,0.0021184918,0.3467344,0.0016784868,0.00030139444,0.00012609201,0.020234806,0.43078202,0.048768178,0.12316925,0.018993685,0.0009547462],"about_ca_topic_score_codex":0.000009287463,"about_ca_topic_score_gemma":0.000020385585,"teacher_disagreement_score":0.73075825,"about_ca_system_score_codex":0.00010953068,"about_ca_system_score_gemma":0.00014916557,"threshold_uncertainty_score":0.5397249},"labels":[],"label_agreement":null},{"id":"W2928032745","doi":"10.1007/s00500-019-03963-y","title":"Automatic keyphrase extraction using word embeddings","year":2019,"lang":"en","type":"article","venue":"Soft Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Department of Industrial and Systems Engineering, Hong Kong Polytechnic University; National Natural Science Foundation of China","keywords":"Word (group theory); Computer science; Natural language processing; Artificial intelligence; Extraction (chemistry); Speech recognition; Linguistics","score_opus":0.014090135774292753,"score_gpt":0.3117116156751691,"score_spread":0.29762147990087634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928032745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40775988,0.00003046406,0.5908777,0.00003628159,0.0001761103,0.00010070002,7.952493e-8,0.00067886617,0.00033992433],"genre_scores_gemma":[0.62391514,6.471087e-7,0.37586227,0.00010420723,0.00005130766,8.448486e-7,6.699202e-7,0.000011663902,0.00005324911],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846596,0.00005742193,0.0003414341,0.00047450172,0.0003012303,0.00035946933],"domain_scores_gemma":[0.99875057,0.00020886614,0.0002803124,0.0006047833,0.00008483312,0.00007061203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040633403,0.00017478433,0.00024620598,0.00021634472,0.00017292927,0.00019185293,0.00063602335,0.000066166955,0.00003701181],"category_scores_gemma":[0.00007128694,0.00018206149,0.00011045615,0.0007000968,0.000022339185,0.0008703593,0.0003663647,0.00021567242,0.0001421058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032245148,0.00010873719,0.00963251,0.00009911078,0.000066949375,0.00003814297,0.0014162688,0.022085488,0.07243502,0.010850584,0.00019692989,0.883067],"study_design_scores_gemma":[0.00011279038,0.000016852451,0.0008158283,0.000094231225,0.000009281709,0.000034166314,0.000035629186,0.98986,0.004978431,0.0035033233,0.00031656103,0.00022291542],"about_ca_topic_score_codex":0.000021293177,"about_ca_topic_score_gemma":0.0000011527806,"teacher_disagreement_score":0.9677745,"about_ca_system_score_codex":0.00014298086,"about_ca_system_score_gemma":0.000043346125,"threshold_uncertainty_score":0.7424252},"labels":[],"label_agreement":null},{"id":"W2943217089","doi":"10.1145/3297280.3297382","title":"Study of linguistic features incorporated in a literary book recommender system","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Recommender system; Computer science; Pleasure; Reading (process); Key (lock); Natural language processing; Information retrieval; Quality (philosophy); Artificial intelligence; World Wide Web; Linguistics; Psychology","score_opus":0.01113746719009497,"score_gpt":0.2691508151635969,"score_spread":0.25801334797350195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943217089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6156848,0.0012657318,0.33264667,0.00019900875,0.0004561019,0.002465932,0.0000018265041,0.0019305126,0.045349427],"genre_scores_gemma":[0.9652565,0.0000029390158,0.03355723,0.00012401387,0.000009943514,0.000018817804,0.0000012214269,0.000007321183,0.0010220151],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886507,0.000113195376,0.0003536774,0.00033601729,0.0001904703,0.00014155361],"domain_scores_gemma":[0.9989054,0.00008667919,0.000161085,0.00070381456,0.0001108329,0.00003217756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023933574,0.000117520554,0.00029210493,0.00031496826,0.000015632302,0.000038091737,0.0006160495,0.000043418364,0.0000124026365],"category_scores_gemma":[0.000025424713,0.00009681723,0.00003644154,0.0007471019,0.000008446328,0.00028104463,0.00025951813,0.00013038094,0.000016913848],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001639171,0.0061972532,0.4437258,0.0007441352,0.00054664986,0.0009268491,0.091771424,0.00103908,0.005433603,0.38795668,0.011484638,0.050009966],"study_design_scores_gemma":[0.018734163,0.012263308,0.21543191,0.0043094843,0.00027018765,0.00030540407,0.018548518,0.4350972,0.052475903,0.22634375,0.009433059,0.0067871157],"about_ca_topic_score_codex":0.0000994698,"about_ca_topic_score_gemma":0.00005816495,"teacher_disagreement_score":0.4340581,"about_ca_system_score_codex":0.00006848419,"about_ca_system_score_gemma":0.000029704557,"threshold_uncertainty_score":0.39480922},"labels":[],"label_agreement":null},{"id":"W2945545832","doi":"10.48550/arxiv.1905.07689","title":"DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Automatic summarization; Graph; Information retrieval; Artificial intelligence; Text graph; Pointer (user interface); Natural language processing; Theoretical computer science","score_opus":0.07042154819932844,"score_gpt":0.2193973463951663,"score_spread":0.14897579819583787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945545832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041629545,0.0001288812,0.9545384,0.00007669587,0.0007466449,0.0007598533,0.00003103711,0.00085443456,0.0012344805],"genre_scores_gemma":[0.9435262,0.00020565432,0.054284997,0.0002201282,0.00017453793,0.0000070753435,0.000038365182,0.00004340986,0.0014996475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967888,0.00013942338,0.000381509,0.0018302503,0.00013779518,0.00072220614],"domain_scores_gemma":[0.99625635,0.0004622933,0.0006876184,0.0021099902,0.0003025171,0.00018125465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004152864,0.0005591797,0.0006834433,0.0005628356,0.0002695789,0.00022425705,0.0029943255,0.00035643665,0.000031145046],"category_scores_gemma":[0.00007784379,0.0006364118,0.0010490591,0.0008942525,0.00013035051,0.000925106,0.0034547772,0.00071729906,0.000056673758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002897525,0.00041297887,0.026997706,0.00041591714,0.0013124796,0.00056583126,0.00055854366,0.46583873,0.00013431536,0.48156327,0.016586881,0.0053236014],"study_design_scores_gemma":[0.0011849264,0.00019527425,0.00076498196,0.0005364006,0.00040689143,0.000011474661,0.00017869097,0.47770378,0.0004943842,0.5134938,0.003508007,0.001521374],"about_ca_topic_score_codex":0.00009104553,"about_ca_topic_score_gemma":0.0000890799,"teacher_disagreement_score":0.90189666,"about_ca_system_score_codex":0.0002102179,"about_ca_system_score_gemma":0.00010343661,"threshold_uncertainty_score":0.9996087},"labels":[],"label_agreement":null},{"id":"W2946532448","doi":"10.1145/3292500.3330727","title":"A User-Centered Concept Mining System for Query and Document Understanding at Tencent","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Knowledge base; Web query classification; Web search query; Web mining; Taxonomy (biology); Query language; Core (optical fiber); Database query","score_opus":0.02961210578107067,"score_gpt":0.2768240722171036,"score_spread":0.2472119664360329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946532448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024729222,0.00009043643,0.972693,0.0002290509,0.00012899886,0.00045239896,0.0000011549147,0.00037172055,0.0013039715],"genre_scores_gemma":[0.8177587,0.000007533173,0.1810308,0.00010285805,0.000012095772,0.000026285663,0.0000016751015,0.0000075651583,0.0010524973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998873,0.000026139773,0.00022873768,0.00042882026,0.00018313916,0.00026018533],"domain_scores_gemma":[0.99924827,0.00013257084,0.00011470293,0.00039235907,0.00003807004,0.00007401063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018405849,0.00013058068,0.0002188983,0.00008753243,0.00010916055,0.00013118985,0.0003347639,0.000040726056,0.000011867435],"category_scores_gemma":[0.0000085968095,0.000108395856,0.000065724635,0.00014057175,0.000029211807,0.00048506784,0.0003442404,0.000034639466,0.000007822846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002542812,0.000023936791,0.0077391383,0.00015134255,0.00009613319,0.000007852138,0.0014438984,0.000093290655,0.005739697,0.9774673,0.0015797807,0.005632184],"study_design_scores_gemma":[0.011593843,0.002383534,0.0018008165,0.00265979,0.0002569984,0.0002720156,0.030909592,0.5765752,0.28032166,0.053403024,0.03548216,0.004341365],"about_ca_topic_score_codex":0.00001248302,"about_ca_topic_score_gemma":0.00001779991,"teacher_disagreement_score":0.9240643,"about_ca_system_score_codex":0.0006098953,"about_ca_system_score_gemma":0.000017529006,"threshold_uncertainty_score":0.44202545},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Structural equation modeling; Path analysis (statistics); Computer science; Bridging (networking); Econometrics; Mathematics; Machine learning","score_opus":0.33215059425669685,"score_gpt":0.48020279125659415,"score_spread":0.1480521969998973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946989286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51249164,0.000050434595,0.48712963,0.000040496216,0.000016728209,0.00014632512,0.0000036340668,0.00007128318,0.000049800514],"genre_scores_gemma":[0.823235,0.000003837834,0.17665845,0.000035685167,0.000008477283,0.000011298329,0.000020859326,0.0000071122217,0.000019282477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724865,0.0005341731,0.00041922758,0.0006199189,0.0008548273,0.00032321215],"domain_scores_gemma":[0.99767613,0.000990823,0.0001707664,0.0007449172,0.00032545373,0.00009192798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017165721,0.00016152725,0.000540507,0.0022379945,0.00011702704,0.00009744045,0.0006518269,0.0001170261,0.00003604261],"category_scores_gemma":[0.00020393297,0.00013929966,0.00019241555,0.004772638,0.00010741181,0.0003024728,0.00024047864,0.0003180062,0.000003928169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001830683,0.0003677298,0.22666937,0.00003947076,0.0004793942,0.000022843455,0.0011645615,0.39330995,0.113784276,0.043229613,0.000025020949,0.2207247],"study_design_scores_gemma":[0.00026510752,0.00026822847,0.0273346,0.000016052034,0.00016820604,8.3453125e-7,0.000033210657,0.9408641,0.030085843,0.00080351654,0.0000032008631,0.00015710738],"about_ca_topic_score_codex":0.0001603069,"about_ca_topic_score_gemma":0.0000067284586,"teacher_disagreement_score":0.54755414,"about_ca_system_score_codex":0.00011477982,"about_ca_system_score_gemma":0.0000436725,"threshold_uncertainty_score":0.5680476},"labels":[],"label_agreement":null},{"id":"W2949826916","doi":"10.48550/arxiv.1810.06387","title":"I can see clearly now: reinterpreting statistical significance","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Null hypothesis; Statistical significance; Null (SQL); CLARITY; Statistical hypothesis testing; Alternative hypothesis; Context (archaeology); Significance testing; Psychology; Cognitive psychology; Computer science; Econometrics; Mathematics; Statistics; History; Biology; Data mining","score_opus":0.041688840126429684,"score_gpt":0.21509957104833752,"score_spread":0.17341073092190784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949826916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024461001,0.000018074767,0.9695979,0.00015942892,0.00024965333,0.00025869135,0.000033706467,0.0008502123,0.0043713385],"genre_scores_gemma":[0.9264341,0.000061847524,0.0715472,0.00013439785,0.00010489258,0.00000197933,0.000016131447,0.00003094983,0.0016684722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697465,0.00023455302,0.0003238753,0.0017600296,0.0001708733,0.00053602015],"domain_scores_gemma":[0.99682015,0.00023753765,0.0003999482,0.0019766192,0.00032183452,0.0002439192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035737825,0.0004145999,0.0004908617,0.00030723872,0.00019281222,0.00021168507,0.002999266,0.00030614453,0.00008361691],"category_scores_gemma":[0.00013034487,0.00049540005,0.00021547431,0.0006480809,0.00033960733,0.0003749211,0.0030622168,0.000841431,0.0002196058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084054256,0.00020043808,0.005382376,0.00015102858,0.00037110443,0.0016058848,0.0007790202,0.038120754,0.00051799446,0.94081414,0.007228983,0.004744223],"study_design_scores_gemma":[0.00018277773,0.00012977718,0.0007830068,0.00018155013,0.00009903928,0.000005289135,0.00003926367,0.63096094,0.00093487476,0.36479965,0.0010437375,0.00084007194],"about_ca_topic_score_codex":0.00023936952,"about_ca_topic_score_gemma":0.00020055476,"teacher_disagreement_score":0.9019731,"about_ca_system_score_codex":0.00045109945,"about_ca_system_score_gemma":0.0002499545,"threshold_uncertainty_score":0.9997498},"labels":[],"label_agreement":null},{"id":"W2950281387","doi":"10.48550/arxiv.1307.8060","title":"Extracting Information-rich Part of Texts using Text Denoising","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Readability; Computer science; Search engine indexing; Set (abstract data type); Text processing; Information retrieval; Relation (database); Noise reduction; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Rest (music); Information extraction; Data mining; Mathematics","score_opus":0.07351421345146757,"score_gpt":0.21806988502735455,"score_spread":0.144555671575887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950281387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27947113,0.00004033977,0.7184516,0.000014525981,0.00013805505,0.00019319152,0.0000030411318,0.00023878242,0.00144928],"genre_scores_gemma":[0.92920995,0.00006687938,0.070440084,0.000039934996,0.00003864995,7.827849e-7,0.000008555769,0.0000132273535,0.00018193379],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982975,0.00009991444,0.00048440305,0.0006069484,0.00016388859,0.0003473358],"domain_scores_gemma":[0.99681985,0.00015484767,0.0010923939,0.0013465007,0.00047234498,0.000114077346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029630394,0.0003131187,0.00044224234,0.00062437926,0.00017655724,0.00018499435,0.0017518819,0.0002738422,0.00003994174],"category_scores_gemma":[0.00010616905,0.0003696821,0.00021488144,0.0009659148,0.00009879383,0.0031237775,0.0021075527,0.000541381,0.000058302452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014353253,0.00016417907,0.008272204,0.0003377749,0.0003472231,0.00008424872,0.0013320008,0.75905585,0.0013036118,0.20194714,0.00040806003,0.026733337],"study_design_scores_gemma":[0.00024377601,0.000029113742,0.0005138429,0.00037968138,0.00015337829,0.000010139595,0.0001869355,0.9132751,0.00473957,0.07841587,0.0012674433,0.0007851319],"about_ca_topic_score_codex":0.00023541196,"about_ca_topic_score_gemma":0.000011384791,"teacher_disagreement_score":0.6497388,"about_ca_system_score_codex":0.00027514473,"about_ca_system_score_gemma":0.00019290212,"threshold_uncertainty_score":0.9998755},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06736840998995927,"score_gpt":0.3578810530827379,"score_spread":0.2905126430927786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950657507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97454876,0.000051875893,0.01761239,0.0071047097,0.0000017242753,0.00019671973,7.8956805e-7,0.000056408535,0.00042660677],"genre_scores_gemma":[0.9800105,0.0000064972373,0.019806396,0.00011920673,0.000037423724,0.000014381887,6.450248e-8,0.0000029142113,0.0000026273576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982503,0.00001272336,0.00017848019,0.00034247627,0.001062951,0.0001530493],"domain_scores_gemma":[0.9993784,0.00009054865,0.00022977727,0.000013887269,0.00024659105,0.000040784784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010723402,0.00007075514,0.00012126681,0.00016128113,0.00015785942,0.00005350732,0.0010109224,0.000033689274,1.7314656e-7],"category_scores_gemma":[0.00007324939,0.000042694293,0.000014153995,0.0033918777,0.0006176758,0.0012639163,0.00020241793,0.0002488344,3.149378e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010162921,0.00016172048,0.40077904,0.0001239193,0.000027197999,7.3717665e-8,0.0030292643,0.052871387,0.043736886,0.45174077,0.000056460784,0.04737166],"study_design_scores_gemma":[0.00008496174,0.00019096644,0.032424368,0.00003476817,0.0000029849598,0.00000295539,0.00010449771,0.93991053,0.0076423534,0.0195468,0.0000025278118,0.00005228274],"about_ca_topic_score_codex":0.000012450919,"about_ca_topic_score_gemma":8.620942e-7,"teacher_disagreement_score":0.8870391,"about_ca_system_score_codex":0.000016714486,"about_ca_system_score_gemma":0.000015197876,"threshold_uncertainty_score":0.22758521},"labels":[],"label_agreement":null},{"id":"W2950905275","doi":"10.48550/arxiv.1706.06542","title":"Extract with Order for Coherent Multi-Document Summarization","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Automatic summarization; Readability; Coherence (philosophical gambling strategy); Computer science; Rank (graph theory); Natural language processing; Key (lock); Selection (genetic algorithm); Sentence; Artificial intelligence; Information retrieval; Mathematics","score_opus":0.08428641476666028,"score_gpt":0.23998538557968446,"score_spread":0.1556989708130242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950905275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005610654,0.000034978726,0.99239403,0.000086577835,0.00014846814,0.0008116193,0.000010213687,0.00040262396,0.0005008238],"genre_scores_gemma":[0.7719092,0.00011832144,0.22414161,0.000035213998,0.000035929686,0.000011936862,0.000052124622,0.000025254536,0.0036704119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814117,0.000057294594,0.00018791707,0.0011805329,0.000111843954,0.0003212602],"domain_scores_gemma":[0.9968162,0.00007332009,0.0005759395,0.0019455105,0.00046962308,0.000119390636],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020004534,0.0003436435,0.00037178455,0.00023304376,0.00029651157,0.00026726437,0.002158992,0.00021718202,0.00001260066],"category_scores_gemma":[0.000051191564,0.00034185036,0.00017211161,0.0002538254,0.000103112565,0.0007451307,0.0012210275,0.00031578747,0.000013082817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024282705,0.00086015963,0.012769694,0.00039444448,0.0010686974,0.00041947857,0.0004600129,0.44118994,0.00032776102,0.5008364,0.0010950768,0.04033554],"study_design_scores_gemma":[0.0010842751,0.00014752861,0.0009365063,0.00018484838,0.00021715339,0.0000024893816,0.000020740246,0.9109704,0.0011418691,0.081223056,0.0032382463,0.00083289924],"about_ca_topic_score_codex":0.0001023032,"about_ca_topic_score_gemma":0.00024901956,"teacher_disagreement_score":0.76825243,"about_ca_system_score_codex":0.0002815101,"about_ca_system_score_gemma":0.00020842295,"threshold_uncertainty_score":0.9999034},"labels":[],"label_agreement":null},{"id":"W2950942184","doi":"10.48550/arxiv.1604.02580","title":"On the Composition of Scientific Abstracts","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Université du Québec à Montréal","keywords":"Sentence; Relevance (law); Similarity (geometry); Computer science; Information retrieval; Composition (language); Phenomenon; Natural language processing; Content (measure theory); Linguistics; Artificial intelligence; Mathematics; Epistemology; Philosophy","score_opus":0.060575209161011875,"score_gpt":0.20249354508480127,"score_spread":0.14191833592378938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950942184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31994337,0.0000083188825,0.67418176,0.00021413487,0.00019071685,0.00012367661,0.000009197116,0.00017007004,0.0051587345],"genre_scores_gemma":[0.9974058,0.000012230644,0.0016170482,0.000046650377,0.00001760198,7.081062e-7,0.0000054564275,0.000007835103,0.0008866321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861217,0.000107056425,0.00019419122,0.00075129536,0.0001392332,0.00019608487],"domain_scores_gemma":[0.99728054,0.00026066246,0.0004261489,0.0017575567,0.00021565869,0.000059439426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038138905,0.000186134,0.0002191816,0.00030472403,0.0001810138,0.00009894399,0.00220549,0.00013243651,0.00002101626],"category_scores_gemma":[0.000032440148,0.00013843368,0.00020463721,0.000518974,0.00029607103,0.00027330365,0.0011677508,0.00029770058,0.00007282989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009282839,0.000076356635,0.00009438837,0.000015231689,0.000043894208,0.000030270536,0.00004356117,0.015563737,0.0025294067,0.9804447,0.00048565402,0.0006634845],"study_design_scores_gemma":[0.00014001862,0.000042966887,0.0008352619,0.0002380321,0.000043503904,0.0000012173801,0.000007269542,0.035388943,0.029609554,0.9331425,0.00025768307,0.0002930846],"about_ca_topic_score_codex":0.000013586378,"about_ca_topic_score_gemma":0.000006922204,"teacher_disagreement_score":0.67746246,"about_ca_system_score_codex":0.00013368703,"about_ca_system_score_gemma":0.0000869982,"threshold_uncertainty_score":0.5645162},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.021646781211188282,"score_gpt":0.30370065186152373,"score_spread":0.28205387065033544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950982165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008318343,0.00011433638,0.96318084,0.00029292243,0.00057739555,0.00027138653,0.0000027984265,0.0007920093,0.026449991],"genre_scores_gemma":[0.4581722,0.00008069454,0.5405839,0.0001655376,0.000086741835,0.00010830701,0.000011530822,0.00002233117,0.0007687232],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977785,0.00013272895,0.00041569222,0.0008785992,0.00045635217,0.00033814815],"domain_scores_gemma":[0.9977864,0.00007746082,0.0003968017,0.0014784867,0.0001373578,0.00012350423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003432683,0.00032739167,0.00038902758,0.000258324,0.00010102928,0.00018638758,0.001167595,0.00027841743,0.0002130094],"category_scores_gemma":[0.000058815323,0.00034092803,0.0002169778,0.00029735616,0.000040957428,0.00031730818,0.00087804283,0.0006420348,0.00007399585],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015443215,0.0005353153,0.0008061539,0.00022862914,0.00029887204,0.0002424151,0.00089450035,0.0014023447,0.23653035,0.032517757,0.030434009,0.6960942],"study_design_scores_gemma":[0.00045674547,0.00011828438,0.00044451095,0.00035751887,0.0001506451,0.00008779627,0.000041134746,0.2889412,0.07819459,0.5884381,0.040902946,0.0018665543],"about_ca_topic_score_codex":0.0000069696366,"about_ca_topic_score_gemma":0.000017508837,"teacher_disagreement_score":0.69422764,"about_ca_system_score_codex":0.00022814325,"about_ca_system_score_gemma":0.00014549508,"threshold_uncertainty_score":0.9999043},"labels":[],"label_agreement":null},{"id":"W2951232267","doi":"10.48550/arxiv.1211.6321","title":"Citation content analysis (cca): A framework for syntactic and semantic analysis of citation content","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Joint Information Systems Committee; National Science Foundation","keywords":"Citation; Computer science; Scope (computer science); Content analysis; Semantic analysis (machine learning); Citation analysis; Content (measure theory); Context (archaeology); Information retrieval; Ranking (information retrieval); Data science; World Wide Web; Sociology; Social science; Mathematics","score_opus":0.17887892196990188,"score_gpt":0.25577303882443764,"score_spread":0.07689411685453576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951232267","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3133503,0.0001474498,0.68582654,0.000050969342,0.00007229122,0.0003773068,0.000026423371,0.00011965751,0.000029057153],"genre_scores_gemma":[0.92344,0.00020961829,0.07606571,0.00004650256,0.000019568277,0.000009521793,0.00009838283,0.000014892826,0.000095819414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760735,0.00019988106,0.0005370041,0.001110526,0.0001972786,0.00034795614],"domain_scores_gemma":[0.99569464,0.00086029933,0.0012080858,0.0012870325,0.0007792875,0.00017067566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059012015,0.0003616586,0.0011331709,0.0029629006,0.00011499773,0.000106721665,0.0008768199,0.00033746654,0.000015238065],"category_scores_gemma":[0.0003221193,0.0004015994,0.0010202414,0.005155237,0.00013268956,0.0006549899,0.00061750086,0.00032645365,0.0000022470026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012954061,0.0003751763,0.11504639,0.00032589695,0.030021917,0.00002331857,0.0024457234,0.16751315,0.00090868294,0.6805245,0.000010130034,0.0026755398],"study_design_scores_gemma":[0.00026401418,0.00006628047,0.061304163,0.00008555032,0.026729306,4.6318428e-7,0.00045765718,0.82994854,0.00044077967,0.08021792,0.0000057209327,0.00047956873],"about_ca_topic_score_codex":0.000319762,"about_ca_topic_score_gemma":0.00020094283,"teacher_disagreement_score":0.6624354,"about_ca_system_score_codex":0.00024997504,"about_ca_system_score_gemma":0.0000572308,"threshold_uncertainty_score":0.9998436},"labels":[],"label_agreement":null},{"id":"W2951739148","doi":"10.48550/arxiv.1204.2231","title":"Investigating Keyphrase Indexing with Text Denoising","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Search engine indexing; Computer science; Benchmark (surveying); Noise reduction; Artificial intelligence; Natural language processing; Noise (video); Information retrieval; Energy (signal processing); Pattern recognition (psychology); Mathematics; Image (mathematics); Statistics","score_opus":0.07049531634463828,"score_gpt":0.20290324027272943,"score_spread":0.13240792392809114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951739148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21671209,0.00008367448,0.7802585,0.000036964608,0.00008020008,0.00018301189,0.0000017812267,0.00072439224,0.0019194104],"genre_scores_gemma":[0.8897059,0.000029414725,0.10969414,0.00011883697,0.000082363746,0.0000013942797,0.000007879587,0.000033023494,0.0003270408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765325,0.00014858597,0.00025276563,0.0012037487,0.00017113493,0.00057052495],"domain_scores_gemma":[0.99717546,0.00012991665,0.0005326294,0.0016685593,0.00019109486,0.0003023361],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034791164,0.00044389252,0.0004457258,0.0004512676,0.00028108034,0.00020600735,0.0020822403,0.00028544225,0.000011428578],"category_scores_gemma":[0.000058863567,0.00046937488,0.00016810372,0.0011444108,0.0002071049,0.0012342948,0.0028008826,0.0009410742,0.000034744397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017838605,0.00020059344,0.08381144,0.00023003964,0.00043509554,0.0006236873,0.0018091237,0.28930408,0.001459577,0.6149612,0.00016096755,0.006986335],"study_design_scores_gemma":[0.00089421734,0.000112382426,0.0038867672,0.0012642335,0.0005106092,0.00005010952,0.00033851629,0.64070517,0.0075116013,0.3411063,0.0006134129,0.0030066548],"about_ca_topic_score_codex":0.0001520517,"about_ca_topic_score_gemma":0.000065683475,"teacher_disagreement_score":0.67299384,"about_ca_system_score_codex":0.0003573972,"about_ca_system_score_gemma":0.00020569238,"threshold_uncertainty_score":0.99977577},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01397295543473869,"score_gpt":0.2989504196007305,"score_spread":0.2849774641659918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953722276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001378752,0.000015986343,0.9954499,0.0002982869,0.00011153751,0.0007560275,0.0000012427201,0.00056852767,0.0014197675],"genre_scores_gemma":[0.5957311,0.0000036412669,0.40331066,0.0006041412,0.0000068372124,0.00013700854,0.000020993735,0.0000046479718,0.00018100934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988089,0.00001515004,0.0004047324,0.0002085057,0.0003219728,0.00024070776],"domain_scores_gemma":[0.9989888,0.000019182253,0.00035980993,0.00039948637,0.00018912746,0.000043568634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036608192,0.00013757341,0.0001294557,0.0003616163,0.00014031175,0.00039512324,0.00047765355,0.00004876306,0.000008091645],"category_scores_gemma":[0.000013679545,0.00013476107,0.0000826362,0.00056149065,0.000017271599,0.0046354425,0.00008658486,0.00007922481,0.000050938284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025688614,0.00011829128,0.0010959718,0.0006030032,0.000029265486,5.3735204e-7,0.0003496749,0.009555063,0.0000794947,0.009800004,0.00040272405,0.97794026],"study_design_scores_gemma":[0.0010789586,0.000033817705,0.007995318,0.00008780326,0.000019199519,7.7553636e-7,0.0000922242,0.94038916,0.0013649275,0.005125605,0.04354413,0.0002680633],"about_ca_topic_score_codex":0.0000054270163,"about_ca_topic_score_gemma":0.0000020816433,"teacher_disagreement_score":0.9776722,"about_ca_system_score_codex":0.000114492264,"about_ca_system_score_gemma":0.00003104425,"threshold_uncertainty_score":0.5495397},"labels":[],"label_agreement":null},{"id":"W2954858138","doi":"10.22260/isarc2019/0171","title":"Automatic Key-phrase Extraction to Support the Understanding of Infrastructure Disaster Resilience","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ... ISARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Resilience (materials science); Computer science; Key (lock); Phrase; Critical infrastructure; Computer security; Natural language processing","score_opus":0.013635449803248044,"score_gpt":0.27092614887838457,"score_spread":0.2572906990751365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954858138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8908441,0.00001170984,0.10117926,0.0016757295,0.00015918912,0.000557105,0.0000017630316,0.00013151458,0.0054396302],"genre_scores_gemma":[0.97177976,0.0000032040607,0.027711768,0.00016612712,0.000018049912,0.000010209104,1.418279e-7,0.000009818774,0.000300889],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986103,0.000010457184,0.00034216724,0.00029118903,0.000526944,0.00021895271],"domain_scores_gemma":[0.9988847,0.00007654786,0.0004138637,0.00042802872,0.0001507705,0.000046130684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041326473,0.00014019184,0.000217531,0.00012871572,0.000096919735,0.00007433709,0.0017506309,0.000051060713,0.0000407986],"category_scores_gemma":[0.00015115147,0.00008205391,0.00011286386,0.0008481929,0.00011564613,0.00081307476,0.00058966776,0.00017405125,0.000010590733],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045149976,0.000115731265,0.043333594,0.00046451617,0.00010000319,7.85901e-7,0.01978602,0.000587995,0.5876361,0.31121325,0.008469717,0.028247109],"study_design_scores_gemma":[0.00062200765,0.00069023354,0.04083892,0.00074338896,0.00014045695,0.00008310179,0.010214051,0.059637193,0.51156795,0.37227324,0.0023781222,0.0008113513],"about_ca_topic_score_codex":0.0000073096408,"about_ca_topic_score_gemma":0.0000024377357,"teacher_disagreement_score":0.080935694,"about_ca_system_score_codex":0.00012606029,"about_ca_system_score_gemma":0.00003516018,"threshold_uncertainty_score":0.33460614},"labels":[],"label_agreement":null},{"id":"W2955707177","doi":"10.3758/s13428-019-01268-4","title":"The Semantic Librarian: A search engine built from vector-space models of semantics","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Computer science; Semantics (computer science); Space (punctuation); Cognition; Semantic space; Information retrieval; Cognitive science; Human–computer interaction; Artificial intelligence; World Wide Web; Data science; Psychology; Programming language","score_opus":0.1924456178434242,"score_gpt":0.5118749448262684,"score_spread":0.3194293269828442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955707177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082346246,0.0007260222,0.91387194,0.0012601342,0.00012619182,0.00088301185,0.000005583328,0.00022415977,0.00055668585],"genre_scores_gemma":[0.41137132,0.00018503716,0.58729887,0.000009133648,0.000039182905,0.000090688074,0.0000031410361,0.000031631782,0.0009709609],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99345905,0.0027276853,0.00049924356,0.0007647766,0.0016579803,0.00089129194],"domain_scores_gemma":[0.99232394,0.0037674047,0.00012629303,0.0029141929,0.0006557446,0.00021240808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074089374,0.00023512814,0.00048738174,0.00046210745,0.00028188128,0.0003517965,0.0036563545,0.00016161405,0.000046628207],"category_scores_gemma":[0.0004218239,0.00017486562,0.00021364298,0.0021884567,0.0003188889,0.0009445429,0.0020560103,0.0010394123,0.000049446404],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057797704,0.00048566662,0.0045471564,0.000080122074,0.00015090076,0.00007376271,0.0021321329,0.0012433155,0.43087846,0.2161933,0.0006396927,0.34351766],"study_design_scores_gemma":[0.00041255343,0.00032987833,0.00545064,0.00009828412,0.000039034934,0.000008376853,0.00028724677,0.4345159,0.48899704,0.06659176,0.0028528043,0.00041647872],"about_ca_topic_score_codex":0.0005347918,"about_ca_topic_score_gemma":0.000021665046,"teacher_disagreement_score":0.4332726,"about_ca_system_score_codex":0.00010380582,"about_ca_system_score_gemma":0.00028255436,"threshold_uncertainty_score":0.7130813},"labels":[],"label_agreement":null},{"id":"W2960010094","doi":"10.1007/978-3-030-47124-8_44","title":"Analysis of Word Embeddings Using Fuzzy Clustering","year":2020,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Fuzzy clustering; Cluster analysis; Artificial intelligence; Fuzzy logic; Computer science; Representation (politics); Data mining; Curse of dimensionality; Pattern recognition (psychology); Similarity (geometry); Mathematics; Natural language processing","score_opus":0.06611174490473551,"score_gpt":0.34387517022084824,"score_spread":0.27776342531611276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960010094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030075074,0.0070557757,0.97217256,0.00011728826,0.00030627922,0.00026782957,0.0000068126055,0.00032425087,0.016741715],"genre_scores_gemma":[0.81394225,0.0012504904,0.18309493,0.00018894454,0.00021727121,0.000004861176,0.000009209385,0.00007160445,0.001220432],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974888,0.000030645013,0.0009246269,0.0008859012,0.00035894325,0.00031107417],"domain_scores_gemma":[0.9980407,0.00037611928,0.00073680235,0.000512227,0.00026744982,0.00006669881],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039615008,0.00046102138,0.0017844463,0.0010167668,0.00018191912,0.00006574941,0.00068561075,0.00015617766,0.0000018749084],"category_scores_gemma":[0.0001178981,0.00045821824,0.0003146378,0.00090813,0.00025668423,0.00020453421,0.0026943295,0.0003811049,6.288026e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051427025,0.000081809805,0.008730979,0.002552271,0.01744496,0.0005407113,0.025017343,0.10913982,0.00033942773,0.28581008,0.00014038688,0.55015075],"study_design_scores_gemma":[0.0002686521,0.00005083447,0.00038450764,0.0014891038,0.0013317127,0.000008963331,0.00044726708,0.9681305,0.000027253685,0.02620845,0.0006625486,0.0009901666],"about_ca_topic_score_codex":0.000022978724,"about_ca_topic_score_gemma":0.000063618034,"teacher_disagreement_score":0.8589907,"about_ca_system_score_codex":0.00012694894,"about_ca_system_score_gemma":0.00003215891,"threshold_uncertainty_score":0.999787},"labels":[],"label_agreement":null},{"id":"W2961582678","doi":"10.1016/j.prevetmed.2019.104728","title":"The inappropriate use of formulae and references and the possible domino effect of spurious results","year":2019,"lang":"en","type":"letter","venue":"Preventive Veterinary Medicine","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency","funders":"Canadian Food Inspection Agency","keywords":"Spurious relationship; Domino; Domino effect; Econometrics; Statistics; Mathematics; Computer science; Biology; Physics","score_opus":0.029180328592751305,"score_gpt":0.2981293379953577,"score_spread":0.26894900940260635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961582678","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42634133,0.025950491,0.072799996,0.46067122,0.0015658672,0.009959829,0.00013752743,0.00035098105,0.00222278],"genre_scores_gemma":[0.94339633,0.014211814,0.01662203,0.017388722,0.00091428333,0.00034595362,0.00009829291,0.00009400172,0.006928571],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968765,0.001121053,0.0007134361,0.0005346911,0.0004897423,0.00026459605],"domain_scores_gemma":[0.9923178,0.005340405,0.0010366509,0.0011276007,0.00015020711,0.00002735635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002182978,0.0003384329,0.0009817947,0.00019037018,0.00012284513,0.000045656252,0.0009960592,0.00019908643,0.0000014971894],"category_scores_gemma":[0.0007366981,0.00014883002,0.000120720615,0.0002962545,0.0012568473,0.00032421658,0.00094392145,0.0006319495,6.8388687e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01556159,0.00016379012,0.0015174983,0.008041635,0.0043308116,0.00087043585,0.0145732695,0.0000110021165,0.013854945,0.008286031,0.3416934,0.59109557],"study_design_scores_gemma":[0.034263324,0.058987495,0.011138412,0.014061084,0.0030833606,0.00127416,0.00019407857,0.01061349,0.01809615,0.079887286,0.7657792,0.0026219566],"about_ca_topic_score_codex":0.00015228572,"about_ca_topic_score_gemma":0.0000037074637,"teacher_disagreement_score":0.5884736,"about_ca_system_score_codex":0.00002083825,"about_ca_system_score_gemma":0.00002921015,"threshold_uncertainty_score":0.60691124},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.013225451306857263,"score_gpt":0.2521054262172721,"score_spread":0.23887997491041485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962704246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04957534,0.000025612426,0.948944,0.00013163945,0.000022394684,0.00018769118,4.2181588e-7,0.0004291562,0.00068374333],"genre_scores_gemma":[0.585518,0.000018167571,0.4142978,0.00007514988,0.000013475149,0.00000656873,0.000006271495,0.0000070461883,0.000057512978],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890226,0.000055739685,0.00018715393,0.00044357282,0.00023194465,0.0001793233],"domain_scores_gemma":[0.9990113,0.000047718746,0.00013530983,0.00036022806,0.0003794975,0.000065988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014300055,0.00014095983,0.00014090062,0.00013273246,0.00020744393,0.00011901958,0.0002948871,0.00005527166,0.000008967841],"category_scores_gemma":[0.00005045316,0.00010936115,0.000017981438,0.0004929872,0.000112433554,0.0010200245,0.00016590324,0.00007514378,0.0000056721524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019017012,0.0006800952,0.14620693,0.00010100527,0.000199914,0.000042931977,0.0049517783,0.0047461074,0.62475455,0.021894623,0.00026325087,0.19596867],"study_design_scores_gemma":[0.0004121035,0.000108454806,0.021850822,0.00006992781,0.000012094214,0.000006234664,0.00007718201,0.8245628,0.15193231,0.00066496,0.00008960891,0.00021349193],"about_ca_topic_score_codex":0.000080927224,"about_ca_topic_score_gemma":0.00008078085,"teacher_disagreement_score":0.8198167,"about_ca_system_score_codex":0.000030633637,"about_ca_system_score_gemma":0.000017556378,"threshold_uncertainty_score":0.4459618},"labels":[],"label_agreement":null},{"id":"W2963665652","doi":"10.3390/bdcc3030044","title":"Archetype-Based Modeling and Search of Social Media","year":2019,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Compute Canada","keywords":"Archetype; Jargon; Social media; Vocabulary; Computer science; Set (abstract data type); Relevance (law); Information retrieval; Slang; Data science; World Wide Web; Linguistics","score_opus":0.11721073622008192,"score_gpt":0.3397729561917595,"score_spread":0.22256221997167758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963665652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30963168,0.00012640354,0.68989223,0.000042506712,0.0000233626,0.000063128624,0.000016899301,0.000041976953,0.00016183848],"genre_scores_gemma":[0.9687459,0.000009727015,0.031056182,0.000072529925,0.000055137793,5.5665936e-7,0.000051555657,0.0000059718864,0.0000024405936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896187,0.0000704895,0.0001707434,0.00042762273,0.0001973403,0.00017194133],"domain_scores_gemma":[0.9990217,0.0004462374,0.0000674564,0.00026705101,0.00015453834,0.000043013515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044575034,0.00009470876,0.00019282341,0.000113485126,0.00009326612,0.000055433535,0.0004556653,0.000037785183,0.0000015041788],"category_scores_gemma":[0.00011247649,0.00009193647,0.000019289995,0.00022818522,0.000077119796,0.00021918782,0.0012384044,0.0001233023,0.0000024406847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009054255,0.000021489424,0.002196888,0.000038678183,0.000021971244,0.0000024034125,0.0008483481,0.00003873577,0.00081352156,0.0019843397,0.00000514109,0.99401945],"study_design_scores_gemma":[0.0003153181,0.000023693041,0.0017846097,0.000079310295,0.000016311735,0.0000020351722,0.00023576828,0.99499935,0.0014053311,0.00099968,0.000019013472,0.00011955298],"about_ca_topic_score_codex":0.000010101524,"about_ca_topic_score_gemma":0.0000052158425,"teacher_disagreement_score":0.99496067,"about_ca_system_score_codex":0.0000052955243,"about_ca_system_score_gemma":0.00004702382,"threshold_uncertainty_score":0.37490603},"labels":[],"label_agreement":null},{"id":"W2964059043","doi":"","title":"Understanding Electric Current Using Agent-based Models: Connecting the Micro-level with Flow Rate.","year":2016,"lang":"en","type":"article","venue":"International Conference on Computer Supported Education","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Electricity; Process (computing); Current (fluid); Bootstrapping (finance); Set (abstract data type); Transient (computer programming); Electrical engineering; Engineering","score_opus":0.2443541035928746,"score_gpt":0.35301889491390503,"score_spread":0.10866479132103044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964059043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010718232,0.000018491706,0.9835661,0.0038073,0.0009928822,0.0002394496,0.000006211959,0.00021900907,0.00043231653],"genre_scores_gemma":[0.85801375,0.000019320294,0.1412458,0.00044119204,0.00017232419,0.000028458839,0.000022450531,0.00001658773,0.000040137846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820817,0.00013617254,0.00034638168,0.00057379715,0.00044201076,0.0002934629],"domain_scores_gemma":[0.99826163,0.00022168385,0.00033765208,0.0005195347,0.00057518634,0.00008432863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033000807,0.00024377568,0.00016768638,0.0004251422,0.00022561116,0.00036840478,0.0011445457,0.000050786934,0.000055888428],"category_scores_gemma":[0.000027348153,0.00015300815,0.00007864287,0.00046334957,0.000048624155,0.0008652958,0.000112473645,0.00018804359,0.000017052302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007073846,0.00055562693,0.0007267581,0.000015798109,0.00019384404,0.000008762121,0.00071963953,0.013268809,0.016802946,0.4349738,0.001777968,0.5308853],"study_design_scores_gemma":[0.00031952743,0.00008533989,0.00022429558,0.0002566406,0.000018019919,0.000020206795,0.00004909238,0.95810276,0.0070399847,0.033244375,0.00036955607,0.00027021623],"about_ca_topic_score_codex":0.000023907196,"about_ca_topic_score_gemma":0.000017470156,"teacher_disagreement_score":0.94483393,"about_ca_system_score_codex":0.00072199287,"about_ca_system_score_gemma":0.0008124615,"threshold_uncertainty_score":0.62394917},"labels":[],"label_agreement":null},{"id":"W2964298985","doi":"","title":"Automatic Text Summarization Approaches to Speed up Topic Model Learning Process","year":2016,"lang":"en","type":"other","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Representation (politics); Information retrieval; Process (computing); Context (archaeology); Big data; Text processing; Space (punctuation); The Internet; Natural language processing; Data science; World Wide Web; Data mining","score_opus":0.02694046449698274,"score_gpt":0.25788570660585497,"score_spread":0.23094524210887224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964298985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000111333575,0.00036735972,0.94503653,0.0018885038,0.00010500594,0.0014656654,0.000015294168,0.006948891,0.044061426],"genre_scores_gemma":[0.026056012,0.0001531249,0.50549465,0.0008841103,0.00025145794,0.0008754666,0.000049457078,0.0006877142,0.465548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959504,0.00018796233,0.0007144525,0.0013283093,0.00079974206,0.0010191471],"domain_scores_gemma":[0.99668133,0.000085732994,0.000734193,0.0019625374,0.00011514849,0.00042108502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053335726,0.0008231383,0.0009088072,0.0018640351,0.00022137773,0.00040481717,0.0025447705,0.000750583,0.00017126341],"category_scores_gemma":[0.0002470371,0.0007458362,0.00027152203,0.0012341979,0.00008602745,0.00064165564,0.0007607505,0.0006503223,0.00017446632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032419357,0.00045769813,0.003158296,0.00069352513,0.0004366308,0.00006927548,0.0015219637,0.04192059,0.0020933056,0.26283786,0.12957886,0.55719954],"study_design_scores_gemma":[0.00025566903,0.000079086836,0.000101474754,0.0004243359,0.000055548837,0.000019211055,0.000021144297,0.9665728,0.0029798034,0.012488933,0.015943453,0.0010585041],"about_ca_topic_score_codex":0.00060209405,"about_ca_topic_score_gemma":0.00075510686,"teacher_disagreement_score":0.9246522,"about_ca_system_score_codex":0.00061814976,"about_ca_system_score_gemma":0.00037426304,"threshold_uncertainty_score":0.99949926},"labels":[],"label_agreement":null},{"id":"W2964457291","doi":"","title":"Event Detection using Images of Temporal Word Patterns.","year":2019,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Event (particle physics); Word (group theory); Artificial intelligence; Natural language processing; Speech recognition; Linguistics","score_opus":0.011971414708768596,"score_gpt":0.27750837842581483,"score_spread":0.2655369637170462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964457291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3913652,0.000007809474,0.6080601,0.000027386108,0.000047905913,0.000057045498,4.2658354e-7,0.00007411541,0.0003599758],"genre_scores_gemma":[0.8719829,0.00000420361,0.12788567,0.000022371834,0.00001496283,0.0000025850861,4.0606923e-7,0.00000515333,0.00008178775],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929273,0.00003006027,0.00016994611,0.00020187002,0.00018391559,0.0001214937],"domain_scores_gemma":[0.9993601,0.000018714367,0.00012763299,0.00041147918,0.000057220812,0.0000248679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010160674,0.000072025505,0.00013790852,0.00010797553,0.000022746177,0.000021168651,0.00032923953,0.00002958042,0.00004745842],"category_scores_gemma":[0.000008765111,0.00006758121,0.00006798823,0.00022963125,0.000014266187,0.00035476987,0.0001416136,0.00006623051,0.000012957853],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003497545,0.00003282393,0.02398716,0.000019857454,0.0000137426,0.0000025532213,0.000078750614,0.00012129117,0.6760176,0.0006121469,0.000019639301,0.29909095],"study_design_scores_gemma":[0.00013789453,0.00006981751,0.008117014,0.000045800807,0.000008728318,0.0000064264364,0.000016335016,0.0862763,0.89044183,0.014443756,0.00027369306,0.00016239716],"about_ca_topic_score_codex":0.000033489174,"about_ca_topic_score_gemma":0.000007183747,"teacher_disagreement_score":0.48061767,"about_ca_system_score_codex":0.000041951735,"about_ca_system_score_gemma":0.000014417026,"threshold_uncertainty_score":0.27558818},"labels":[],"label_agreement":null},{"id":"W2964657702","doi":"10.29173/cais295","title":"Doctoral Students’ Mental Models of a Web Search Engine","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Psychology; Mental model; Humanities; Context (archaeology); Art; Geography; Cognitive science","score_opus":0.04434080710215641,"score_gpt":0.29227336408815535,"score_spread":0.24793255698599895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964657702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984705,0.0010488852,0.0041290987,0.0053548324,0.0002498621,0.00093701103,0.0001716459,0.00009651265,0.0033071816],"genre_scores_gemma":[0.97843766,0.00057593663,0.01805685,0.0001532004,0.000090617425,0.00005903406,0.000003437226,0.000037985952,0.0025852537],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957259,0.00006934386,0.001142107,0.0006627753,0.0015617049,0.0008381263],"domain_scores_gemma":[0.93962747,0.0001943441,0.0011765918,0.0005320313,0.05820809,0.0002614581],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0010184802,0.000518874,0.0010467813,0.0004030533,0.00014063812,0.0030923102,0.0062957006,0.0002815383,0.00011136518],"category_scores_gemma":[0.0034871171,0.00044047632,0.00045302443,0.0012497368,0.0011832569,0.027472029,0.003335602,0.00057359727,0.000010470947],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002479131,0.0029350377,0.28689498,0.002552297,0.0014570596,0.00000738727,0.14618762,0.00039040743,0.1900044,0.26435167,0.018208027,0.08676321],"study_design_scores_gemma":[0.003065546,0.0026000605,0.06095179,0.0036888595,0.0006347983,0.00011485054,0.006697284,0.2541792,0.5267092,0.1131736,0.026081705,0.0021031213],"about_ca_topic_score_codex":0.0011451985,"about_ca_topic_score_gemma":0.000019607813,"teacher_disagreement_score":0.3367048,"about_ca_system_score_codex":0.00016494082,"about_ca_system_score_gemma":0.0004520992,"threshold_uncertainty_score":0.9998047},"labels":[],"label_agreement":null},{"id":"W2964996848","doi":"10.35050/jipm010.2019.031","title":"Structural analyzing of “Information Science Theories’ based on co-word network analysis of articles in Web of Science database (1983-2017)","year":2022,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Web of science; Information retrieval; World Wide Web; Data science; Database; Linguistics; Political science; MEDLINE; Philosophy","score_opus":0.11379743007524001,"score_gpt":0.5063494908679989,"score_spread":0.39255206079275884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964996848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92190635,0.0005041746,0.07619247,0.00004262164,0.00013420019,0.00030197197,0.000076500655,0.000031595933,0.0008101464],"genre_scores_gemma":[0.98543537,0.00017831643,0.01426115,0.00007522401,0.000011081506,0.000016217064,0.000012187724,0.000007797744,0.0000026669375],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99462813,0.0003357958,0.0015691455,0.00052975107,0.002448591,0.00048856373],"domain_scores_gemma":[0.99440336,0.0005270395,0.0026421293,0.0014092753,0.000854257,0.00016390762],"candidate_categories":["bibliometrics","open_science"],"consensus_categories":[],"category_scores_codex":[0.008321623,0.00023686381,0.0009770694,0.007672771,0.0005515971,0.0004866881,0.0087937275,0.00003091949,0.0005427757],"category_scores_gemma":[0.0008242169,0.00021835696,0.00023680639,0.030491909,0.001490289,0.010434445,0.0025458743,0.00034364642,4.143116e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016358893,0.00015589909,0.47222814,0.00004373598,0.00014427927,0.000006057318,0.00059221376,0.3474598,0.1520462,0.009773516,0.00014131368,0.017245246],"study_design_scores_gemma":[0.00031895275,0.00003716685,0.38652372,0.00015430554,0.00015648291,0.0000017751162,0.00020419831,0.46549955,0.13936648,0.007412264,0.00004063,0.00028449413],"about_ca_topic_score_codex":0.0004173349,"about_ca_topic_score_gemma":0.00007123541,"teacher_disagreement_score":0.11803976,"about_ca_system_score_codex":0.00026627534,"about_ca_system_score_gemma":0.0008856343,"threshold_uncertainty_score":0.99656916},"labels":[],"label_agreement":null},{"id":"W2965420532","doi":"10.29173/cais548","title":"Re-Conceiving Information Studies: A Quantum Approach","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Instrumentalism; The Renaissance; Humanities; Epistemology; Sociology; Philosophy; Art; Art history","score_opus":0.04289168566847006,"score_gpt":0.28216611247005735,"score_spread":0.23927442680158728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965420532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8937449,0.0051698545,0.04496477,0.019144295,0.00096366025,0.0025243268,0.00012751066,0.00046101745,0.032899696],"genre_scores_gemma":[0.9716199,0.0008393588,0.025577944,0.0004915491,0.00012159112,0.0001437493,0.0000036448976,0.000025732616,0.0011765234],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99629533,0.000068424386,0.0013533883,0.00053978985,0.0009309181,0.0008121516],"domain_scores_gemma":[0.89939684,0.00032716664,0.0023993184,0.0005702036,0.09709918,0.00020732409],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0012391842,0.00054343726,0.0010339327,0.00037442698,0.00026510656,0.0055915136,0.004246917,0.00031771188,0.00003394673],"category_scores_gemma":[0.025877368,0.00044408362,0.00038151225,0.0014532972,0.0012274556,0.07143062,0.0021951497,0.0006023848,0.000024393685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097616685,0.00058608537,0.03581838,0.0040039364,0.0010362463,0.0000016753121,0.4095337,0.00012805962,0.0070821433,0.38913482,0.04485035,0.107727],"study_design_scores_gemma":[0.0023260084,0.0020656947,0.06898473,0.006601078,0.0010325134,0.00016823557,0.101254,0.22364974,0.08601497,0.26589513,0.23856041,0.003447497],"about_ca_topic_score_codex":0.00071927684,"about_ca_topic_score_gemma":0.0000122743795,"teacher_disagreement_score":0.3082797,"about_ca_system_score_codex":0.00020967654,"about_ca_system_score_gemma":0.00036968285,"threshold_uncertainty_score":0.9998011},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.007519555874121481,"score_gpt":0.25303840469536454,"score_spread":0.24551884882124306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966026905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116725676,0.000021411845,0.8626634,0.0004836322,0.000048372778,0.0001348496,9.512994e-8,0.00079827686,0.01912429],"genre_scores_gemma":[0.83491075,0.0000038040605,0.16244678,0.00022736531,0.000015748226,0.0000061932506,8.7675545e-7,0.000006339643,0.0023821723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920183,0.000021033049,0.00010596532,0.00030260434,0.00020891371,0.00015963544],"domain_scores_gemma":[0.9992718,0.000035549852,0.000045865883,0.0005494943,0.00005822046,0.000039080984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007170908,0.000098805176,0.000115811694,0.0000938266,0.000036668065,0.00008258252,0.00041749072,0.000026228921,0.00015891434],"category_scores_gemma":[0.0000042900515,0.00006981702,0.000041869334,0.00037869098,0.000013466416,0.0010518192,0.00007524088,0.00008676764,0.00014011735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006596466,0.00036375504,0.0799307,0.000044814802,0.00019292072,0.00009508349,0.0007240584,0.0032949424,0.15411127,0.3859894,0.003211428,0.3719757],"study_design_scores_gemma":[0.0011520231,0.0009353722,0.038358953,0.000035413243,0.00003608726,0.00013046649,0.00016243261,0.7048553,0.22119203,0.015310806,0.016700668,0.0011304525],"about_ca_topic_score_codex":0.000027650121,"about_ca_topic_score_gemma":0.000028408198,"teacher_disagreement_score":0.71818507,"about_ca_system_score_codex":0.000027256723,"about_ca_system_score_gemma":0.00001555403,"threshold_uncertainty_score":0.28470555},"labels":[],"label_agreement":null},{"id":"W2969275073","doi":"","title":"An Efficient Method to Determine which Combination of Keywords Triggered Automatic Filtering of a Message","year":2019,"lang":"en","type":"article","venue":"USENIX Security Symposium","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data mining","score_opus":0.00827297475080617,"score_gpt":0.28901719527453423,"score_spread":0.28074422052372805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969275073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48995286,0.000009745279,0.5089114,0.00017724324,0.00006801672,0.00036979397,0.000004922038,0.00019064746,0.00031536838],"genre_scores_gemma":[0.7468452,0.0000017756693,0.25304884,0.00003789757,0.0000081600465,0.000018428613,0.0000042347533,0.000013635911,0.000021828677],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977706,0.000272203,0.00063560886,0.0005099057,0.00053474074,0.00027690447],"domain_scores_gemma":[0.997661,0.00021630789,0.00038712576,0.0012611592,0.00035609267,0.0001183471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087182806,0.00020908634,0.00056229136,0.00046764893,0.000040488612,0.000052308704,0.0011014489,0.00009442632,0.000023966775],"category_scores_gemma":[0.000062191146,0.00020844073,0.00012455072,0.0012772401,0.000023320563,0.00042224844,0.00033550907,0.00012285027,0.0000085763495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024348561,0.00077535113,0.0006596132,0.0003469875,0.000051251733,0.0000057303428,0.009210406,0.007979464,0.96009326,0.013294523,0.000047536876,0.007511524],"study_design_scores_gemma":[0.00031470135,0.00033849388,0.00044246396,0.000083252045,0.000021463768,0.0000060145394,0.000029241673,0.60086054,0.39648354,0.0011565567,0.000089490866,0.00017428628],"about_ca_topic_score_codex":0.00007286541,"about_ca_topic_score_gemma":0.00002661247,"teacher_disagreement_score":0.592881,"about_ca_system_score_codex":0.00007577822,"about_ca_system_score_gemma":0.000050246013,"threshold_uncertainty_score":0.8499966},"labels":[],"label_agreement":null},{"id":"W297012442","doi":"","title":"Disseminative Characteristics of Poetry Embryology and Development/LES CARACTÉRISTIQUES COMMUNICATIVES DE LA POÉSIE DURANT SON APPARITION ET DÉVELOPPEMENT","year":2008,"lang":"fr","type":"article","venue":"Canadian social science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poetry; Literature; Humanities; Style (visual arts); Art; Philosophy","score_opus":0.03189833034654696,"score_gpt":0.33676293756220727,"score_spread":0.30486460721566033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W297012442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7001307,0.00296522,0.24110918,0.010746781,0.00027019996,0.0005969857,0.00019989406,0.00013986052,0.043841187],"genre_scores_gemma":[0.91730624,0.0011048507,0.08094923,0.00027438957,0.000030666368,0.000019537225,0.000012910104,0.0000104222045,0.0002917533],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99766225,0.0004827345,0.00041674532,0.0004497551,0.00033889362,0.00064961886],"domain_scores_gemma":[0.99821055,0.000324661,0.00035262902,0.00028669156,0.00042654728,0.00039890915],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0014311252,0.0002210781,0.00037568383,0.00032293363,0.001355242,0.000119526725,0.0010380353,0.00019629698,0.000025029633],"category_scores_gemma":[0.0004262518,0.0002576942,0.000047130834,0.0008802725,0.0059056217,0.00070149644,0.00033021666,0.0003664041,0.0000032737717],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001677802,0.00025113806,0.0914481,0.00012963728,0.00008205678,0.000266656,0.14311194,8.1007454e-7,0.014244918,0.32304764,0.0016188656,0.42578146],"study_design_scores_gemma":[0.00014879047,0.000078498146,0.97191924,0.0001701162,0.000020662472,0.00011389799,0.003200599,0.00049858587,0.011396234,0.0031622432,0.008832284,0.00045885224],"about_ca_topic_score_codex":0.012951534,"about_ca_topic_score_gemma":0.008097088,"teacher_disagreement_score":0.8804711,"about_ca_system_score_codex":0.0010319947,"about_ca_system_score_gemma":0.002789994,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W2970591538","doi":"","title":"KlickLabs at the TAC 2018 Drug-drug Interaction Extraction from Drug Labels Track.","year":2018,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Drug; Track (disk drive); Drug-drug interaction; Extraction (chemistry); Computer science; Pharmacology; Chemistry; Medicine; Chromatography","score_opus":0.007887684036896365,"score_gpt":0.28527664641641864,"score_spread":0.27738896237952226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970591538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15169267,0.000759387,0.84221137,0.0013592276,0.00010741491,0.00037113146,0.00001710641,0.0002782802,0.0032034272],"genre_scores_gemma":[0.98966694,0.00018517539,0.0060060713,0.00013129997,0.00019986743,0.00019380826,0.000021898935,0.000010993211,0.003583959],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988865,0.00015867584,0.00029049398,0.00035480934,0.00016447874,0.00014502874],"domain_scores_gemma":[0.9980137,0.00060912414,0.0002849955,0.0008736657,0.00017380032,0.000044725402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062682544,0.00014638763,0.00017091916,0.000081831255,0.0004914333,0.00008413834,0.0005976775,0.000037861795,0.00008469866],"category_scores_gemma":[0.000030066894,0.00011032572,0.000057148023,0.0003950965,0.0005709428,0.00082186726,0.00022121887,0.00013348999,0.00007311667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054312746,0.00008680865,0.0001099862,0.000010082274,0.000052176965,2.359851e-7,0.0041125505,0.00000981898,0.0222971,0.86515987,0.0046747522,0.10343231],"study_design_scores_gemma":[0.000081916,0.000013546024,0.00026098304,0.0000086617465,0.00003952781,0.0000042770657,0.0008384036,0.00024008048,0.3521688,0.58216417,0.064044274,0.00013534447],"about_ca_topic_score_codex":0.0001417134,"about_ca_topic_score_gemma":0.00019941875,"teacher_disagreement_score":0.83797425,"about_ca_system_score_codex":0.00004248605,"about_ca_system_score_gemma":0.000021733571,"threshold_uncertainty_score":0.4498952},"labels":[],"label_agreement":null},{"id":"W2972128553","doi":"10.22215/etd/2019-13484","title":"Persuasive Content Generator The Design, Development and Validation of Persuasive Contect Generator Based on Social Media Profiles","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Popularity; Categorization; Social media; Comprehension; Internet privacy; Persuasion; World Wide Web; The Internet; Generator (circuit theory); Psychology; Social psychology; Power (physics); Artificial intelligence","score_opus":0.06364569148738479,"score_gpt":0.29159320748186235,"score_spread":0.22794751599447755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972128553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19031502,0.00034683116,0.80585945,0.00027322763,0.00047924998,0.0019395979,0.000019546798,0.000235012,0.00053204707],"genre_scores_gemma":[0.83210385,0.00003872813,0.1654807,0.0003481065,0.00013841211,0.0004784476,0.0004339247,0.000054731918,0.0009230927],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99749213,0.0002725451,0.00054976466,0.00069033867,0.00073729875,0.00025791363],"domain_scores_gemma":[0.99749887,0.00050847715,0.0006644541,0.0004492522,0.0008156581,0.00006330398],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048093268,0.0004234882,0.0005693944,0.000297058,0.000270561,0.00013724773,0.00072821236,0.0002624172,0.000024249495],"category_scores_gemma":[0.00023155064,0.00029112396,0.00016154586,0.00030363753,0.00007024795,0.0002133669,0.00006887946,0.00024583988,0.000010022716],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010022144,0.0008153733,0.000406539,0.0007428048,0.0016530919,0.000036065154,0.09037962,0.00073236926,0.5930313,0.06447019,0.0057527176,0.24097773],"study_design_scores_gemma":[0.00044238998,0.00012445464,0.0005051177,0.0000768507,0.000073261246,6.6353346e-7,0.0028520748,0.008730026,0.9864824,0.00012007278,0.00018159793,0.00041110825],"about_ca_topic_score_codex":0.000012571078,"about_ca_topic_score_gemma":0.00004075489,"teacher_disagreement_score":0.64178884,"about_ca_system_score_codex":0.0001830869,"about_ca_system_score_gemma":0.00064022606,"threshold_uncertainty_score":0.9999541},"labels":[],"label_agreement":null},{"id":"W2973402705","doi":"10.5539/mas.v13n10p26","title":"Scaled Pearson’s Correlation Coefficient for Evaluating Text Similarity Measures","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pearson product-moment correlation coefficient; Similarity (geometry); Correlation; Correlation coefficient; Outlier; Metric (unit); Statistics; Mathematics; Spearman's rank correlation coefficient; Computer science; Artificial intelligence","score_opus":0.03021596462251229,"score_gpt":0.31650101331620906,"score_spread":0.28628504869369675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973402705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030995565,0.000031738866,0.9634887,0.00014854889,0.00014916155,0.000979358,0.0000016598607,0.00041098226,0.0037943055],"genre_scores_gemma":[0.7692155,0.0000012337975,0.23030785,0.00019022459,0.000015820533,0.00009011389,0.0000017566512,0.000010293866,0.00016717611],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666524,0.000032514665,0.00033420336,0.0010721635,0.0013367035,0.00055918284],"domain_scores_gemma":[0.99804217,0.00018060906,0.00022158503,0.0010384344,0.00038839655,0.00012881856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002793418,0.00019847561,0.0002588143,0.00027570003,0.00051867554,0.0003243401,0.0018172584,0.00006999171,0.000008869338],"category_scores_gemma":[0.00019965133,0.00018595398,0.00008950158,0.001200512,0.00023214969,0.0007004487,0.00043887369,0.00017277316,0.00007568383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024787141,0.0001038686,0.00057055755,0.000017638404,0.000007938833,4.1081057e-7,0.0013898805,0.04720849,0.69690734,0.07265757,0.00008566014,0.18102586],"study_design_scores_gemma":[0.00030109118,0.000064813656,0.00078085513,0.000011553814,0.000008439773,0.0000015147873,0.000025013045,0.9380786,0.024374643,0.03597237,0.0001486044,0.00023251181],"about_ca_topic_score_codex":0.000005245788,"about_ca_topic_score_gemma":0.000005734938,"teacher_disagreement_score":0.8908701,"about_ca_system_score_codex":0.00025598475,"about_ca_system_score_gemma":0.00024167178,"threshold_uncertainty_score":0.7582983},"labels":[],"label_agreement":null},{"id":"W2973421725","doi":"10.1007/978-3-030-30712-7_46","title":"Visual Exploration of Topic Controversy in Online Conversations","year":2019,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Visualization; Data science; Online discussion; Work (physics); World Wide Web; Artificial intelligence; Engineering","score_opus":0.04436041703731572,"score_gpt":0.338240783602607,"score_spread":0.29388036656529126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973421725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016095213,0.00014460675,0.94921005,0.0009210159,0.0001211262,0.00045066283,0.000010771186,0.00006517036,0.048915632],"genre_scores_gemma":[0.47776228,0.0055969018,0.51311535,0.0012302649,0.000035006524,0.000038663136,0.0002404348,0.000015095013,0.0019660208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984603,0.000029429126,0.0007902213,0.00022060478,0.0003561053,0.00014336333],"domain_scores_gemma":[0.9974229,0.00022676842,0.00047210546,0.0014454224,0.0003921067,0.00004071346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057630765,0.00015416184,0.00030112383,0.0014804301,0.000095423835,0.00014054976,0.0019467912,0.00010200738,0.000004999123],"category_scores_gemma":[0.000054678858,0.00016394096,0.00004422139,0.0005808725,0.00046352774,0.011251553,0.0012574791,0.00029221177,0.000014564903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014316413,0.000027495707,0.00014938854,0.000017442866,0.000003693813,1.2726323e-7,0.0012297417,0.00055852707,0.000012380692,0.9015161,0.000023781608,0.09645993],"study_design_scores_gemma":[0.0005724682,0.00010726594,0.0021802841,0.00026885985,0.0000072951584,0.0000032495573,0.00008149534,0.93196374,0.00007633304,0.035525493,0.028879672,0.00033384404],"about_ca_topic_score_codex":0.000021139609,"about_ca_topic_score_gemma":0.000059912585,"teacher_disagreement_score":0.9314052,"about_ca_system_score_codex":0.00016868592,"about_ca_system_score_gemma":0.00029865868,"threshold_uncertainty_score":0.8157104},"labels":[],"label_agreement":null},{"id":"W2974266994","doi":"10.1167/19.10.187","title":"Statistical learning enables implicit subadditive predictions","year":2019,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Subadditivity; Outcome (game theory); Object (grammar); Association (psychology); Psychology; Statistics; Statistical hypothesis testing; Coin flipping; Alternative hypothesis; Cognitive psychology; Mathematics; Artificial intelligence; Computer science; Combinatorics; Null hypothesis","score_opus":0.0061224596720312495,"score_gpt":0.2984555302704867,"score_spread":0.2923330705984555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974266994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027717747,0.00005765034,0.97077596,0.00020200829,0.00011428057,0.0000450554,0.0000014219218,0.000054608958,0.0010312893],"genre_scores_gemma":[0.8606836,0.00005660079,0.13893057,0.000041635896,0.00006565542,6.416822e-7,0.0000010810352,0.000005649814,0.0002145048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899644,0.00007373736,0.0003129626,0.00013136188,0.00034784002,0.00013764114],"domain_scores_gemma":[0.9989552,0.00025110532,0.00030483954,0.00017121997,0.00024009703,0.000077543584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035229206,0.00007358936,0.0001861537,0.00019707908,0.000071632545,0.00007527251,0.00035922253,0.000039492672,0.00009152571],"category_scores_gemma":[0.00014795484,0.000057269343,0.00008242584,0.00024263638,0.000019933177,0.0008228435,0.000111185065,0.00030372528,0.000041186882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015685894,0.00078327046,0.028995464,0.00006278499,0.00036484416,0.0003463708,0.001961239,0.019826094,0.17126049,0.21483964,0.03426798,0.52713495],"study_design_scores_gemma":[0.0023059668,0.008964171,0.32451186,0.00079282577,0.0001705393,0.0010557862,0.00062121963,0.393289,0.019933995,0.1363655,0.111017495,0.00097161846],"about_ca_topic_score_codex":0.00000257787,"about_ca_topic_score_gemma":6.6022386e-7,"teacher_disagreement_score":0.8329659,"about_ca_system_score_codex":0.00006817422,"about_ca_system_score_gemma":0.00004698102,"threshold_uncertainty_score":0.2335376},"labels":[],"label_agreement":null},{"id":"W2974657091","doi":"10.4018/ijossp.2019070103","title":"A Topic Modeling Based Approach for Enhancing Corpus Querying","year":2019,"lang":"en","type":"article","venue":"International Journal of Open Source Software and Processes","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Query expansion; Ranking (information retrieval); Information retrieval; Query optimization; Process (computing); Selection (genetic algorithm); Web query classification; Web search query; Data mining; Query language; Sargable; Quality (philosophy); Search engine; Machine learning","score_opus":0.025355173247787816,"score_gpt":0.3171102658473063,"score_spread":0.2917550925995185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974657091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012830322,0.0005442678,0.98594844,0.0002231243,0.00010013272,0.00017051017,0.0000014010343,0.000041964795,0.00013986154],"genre_scores_gemma":[0.5416125,0.00003216976,0.4578527,0.00029724475,0.00006407387,0.000009189821,0.0000021982316,0.000007617107,0.00012231902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989741,0.000019180774,0.00035534092,0.00020834603,0.00032131953,0.000121722514],"domain_scores_gemma":[0.99820423,0.00023828872,0.00034998416,0.00013540055,0.0010200818,0.00005202716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041445196,0.000105617044,0.00022528222,0.00018035289,0.00006566045,0.000565741,0.001603201,0.00003886607,0.0000061687438],"category_scores_gemma":[0.00033418526,0.00008949882,0.00006994079,0.00015633255,0.0000130196495,0.0014824653,0.00028134143,0.000114714974,7.3525575e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043764876,0.0004328874,0.02591908,0.0008656999,0.00064798974,0.00003599752,0.0038755988,0.28455654,0.003368367,0.0065201023,0.000273087,0.67306703],"study_design_scores_gemma":[0.0027630543,0.0005168794,0.00007837057,0.0009545679,0.00007731858,0.0003209862,0.0005314326,0.9132523,0.025664773,0.03378433,0.021330884,0.0007251273],"about_ca_topic_score_codex":0.000016577746,"about_ca_topic_score_gemma":0.000005930261,"teacher_disagreement_score":0.6723419,"about_ca_system_score_codex":0.000040437382,"about_ca_system_score_gemma":0.0002167672,"threshold_uncertainty_score":0.54554534},"labels":[],"label_agreement":null},{"id":"W2982496367","doi":"","title":"Towards using task similarity to recommend Stack Overflow posts.","year":2018,"lang":"en","type":"article","venue":"Conferencia Iberoamericana de Software Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Stack (abstract data type); Similarity (geometry); Artificial intelligence; Programming language; Engineering","score_opus":0.020727173550247106,"score_gpt":0.27892915757006786,"score_spread":0.25820198401982075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982496367","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068725675,0.00005172902,0.9291345,0.00018697868,0.0002108879,0.00019226965,0.000013405112,0.0013050113,0.0001795638],"genre_scores_gemma":[0.48094362,0.0000067878786,0.51832414,0.00053921883,0.000116126845,0.000015859114,0.000003713302,0.000032151456,0.000018364888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977022,0.000052689593,0.00038267224,0.00069423317,0.00035740153,0.00081080047],"domain_scores_gemma":[0.9979066,0.00013273337,0.00012851099,0.0010482629,0.00034910397,0.00043474656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002877332,0.0003855227,0.00047269918,0.00038897936,0.00015800308,0.00018894768,0.0012483186,0.00011869507,0.000060691742],"category_scores_gemma":[0.0007951135,0.00043453326,0.00013479903,0.0013141722,0.000067801,0.00052961137,0.0006066529,0.0003247427,0.00003497982],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048535734,0.00029250246,0.0274326,0.00015874412,0.0006505639,0.00020197591,0.0066357865,0.015132857,0.080101766,0.015718034,0.005464811,0.8481618],"study_design_scores_gemma":[0.0009548539,0.0011719518,0.058632687,0.00047422314,0.00020374071,0.00014652118,0.00015414758,0.7906021,0.09406659,0.0039136764,0.04521744,0.004462108],"about_ca_topic_score_codex":0.00038097124,"about_ca_topic_score_gemma":0.000053270596,"teacher_disagreement_score":0.8436997,"about_ca_system_score_codex":0.0005901547,"about_ca_system_score_gemma":0.0003199807,"threshold_uncertainty_score":0.99981064},"labels":[],"label_agreement":null},{"id":"W2990795924","doi":"10.1177/2515245919882693","title":"Advancing Meta-Analysis With Knowledge-Management Platforms: Using metaBUS in Psychology","year":2019,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern Alberta Institute of Technology","funders":"","keywords":"Knowledge management; Data science; Computer science; Numbering; Visualization; Engineering ethics; World Wide Web; Psychology; Engineering","score_opus":0.11064732021659938,"score_gpt":0.5827248165838096,"score_spread":0.4720774963672102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990795924","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035120964,0.013883998,0.9311672,0.00023493894,0.00015311205,0.0004970648,4.0000157e-7,0.00006948161,0.018872825],"genre_scores_gemma":[0.30483577,0.003026087,0.69171673,0.00033452496,0.0000054354646,0.000058790552,2.44267e-7,0.0000056473773,0.000016785069],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951569,0.0006967052,0.0007824261,0.0020545863,0.000489395,0.0008200163],"domain_scores_gemma":[0.99622446,0.001517921,0.0008150735,0.0012327015,0.000083028695,0.00012683858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012113669,0.00033882482,0.0011897045,0.0018476793,0.000110799774,0.00016124257,0.0019991656,0.000115209616,0.00005041806],"category_scores_gemma":[0.000519033,0.00022487747,0.00017138851,0.012577294,0.0005444998,0.006438855,0.00057359034,0.00062875025,0.000004749224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021293327,0.001155099,0.07417376,0.000066029235,0.0018211905,0.00022731893,0.0010121347,0.022210343,0.002877794,0.115643874,0.0000014681885,0.78059804],"study_design_scores_gemma":[0.0034323058,0.0017173329,0.07062211,0.000110411056,0.0096599795,0.00024148152,0.0017411207,0.24704868,0.001670513,0.6402438,0.020504618,0.0030076462],"about_ca_topic_score_codex":0.000028000784,"about_ca_topic_score_gemma":0.0003579103,"teacher_disagreement_score":0.7775904,"about_ca_system_score_codex":0.00011685616,"about_ca_system_score_gemma":0.000027340506,"threshold_uncertainty_score":0.91702366},"labels":[],"label_agreement":null},{"id":"W2994813639","doi":"10.5539/cis.v13n3p57","title":"Topic Subject Creation Using Unsupervised Learning for Topic Modeling","year":2020,"lang":"en","type":"preprint","venue":"Computer and Information Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Non-negative matrix factorization; Subject (documents); Computer science; Artificial intelligence; Machine learning; Matrix decomposition; Data science; World Wide Web","score_opus":0.050476913095002,"score_gpt":0.32253521218980263,"score_spread":0.2720582990948006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994813639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022645757,0.000047985777,0.97570014,0.00031214394,0.00028645154,0.0003756815,0.0000011052605,0.00031902792,0.00031172115],"genre_scores_gemma":[0.52720165,0.000049493752,0.4721773,0.00044026403,0.0000896715,0.000018983712,0.00001471578,0.0000036659726,0.000004242698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844015,0.000028954406,0.00047358772,0.00044836925,0.00035387644,0.0002550415],"domain_scores_gemma":[0.9987275,0.00004959255,0.00024014212,0.00040569296,0.00046652323,0.00011054356],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005482225,0.00019629962,0.00026446066,0.0004552188,0.00044518377,0.0012051308,0.0010724489,0.00009598619,0.0000011788588],"category_scores_gemma":[0.00010267268,0.00019307664,0.00008648008,0.00062031473,0.00008987335,0.0067142337,0.0015441638,0.00027787228,0.0000027253632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054699703,0.000010217212,0.00029320517,0.00026969225,0.000016514385,5.5143596e-7,0.0053690416,0.60786086,0.00059981114,0.045871105,0.000028393939,0.33967513],"study_design_scores_gemma":[0.00013173373,0.00004338445,0.00017228536,0.000059093858,0.000009217393,0.0000031980942,0.000021322001,0.9887592,0.00064867694,0.009253691,0.0006817328,0.00021645022],"about_ca_topic_score_codex":0.000021347027,"about_ca_topic_score_gemma":5.6407475e-7,"teacher_disagreement_score":0.5045559,"about_ca_system_score_codex":0.000120582496,"about_ca_system_score_gemma":0.00024368915,"threshold_uncertainty_score":0.99983174},"labels":[],"label_agreement":null},{"id":"W3004295495","doi":"10.22148/001c.11829","title":"On the perceived complexity of literature. A response to Nan Z. Da","year":2020,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reductionism; Variance (accounting); Literary criticism; Epistemology; Sociology; Linguistics; Philosophy; Economics","score_opus":0.07676143944045041,"score_gpt":0.3253034171408474,"score_spread":0.24854197770039696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004295495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7229555,0.000109378045,0.19393508,0.082485124,0.00006731479,0.0001357048,0.0000066144603,0.000046712707,0.00025854126],"genre_scores_gemma":[0.9509771,0.000018658693,0.046113327,0.0027299044,0.000072460185,4.6964612e-7,4.1765995e-7,0.000004318076,0.00008335767],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984972,0.00020435988,0.0004917736,0.00014567153,0.00051919447,0.00014179798],"domain_scores_gemma":[0.99814385,0.00023968589,0.00044376586,0.00029596357,0.0007064937,0.0001702384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047971946,0.00013369214,0.0003386385,0.000109642024,0.00007782883,0.00015603603,0.001213543,0.00003896379,0.000014951277],"category_scores_gemma":[0.00096926524,0.000068103815,0.00028027841,0.0010709929,0.00009372162,0.00036658545,0.00015435586,0.0003350454,0.0000075297935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031309356,0.00046268618,0.00035778488,0.000070748356,0.0008633867,0.00046853776,0.05947386,0.011537629,0.5478448,0.29753843,0.07103467,0.0072165234],"study_design_scores_gemma":[0.0043067853,0.01934083,0.059850223,0.0028983864,0.0009137309,0.0009448749,0.006916361,0.3437669,0.19717212,0.2848944,0.07596045,0.0030348988],"about_ca_topic_score_codex":0.0000014421067,"about_ca_topic_score_gemma":0.000001824049,"teacher_disagreement_score":0.35067266,"about_ca_system_score_codex":0.000054738768,"about_ca_system_score_gemma":0.000043033368,"threshold_uncertainty_score":0.2777193},"labels":[],"label_agreement":null},{"id":"W3007728180","doi":"10.1109/icmla.2019.00228","title":"Using Convolutional Neural Networks to Extract Keywords and Keyphrases: A Case Study for Foodborne Illnesses","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Benchmark (surveying); Identification (biology); Generalization; Field (mathematics); Deep learning; Information extraction; Natural language processing; Machine learning; Information retrieval","score_opus":0.040456376868748964,"score_gpt":0.344727807278998,"score_spread":0.304271430410249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007728180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41379148,0.000056801066,0.5852235,0.000055878718,0.000092028706,0.0005992369,0.0000012065901,0.00014500908,0.000034875116],"genre_scores_gemma":[0.80533916,0.000001240547,0.19422254,0.00023504326,0.000051437375,0.00005201513,0.0000010173374,0.0000107683745,0.000086784625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986867,0.000046111578,0.00025385222,0.00053987437,0.0001746796,0.0002988008],"domain_scores_gemma":[0.9988998,0.00027818236,0.00007987973,0.00047412113,0.00014786304,0.000120143726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026471965,0.00017480308,0.00025262107,0.00015033784,0.00016515472,0.0001603921,0.00033021485,0.00004403206,0.000016328479],"category_scores_gemma":[0.00004306933,0.00015274492,0.00006393038,0.000453343,0.000026372067,0.00066191686,0.00031261216,0.000084656065,0.0000021940893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003253601,0.0032206331,0.1814774,0.00016136313,0.00081553444,0.0028663462,0.005630463,0.29325056,0.0046994425,0.09095875,0.0027619377,0.41383222],"study_design_scores_gemma":[0.00041048406,0.00043015165,0.00053244445,0.000008667685,0.000027111815,0.00053095486,0.0006108565,0.9959986,0.00019088369,0.0007297876,0.0002579095,0.0002721184],"about_ca_topic_score_codex":0.00019357947,"about_ca_topic_score_gemma":0.00021719284,"teacher_disagreement_score":0.70274806,"about_ca_system_score_codex":0.00004786224,"about_ca_system_score_gemma":0.000031745272,"threshold_uncertainty_score":0.6228757},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ontology; Computer science; Recommender system; Information retrieval; Artificial intelligence","score_opus":0.027770495797533334,"score_gpt":0.38999263871658607,"score_spread":0.36222214291905275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014604514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111304775,0.00019954314,0.88432264,0.0022714005,0.00004296899,0.0016592783,0.000011850886,0.00015604538,0.000031525797],"genre_scores_gemma":[0.54965377,0.000001522073,0.44941333,0.0006284248,0.000023452323,0.00023920425,0.000032856355,0.0000059232375,0.0000015232162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833727,0.00005584238,0.0007552668,0.00015242453,0.0004847681,0.00021443346],"domain_scores_gemma":[0.9990623,0.00005339364,0.0003374276,0.00012630159,0.00014238294,0.00027821193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051649567,0.00013863697,0.0003200047,0.00015938703,0.00007683365,0.000055783265,0.0003211941,0.000044536566,0.0000030448314],"category_scores_gemma":[0.000118726624,0.00011621124,0.000029462786,0.00031715469,0.000036222584,0.00035356873,0.00017775422,0.00011418446,3.2462222e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009953639,0.0007277688,0.0028771872,0.025309853,0.00005080316,0.000002733396,0.06640373,0.00003918828,0.00030603647,0.004781003,0.0010195813,0.8983826],"study_design_scores_gemma":[0.0013356352,0.00025339078,0.0041197813,0.0036024307,0.000011941021,0.0000017894371,0.00082112115,0.98349875,0.0033166134,0.000053006446,0.0026023905,0.0003831579],"about_ca_topic_score_codex":0.000007184322,"about_ca_topic_score_gemma":0.0000102096155,"teacher_disagreement_score":0.98345953,"about_ca_system_score_codex":0.0007251229,"about_ca_system_score_gemma":0.0027010078,"threshold_uncertainty_score":0.4791472},"labels":[],"label_agreement":null},{"id":"W3015234797","doi":"10.36227/techrxiv.12100692.v1","title":"Deep Learning for text in limted data settings","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Sequence (biology); Transfer of learning; Sequence learning; Natural language processing; Machine learning; Recurrent neural network; Sentiment analysis; Artificial neural network","score_opus":0.05509319530841789,"score_gpt":0.34010155808589826,"score_spread":0.2850083627774804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015234797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007525236,0.00016086618,0.9929267,0.0037598172,0.000069568356,0.00047222903,0.0000034437655,0.0011515529,0.0013805632],"genre_scores_gemma":[0.09836517,0.000065546585,0.9000415,0.0007087291,0.00007954457,0.000096478194,0.00029174838,0.000027515103,0.00032377505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974372,0.00007581031,0.00045247152,0.0014720412,0.00024385187,0.0003186433],"domain_scores_gemma":[0.9971873,0.00025711703,0.00028292811,0.002098339,0.00009452134,0.00007975684],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00053250504,0.000265936,0.00046322984,0.00024085166,0.00006213163,0.0002499164,0.0050995783,0.00020553239,0.000014844676],"category_scores_gemma":[0.00068724935,0.00026619592,0.00010618882,0.00048008308,0.000025386506,0.00048534817,0.011406377,0.00087044237,0.000023487595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023200822,0.00015034399,0.0014878984,0.0005500279,0.00020954163,0.000063750456,0.0020389503,0.019733181,0.001540986,0.046187364,0.013754751,0.91426],"study_design_scores_gemma":[0.00010934352,0.000025881658,0.00012385081,0.000062608124,0.000014336763,0.0000010875514,0.000025748364,0.94292706,0.00069550704,0.037288155,0.01841177,0.00031463103],"about_ca_topic_score_codex":0.000058311285,"about_ca_topic_score_gemma":0.000099858415,"teacher_disagreement_score":0.9231939,"about_ca_system_score_codex":0.00007906302,"about_ca_system_score_gemma":0.00008520015,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W3023453969","doi":"10.1007/978-3-030-47358-7_19","title":"Using Topic Modelling to Improve Prediction of Financial Report Commentary Classes","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Class (philosophy); Task (project management); Feature selection; Selection (genetic algorithm); Artificial intelligence; Machine learning; Data mining; Feature (linguistics); Finance; Topic model","score_opus":0.03398848257873614,"score_gpt":0.28170749902452086,"score_spread":0.2477190164457847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023453969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019602475,0.000091591326,0.99710035,0.0009091377,0.00079965394,0.00040328703,0.000010086891,0.00018304729,0.00030679058],"genre_scores_gemma":[0.08219323,0.000013546759,0.91517025,0.002134426,0.00042645575,0.000006399275,0.0000063868656,0.000021648371,0.000027627922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659294,0.00002224535,0.0007954317,0.0013779105,0.0008374315,0.00037404473],"domain_scores_gemma":[0.99772596,0.00014881184,0.0004773253,0.0012143106,0.00028329808,0.00015027556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004606154,0.0003853913,0.0006082618,0.00066482654,0.00014797495,0.00013667955,0.0019749077,0.00022091586,0.0000030066954],"category_scores_gemma":[0.00009398036,0.0003886591,0.00015734119,0.0007518513,0.00024919544,0.0006225666,0.00143877,0.00056068535,0.0000019895085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011381286,0.000044872217,0.00019644835,0.00008882315,0.000023858174,0.0003076144,0.00067882775,0.61947197,0.005235881,0.011864377,0.000077480116,0.36199844],"study_design_scores_gemma":[0.00008140344,0.00017498675,0.000019604533,0.00024436568,0.000016341948,0.000040282015,8.287468e-8,0.8794293,0.01323822,0.10558382,0.00085966726,0.000311942],"about_ca_topic_score_codex":0.000055565608,"about_ca_topic_score_gemma":0.000021698263,"teacher_disagreement_score":0.3616865,"about_ca_system_score_codex":0.0003700841,"about_ca_system_score_gemma":0.0003903056,"threshold_uncertainty_score":0.99985653},"labels":[],"label_agreement":null},{"id":"W3023942231","doi":"10.1075/ml.20004.nis","title":"Clozapp","year":2019,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep André Laurendeau","funders":"","keywords":"Computer science; Data collection; Replication (statistics); Predictability; Information retrieval; Java; Natural language processing; Artificial intelligence; Programming language; Statistics","score_opus":0.007162570725038875,"score_gpt":0.2528083073504823,"score_spread":0.24564573662544345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023942231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47528067,0.0003772388,0.39556143,0.007146201,0.00072123786,0.00083679846,0.000002229008,0.0013159114,0.118758276],"genre_scores_gemma":[0.9832044,0.000008940446,0.012475095,0.00069817004,0.000023476678,0.000008019303,0.0000012949466,0.0000051063244,0.00357546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994119,0.000029136372,0.00008965096,0.00017282182,0.00016093143,0.00013555854],"domain_scores_gemma":[0.99930984,0.000025649017,0.00004402829,0.00058806717,0.0000098189685,0.000022596156],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014838415,0.00006940637,0.00007886787,0.000029683897,0.000058431913,0.0000483099,0.0008118957,0.000017969876,0.000106498235],"category_scores_gemma":[0.000002652794,0.000044642722,0.000052263385,0.00016584911,0.000027996102,0.00027082593,0.00026750486,0.00007395395,0.000858887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000953078,0.0000745527,0.0018181351,0.000006361509,0.000039646107,0.000003842363,0.0012069928,0.000036202397,0.10639806,0.7447629,0.0029615236,0.14268228],"study_design_scores_gemma":[0.0007417136,0.00032532847,0.0041265567,0.000039688883,0.00001810833,0.000045772053,0.00018894703,0.038915515,0.5969066,0.17215167,0.18590859,0.0006315331],"about_ca_topic_score_codex":0.000010441877,"about_ca_topic_score_gemma":0.0000022720947,"teacher_disagreement_score":0.5726112,"about_ca_system_score_codex":0.000039088867,"about_ca_system_score_gemma":0.000009230043,"threshold_uncertainty_score":0.99991906},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06664237805374586,"score_gpt":0.31143453917885444,"score_spread":0.2447921611251086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027864066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012818293,0.00035721823,0.9932447,0.0030503715,0.00022077406,0.00014411473,0.000643295,0.00058132946,0.00047638902],"genre_scores_gemma":[0.8561631,0.0001285432,0.14195356,0.0007959017,0.00015258684,0.000029941071,0.00038892665,0.000030129637,0.0003573156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981965,0.00009602082,0.00023930662,0.0009877858,0.00023205952,0.0002483482],"domain_scores_gemma":[0.995061,0.0003462591,0.000075508455,0.0043085604,0.00004851175,0.00016017193],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00012105525,0.0002262196,0.00025762097,0.000106142965,0.00021761477,0.00021561839,0.0058762324,0.000075891505,0.00005461461],"category_scores_gemma":[0.00011339957,0.00021976218,0.00011378573,0.0006317184,0.00007222089,0.003915032,0.0003020019,0.00039071694,0.00048925646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011850766,0.0015119255,0.0006964733,0.00005939703,0.00068428303,0.000071722796,0.0032724647,0.0019353784,0.005527878,0.010437296,0.049011376,0.9266733],"study_design_scores_gemma":[0.0026126516,0.0008706229,0.0046979073,0.0002544108,0.0006033848,0.000011236802,0.0005607742,0.2985135,0.04590346,0.063127816,0.5796736,0.0031706733],"about_ca_topic_score_codex":0.00003863608,"about_ca_topic_score_gemma":0.00028112388,"teacher_disagreement_score":0.9235026,"about_ca_system_score_codex":0.000058666643,"about_ca_system_score_gemma":0.0001077944,"threshold_uncertainty_score":0.9995025},"labels":[],"label_agreement":null},{"id":"W3031557112","doi":"10.18653/v1/2020.coling-main.6","title":"Catching Attention with Automatic Pull Quote Selection","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Task (project management); Readability; Computer science; Selection (genetic algorithm); Identification (biology); Presentation (obstetrics); Salient; Code (set theory); Natural language processing; Artificial intelligence; Perception; Cognitive psychology; Psychology","score_opus":0.01647314170779892,"score_gpt":0.2747997570315964,"score_spread":0.2583266153237975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031557112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005390755,0.000032324802,0.9882946,0.0013294229,0.0001020655,0.00031990712,5.649859e-7,0.0030119366,0.0015184358],"genre_scores_gemma":[0.45292932,0.000011052724,0.54647344,0.0001251096,0.000051067735,0.00005760292,0.000013366016,0.000016606415,0.00032241776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822056,0.000076696204,0.0002993558,0.000787373,0.0003996584,0.00021633785],"domain_scores_gemma":[0.9988173,0.000029096831,0.00030353758,0.0006323852,0.0001356042,0.00008203638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016475492,0.00026531785,0.00032821178,0.00019834861,0.00010030072,0.00041262285,0.00090364635,0.00014042883,0.000011677048],"category_scores_gemma":[0.000020840735,0.00022125263,0.000109756475,0.0005024397,0.000020146872,0.00046363738,0.000909248,0.0005716115,0.000040283758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029316332,0.00051886437,0.008362736,0.0014622273,0.0015960305,0.00016609867,0.002568607,0.099899374,0.019084727,0.3398324,0.009321565,0.51715803],"study_design_scores_gemma":[0.000065184424,0.000059699712,0.0013783053,0.00009701581,0.000049397702,0.00001470086,0.000009519084,0.9679745,0.0010886284,0.028650388,0.00026958605,0.00034308308],"about_ca_topic_score_codex":0.00027578385,"about_ca_topic_score_gemma":0.000077941244,"teacher_disagreement_score":0.86807513,"about_ca_system_score_codex":0.00017133073,"about_ca_system_score_gemma":0.00011644637,"threshold_uncertainty_score":0.90224206},"labels":[],"label_agreement":null},{"id":"W3034847701","doi":"10.5430/ijhe.v9n4p169","title":"Analysis of Text Mining from Full-text Articles and Abstracts by Postgraduates Students in Selected Nigeria Universities","year":2020,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Originality; Computer science; Data collection; Library science; World Wide Web; Psychology; Mathematics education; Medical education; Information retrieval; Medicine; Sociology; Qualitative research; Social science","score_opus":0.010294624633854506,"score_gpt":0.307760733735449,"score_spread":0.2974661091015945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034847701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889928,0.00044517274,0.007479497,0.002865016,0.00013115941,0.000026478288,0.0000059157546,0.000012944171,0.000041012627],"genre_scores_gemma":[0.9882044,0.00005101322,0.01139414,0.00022482961,0.000053907188,7.0746796e-7,0.0000131343295,0.000003899686,0.000053922355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988793,0.00004988121,0.0004236161,0.0001448635,0.0004296832,0.00007264929],"domain_scores_gemma":[0.99869573,0.00012590669,0.0005123094,0.000079467194,0.0005220395,0.00006454735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009739222,0.000080224825,0.00020424291,0.00048436745,0.000016373326,0.00009567765,0.000621496,0.000030847907,0.000044118984],"category_scores_gemma":[0.00003463339,0.00007861889,0.0000599585,0.00075540296,0.00002946806,0.0006842612,0.000083504725,0.00008719406,0.0000011367945],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001759616,0.0007515463,0.8215522,0.0000073520046,0.0028017573,0.00002696576,0.01432764,0.0011636585,0.12953402,0.0009466056,0.0032995073,0.025412766],"study_design_scores_gemma":[0.0003218893,0.0000904417,0.98355967,0.000049941817,0.0001468247,0.000002799732,0.0011045502,0.0017857107,0.011451657,0.0009559373,0.0004145927,0.00011596213],"about_ca_topic_score_codex":0.00015219962,"about_ca_topic_score_gemma":0.000037007838,"teacher_disagreement_score":0.16200748,"about_ca_system_score_codex":0.0001081098,"about_ca_system_score_gemma":0.00011277118,"threshold_uncertainty_score":0.32059854},"labels":[],"label_agreement":null},{"id":"W3035454674","doi":"","title":"Meta Variance Transfer: Learning to Augment from the Others","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Augment; Computer science; Variance (accounting); Artificial intelligence","score_opus":0.044351630801325675,"score_gpt":0.26800000279086234,"score_spread":0.22364837198953666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035454674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006657377,0.000120423996,0.9619488,0.034872063,0.000017295999,0.00012576817,8.078408e-7,0.00051645865,0.0017326174],"genre_scores_gemma":[0.5747596,0.000020250303,0.40275908,0.02183861,0.000057729445,0.00004018736,8.811548e-7,0.000011497817,0.0005121744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990267,0.000080288875,0.00014750709,0.0003686588,0.00022062862,0.00015619193],"domain_scores_gemma":[0.99934477,0.00012837457,0.000018328941,0.00038696657,0.000024944322,0.00009664326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014600881,0.00010909536,0.00017888506,0.000015971751,0.00009373523,0.00010273603,0.0011141961,0.000021084157,0.00021326785],"category_scores_gemma":[0.00002933896,0.00006678787,0.00012403018,0.0004485902,0.000014868323,0.00022635776,0.00014763235,0.00013523322,0.000118077194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046348672,0.00013213439,0.00094337174,0.0000109383,0.004435392,0.000046213077,0.046634268,0.060399663,0.07698446,0.44887206,0.02095753,0.34053764],"study_design_scores_gemma":[0.00043925727,0.00038638437,0.0006810293,0.00001537819,0.0007074605,0.000001508346,0.0005231485,0.21402863,0.13468443,0.018875463,0.6287841,0.00087318436],"about_ca_topic_score_codex":0.00014217073,"about_ca_topic_score_gemma":0.000026893318,"teacher_disagreement_score":0.6078266,"about_ca_system_score_codex":0.000017120065,"about_ca_system_score_gemma":0.000014099637,"threshold_uncertainty_score":0.27235302},"labels":[],"label_agreement":null},{"id":"W3038540624","doi":"10.1007/978-3-030-43961-3_3","title":"Animated Guide to Represent a Novel Means of Gut-Brain Axis Communication","year":2020,"lang":"en","type":"article","venue":"Advances in experimental medicine and biology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"Neuroscience; Computer science; Cognitive science; Biology; Psychology","score_opus":0.04733392472226366,"score_gpt":0.4147131304726079,"score_spread":0.3673792057503442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038540624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041058306,0.020835146,0.9016495,0.031223204,0.00007512916,0.00046118768,0.0000039859656,0.00018263231,0.004510931],"genre_scores_gemma":[0.8439123,0.0006585909,0.15255915,0.0027959454,0.000022905535,0.00003133059,0.0000075199623,0.000004280084,0.000008006539],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990019,0.00006638483,0.00036845673,0.0003442678,0.000077145945,0.00014184361],"domain_scores_gemma":[0.9992386,0.00016367316,0.00011165722,0.00037091377,0.00003922023,0.00007593302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001709845,0.000109027314,0.00029483478,0.000104607825,0.000029231223,0.0000032776293,0.0005163753,0.000040189356,0.000012462359],"category_scores_gemma":[0.0002388488,0.000085270796,0.000020874475,0.0004623781,0.0002144108,0.00023799484,0.00041492138,0.00007436691,0.0000011529428],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003102033,0.00006820765,0.0010417111,0.000008288906,0.0000091272905,0.0000017987238,0.0031645896,0.000027025879,0.9481363,0.029322162,0.0005298427,0.017659893],"study_design_scores_gemma":[0.0023315237,0.004220132,0.00075858214,0.00022366838,0.000010142534,0.00002139204,0.0049176337,0.015270012,0.7417355,0.0075511434,0.22247101,0.00048922875],"about_ca_topic_score_codex":0.00009440919,"about_ca_topic_score_gemma":0.000027321787,"teacher_disagreement_score":0.80285394,"about_ca_system_score_codex":0.000026284233,"about_ca_system_score_gemma":0.0000079261945,"threshold_uncertainty_score":0.3477242},"labels":[],"label_agreement":null},{"id":"W3042358492","doi":"10.17705/1jais.00627","title":"Basic Classes in Conceptual Modeling: Theory and Practical Guidelines","year":2020,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Computer science; Variety (cybernetics); Domain (mathematical analysis); Conceptual model; Conceptual framework; Interface (matter); Diversity (politics); Management science; Data science; Information system; Knowledge management; Artificial intelligence; Epistemology; Mathematics; Engineering; Database; Sociology","score_opus":0.06347917459344107,"score_gpt":0.34107894678391293,"score_spread":0.2775997721904718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042358492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048802854,0.00008170593,0.98649645,0.0077642766,0.00022360244,0.00020084814,0.0000028046045,0.000027655895,0.0003223595],"genre_scores_gemma":[0.9857893,0.000026732261,0.012832157,0.001184062,0.00011843629,0.000007096463,8.297522e-7,0.00000296392,0.000038448907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983382,0.00018084128,0.0009082572,0.000051805866,0.00042505944,0.00009579478],"domain_scores_gemma":[0.99696845,0.00043707187,0.0014749125,0.00009876987,0.0009761378,0.000044641518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026715754,0.000065928165,0.00019894513,0.000099606725,0.00006173473,0.00019577166,0.00026161937,0.00006544533,2.814913e-7],"category_scores_gemma":[0.005187197,0.000044715343,0.000088327295,0.00028141175,0.000010481457,0.0030993407,0.00007156145,0.00014635429,0.0000021322073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008976943,0.000025576392,0.004928948,0.00006151488,0.00014097468,8.5718847e-7,0.009164611,0.072695374,0.00019109414,0.89468014,0.01492984,0.003091305],"study_design_scores_gemma":[0.0008018073,0.00009093171,0.00023003876,0.00006704227,0.00003166711,0.00002682394,0.0025580174,0.9388759,0.00023327177,0.007138212,0.04982582,0.000120462995],"about_ca_topic_score_codex":0.0000020916552,"about_ca_topic_score_gemma":7.929523e-7,"teacher_disagreement_score":0.980909,"about_ca_system_score_codex":0.0001717851,"about_ca_system_score_gemma":0.00010228074,"threshold_uncertainty_score":0.62099344},"labels":[],"label_agreement":null},{"id":"W3043122048","doi":"10.56042/alis.v67i1.28307","title":"Citations in chemical engineering research: factors and their assessment","year":2020,"lang":"en","type":"article","venue":"Annals of Library and Information Studies","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citation; China; Impact factor; Library science; Web of science; Geography; Political science; Computer science; MEDLINE; Archaeology; Law","score_opus":0.20239466047734267,"score_gpt":0.3965406839996783,"score_spread":0.19414602352233562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043122048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88293195,0.0017595044,0.08261183,0.030021302,0.000018486537,0.00021542229,0.000009872021,0.00022648445,0.0022051593],"genre_scores_gemma":[0.98068994,0.0015932677,0.017196445,0.0005016703,0.000005310709,0.0000071818404,0.0000035971002,0.000001283625,0.0000013254967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999558,0.000017355624,0.00020600749,0.000060465944,0.000080575985,0.00007763616],"domain_scores_gemma":[0.9996162,0.0002023656,0.00004741693,0.000060522652,0.000040027706,0.000033483753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000108159074,0.00005210213,0.00011939774,0.00015580755,0.00003503142,0.000045192475,0.0001052135,0.000015611755,7.750349e-7],"category_scores_gemma":[0.000095838164,0.0000386571,0.000014642614,0.00042114782,0.0000435545,0.008564072,0.00026946905,0.00007873608,2.3552568e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013017172,0.00003920922,0.02668008,0.00038433226,0.000177162,0.0000011070881,0.06784038,0.00024869555,0.0024589142,0.8380126,0.003982541,0.060161956],"study_design_scores_gemma":[0.0007505651,0.00067644764,0.1875031,0.00037466953,0.000008586572,0.000002660735,0.021665547,0.24643496,0.4255791,0.062785864,0.053409588,0.00080890296],"about_ca_topic_score_codex":3.1436193e-7,"about_ca_topic_score_gemma":1.6836998e-8,"teacher_disagreement_score":0.7752267,"about_ca_system_score_codex":0.0000011961658,"about_ca_system_score_gemma":0.000009014105,"threshold_uncertainty_score":0.6208745},"labels":[],"label_agreement":null},{"id":"W3080743972","doi":"10.11606/d.55.2020.tde-20082020-093906","title":"Interactive keyterm-based document clustering and visualization via neural language models","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Dalhousie University; Indiana Corn Marketing Council","keywords":"Cluster analysis; Visualization; Computer science; Natural language processing; Artificial neural network; Artificial intelligence","score_opus":0.009807791098549257,"score_gpt":0.3188874140990868,"score_spread":0.30907962300053754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080743972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003047761,0.000106274514,0.99351037,0.00009958326,0.00011918041,0.0002609439,9.665162e-7,0.0005656173,0.0022893054],"genre_scores_gemma":[0.9130115,0.000019030647,0.08525413,0.0004902459,0.000037118272,0.000057158304,0.00032824322,0.00003298699,0.0007695705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862593,0.000058310263,0.00029794782,0.0005789991,0.00027100582,0.00016782062],"domain_scores_gemma":[0.99921095,0.000038980717,0.0002454625,0.00033116492,0.00009288886,0.000080574515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000061020208,0.00026978026,0.000296914,0.00023101739,0.0000679014,0.00024785075,0.00044506515,0.00010973744,0.000018487224],"category_scores_gemma":[0.00001605798,0.0002580259,0.00008536639,0.00027744926,0.000011004471,0.0010447165,0.00014004532,0.00018331977,0.0000050644603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039008632,0.00026944722,0.000067019224,0.0011843237,0.00037248255,0.00029267138,0.051782258,0.028269736,0.055331178,0.05008271,0.0006422905,0.8113158],"study_design_scores_gemma":[0.00013043452,0.00006310082,0.000028250512,0.00006136158,0.000026209933,0.0000017765134,0.00020918735,0.9743262,0.022025406,0.002814088,0.00004140047,0.00027257425],"about_ca_topic_score_codex":0.000073407784,"about_ca_topic_score_gemma":0.00021498186,"teacher_disagreement_score":0.9460565,"about_ca_system_score_codex":0.00008212366,"about_ca_system_score_gemma":0.000029172606,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W3082570699","doi":"10.48550/arxiv.2106.14731","title":"The DELICES project: Indexing scientific literature through semantic expansion","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Search engine indexing; Computer science; Relevance (law); Information retrieval; Scientific literature; Digital library; Data science; World Wide Web; Linguistics; Political science","score_opus":0.06650420550289016,"score_gpt":0.2294048143742566,"score_spread":0.16290060887136645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082570699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1492249,0.0013519429,0.8467357,0.00015070182,0.0006455109,0.0003821938,0.000003641282,0.0005710439,0.0009343613],"genre_scores_gemma":[0.98007303,0.0009940203,0.016477635,0.000077215285,0.00006635446,0.0000036933043,0.00003444593,0.000021496182,0.0022520907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691236,0.00026518118,0.00028644153,0.0017980634,0.0002498399,0.00048808893],"domain_scores_gemma":[0.99601424,0.0001785679,0.0004042107,0.002730947,0.000598446,0.000073594456],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051252067,0.00039344287,0.00036653096,0.00032117093,0.0010693066,0.0023195487,0.003428602,0.00033239558,0.0000036484864],"category_scores_gemma":[0.000087268374,0.00033591356,0.00035191997,0.0029096832,0.00028915697,0.0015781227,0.0044366056,0.0009870736,0.000012129416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006484358,0.00054316386,0.0027603034,0.00071150804,0.0008861591,0.0038048418,0.022039423,0.10478858,0.0041277665,0.83924,0.0035701392,0.017463265],"study_design_scores_gemma":[0.00037002962,0.000060061226,0.0002640423,0.0015340388,0.0002184051,0.0000332754,0.001147437,0.6736758,0.007779569,0.305284,0.008139682,0.0014936565],"about_ca_topic_score_codex":0.00010424336,"about_ca_topic_score_gemma":0.00019287394,"teacher_disagreement_score":0.83084816,"about_ca_system_score_codex":0.00020526705,"about_ca_system_score_gemma":0.00040487916,"threshold_uncertainty_score":0.9999093},"labels":[],"label_agreement":null},{"id":"W3087953246","doi":"","title":"Strategic Categorization, Category Bundle, and Typecasting: Three Essays on Product Categorization","year":2020,"lang":"en","type":"dissertation","venue":"York University Digital Library (York University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Southern California","keywords":"Categorization; Product (mathematics); Product category; Bundle; Computer science; Artificial intelligence; Mathematics; Materials science","score_opus":0.01715802069653554,"score_gpt":0.18401840740315073,"score_spread":0.16686038670661518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087953246","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018101934,0.00045666564,0.14989866,0.0009609655,0.00076765916,0.0016139299,0.0003305396,0.005226943,0.8226427],"genre_scores_gemma":[0.92423236,0.000273106,0.0048971567,0.00009055765,0.00018703393,6.4385557e-7,0.006069952,0.00011402975,0.064135164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971914,0.00009780511,0.0002879827,0.0014901703,0.00047350168,0.00045909852],"domain_scores_gemma":[0.9980577,0.000104849394,0.0005430123,0.00077955564,0.00015753314,0.00035733284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00003691442,0.00064746704,0.0005724617,0.0012219816,0.0005714131,0.00081216195,0.0019680818,0.00037421245,0.000034429664],"category_scores_gemma":[0.000027412672,0.0008052236,0.00020052679,0.003627459,0.0001439356,0.0052600848,0.00049783575,0.000620981,0.0000855792],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026224167,0.0002496953,0.0016491818,0.00017748013,0.00021510091,0.0003993538,0.0006070259,0.0002734412,0.00006544132,0.988091,0.003136202,0.004873852],"study_design_scores_gemma":[0.005781876,0.004043064,0.0050301244,0.001284444,0.0018615632,0.0000955596,0.02523776,0.022249224,0.0072733825,0.30911666,0.6052769,0.012749467],"about_ca_topic_score_codex":0.000044574736,"about_ca_topic_score_gemma":0.00007091141,"teacher_disagreement_score":0.90613043,"about_ca_system_score_codex":0.00020993483,"about_ca_system_score_gemma":0.00063953805,"threshold_uncertainty_score":0.99943984},"labels":[],"label_agreement":null},{"id":"W3089646862","doi":"10.1016/j.cjca.2020.07.236","title":"ECG PRACTICE WITH SELF-GENERATION OF DIAGNOSES IMPROVES POST-TEST PERFORMANCE AND FLUENCY OVER MULTIPLE CHOICE","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Medical diagnosis; Fluency; Interpretation (philosophy); Test (biology); Medical education; Gold standard (test); Cognitive psychology; Mathematics education; Internal medicine; Pathology; Psychology; Computer science","score_opus":0.011849256712963595,"score_gpt":0.23291653183031524,"score_spread":0.22106727511735164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089646862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7648817,0.0011347408,0.22885352,0.004197097,0.00013705791,0.00017703066,0.000011087983,0.000037132013,0.000570651],"genre_scores_gemma":[0.9588599,0.00017280361,0.03993805,0.0007612258,0.00025418174,0.0000024737046,0.0000012790952,0.0000074449504,0.0000026427615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991607,0.000085014995,0.00027976918,0.00017237022,0.00011763824,0.00018449362],"domain_scores_gemma":[0.9981791,0.00046226638,0.00034791345,0.00017962215,0.000537189,0.00029392116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018158606,0.000107883294,0.00031068263,0.00014811743,0.00007522788,0.000038047496,0.0003389454,0.00006017815,0.000001118314],"category_scores_gemma":[0.0015694993,0.0000893866,0.000050427872,0.00024241788,0.00008708913,0.0009987584,0.000029273788,0.00018359328,6.644879e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071200186,0.00002476073,0.82217824,0.00010003616,0.00077410083,0.00037752488,0.0035414875,0.009419795,0.08846897,0.001106057,0.005398927,0.06853892],"study_design_scores_gemma":[0.0033266624,0.011071967,0.6513197,0.0001547191,0.00071609125,0.002780348,0.00045001213,0.08177802,0.045745123,0.00022886568,0.20116127,0.0012672261],"about_ca_topic_score_codex":0.00039438021,"about_ca_topic_score_gemma":0.0009613308,"teacher_disagreement_score":0.19576235,"about_ca_system_score_codex":0.000053569423,"about_ca_system_score_gemma":0.00052485097,"threshold_uncertainty_score":0.364508},"labels":[],"label_agreement":null},{"id":"W3098677341","doi":"","title":"Categorisation techniques in computer assisted reading and analysis of texts (CARAT) in the humanities","year":2001,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reading (process); Set (abstract data type); Computer science; Process (computing); Artificial intelligence; Natural language processing; Linguistics; Programming language; Philosophy","score_opus":0.027610245696320417,"score_gpt":0.29281819273416215,"score_spread":0.26520794703784173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098677341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10571352,0.000042309697,0.8907685,0.00017004019,0.0000059312074,0.0001379718,3.290522e-7,0.00012978623,0.003031592],"genre_scores_gemma":[0.90198684,0.000049875427,0.09767625,0.00020757143,0.000008425898,0.000020012221,0.000004830786,0.00000313871,0.000043091008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99894303,0.00012827628,0.00034770835,0.0002525439,0.00018849832,0.00013996109],"domain_scores_gemma":[0.99925727,0.00015949005,0.00011888622,0.00039707372,0.000057498914,0.000009761466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000577913,0.00010283608,0.00027212055,0.0011279951,0.000048248694,0.00011001777,0.00044390283,0.000049512484,0.0000043860964],"category_scores_gemma":[0.000013657087,0.00007501137,0.00005778051,0.002469467,0.00007160053,0.00048788943,0.00010889836,0.00009914573,3.6494146e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011526844,0.00030346995,0.2842233,0.000021686023,0.00024203361,0.00006231507,0.0125644235,0.0006366094,0.0033595634,0.17380436,0.00020834434,0.52456236],"study_design_scores_gemma":[0.00020581576,0.00013465164,0.60806715,0.000045386572,0.00014803177,0.000017021659,0.00039008274,0.35902688,0.009586388,0.02122643,0.00077726337,0.00037490294],"about_ca_topic_score_codex":0.00066190585,"about_ca_topic_score_gemma":0.002373205,"teacher_disagreement_score":0.7962733,"about_ca_system_score_codex":0.000052854757,"about_ca_system_score_gemma":0.00001171539,"threshold_uncertainty_score":0.3058875},"labels":[],"label_agreement":null},{"id":"W3102769546","doi":"10.22215/etd/2020-14277","title":"A Graph-Based Indexing Technique for Efficient Searching in Large Scale Textual Documents","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Search engine indexing; Hash table; Inverted index; Hash function; Graph; Workload; Information retrieval; Search engine; Latency (audio); Data mining; Theoretical computer science; Operating system; Programming language","score_opus":0.010708776366627721,"score_gpt":0.3233975948074325,"score_spread":0.3126888184408048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102769546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001982947,0.00004082461,0.9912568,0.000114392424,0.00006574998,0.0017066499,0.000009722971,0.0005979141,0.0042249993],"genre_scores_gemma":[0.4552626,0.000004938628,0.54219437,0.00025744303,0.00002918516,0.0012410523,0.00036867196,0.00005151198,0.0005902557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971516,0.00009327283,0.00058115367,0.0010039319,0.00058495504,0.000585065],"domain_scores_gemma":[0.9986704,0.00016821118,0.0002733241,0.00061222573,0.00015036065,0.00012547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069254846,0.0003817933,0.00052322133,0.0010861984,0.00016706456,0.00014453132,0.0014119023,0.00028110173,0.00001207184],"category_scores_gemma":[0.000106106265,0.00037802663,0.00029521383,0.0014534076,0.000019817822,0.00026076625,0.00017302304,0.0005890132,0.0000075284265],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011164647,0.005344843,0.006306377,0.0053920937,0.00066175556,0.0003683429,0.024245152,0.020325286,0.2538449,0.52218854,0.0034549024,0.15675135],"study_design_scores_gemma":[0.0016423854,0.00035356655,0.00069531327,0.0010491316,0.00005526108,0.000002324397,0.00089150126,0.5237631,0.44267392,0.02501643,0.0021944917,0.0016625863],"about_ca_topic_score_codex":0.000049241695,"about_ca_topic_score_gemma":0.0005662811,"teacher_disagreement_score":0.5034378,"about_ca_system_score_codex":0.00018765173,"about_ca_system_score_gemma":0.00022469419,"threshold_uncertainty_score":0.99986714},"labels":[],"label_agreement":null},{"id":"W310333832","doi":"10.1007/978-1-4939-7131-2_352","title":"Automatic Document Topic Identification Using Social Knowledge Network","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identification (biology); Computer science; Social knowledge; Information retrieval; Social network (sociolinguistics); Data science; World Wide Web; Social media; Sociology; Social science; Biology","score_opus":0.03248065181316784,"score_gpt":0.32177536835942844,"score_spread":0.2892947165462606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W310333832","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030203246,0.0001974593,0.79198515,0.00007256093,0.00033510773,0.00022152856,4.380551e-7,0.00071907585,0.20643848],"genre_scores_gemma":[0.0045151412,0.000037505153,0.3164933,0.00015063844,0.0016213756,0.000020270098,0.000014885361,0.000052903266,0.677094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826175,0.0000302901,0.00054762006,0.0005813343,0.0003087809,0.0002701968],"domain_scores_gemma":[0.9984625,0.00004047111,0.0004368805,0.0008030749,0.00020409445,0.000052952557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031742454,0.00029419633,0.00038666106,0.00018000198,0.00026588116,0.00024373073,0.0010222842,0.0002503825,0.0008488635],"category_scores_gemma":[0.0000073251067,0.00028714456,0.00021308503,0.00012014919,0.00009080297,0.00041774017,0.0005226526,0.00017726513,0.0005154217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3358884e-7,0.000009658986,0.0000013172212,0.000027724796,0.000077866,0.0000028494762,0.00032086225,0.0000051721677,0.000036822963,0.88652873,0.011948964,0.10103968],"study_design_scores_gemma":[0.00006155557,0.000023283152,0.00002128313,0.00010615629,0.00009008842,0.0000046541372,0.000002370747,0.04744936,0.0002234282,0.8666419,0.08491192,0.00046404512],"about_ca_topic_score_codex":0.0000043064406,"about_ca_topic_score_gemma":0.000025815962,"teacher_disagreement_score":0.47549185,"about_ca_system_score_codex":0.00032314594,"about_ca_system_score_gemma":0.00008773226,"threshold_uncertainty_score":0.9999581},"labels":[],"label_agreement":null},{"id":"W3108390127","doi":"","title":"ScholarLensViz: A Visualization Framework for Transparency in Semantic User Profiles","year":2020,"lang":"en","type":"article","venue":"International Semantic Web Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Transparency (behavior); Visualization; Data visualization; Human–computer interaction; Data mining; Computer security","score_opus":0.04154389703295188,"score_gpt":0.33338222743079854,"score_spread":0.2918383303978467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108390127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021883955,0.000043380875,0.9703131,0.0064312927,0.00017559477,0.0004311942,0.000012024354,0.00031749107,0.00039198817],"genre_scores_gemma":[0.83433867,0.000048675785,0.1646273,0.00067828957,0.00008454897,0.000108885564,0.000021166088,0.000015298516,0.00007718712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980751,0.000060077575,0.00050986075,0.0006279519,0.0004577417,0.00026923668],"domain_scores_gemma":[0.9988424,0.00018991395,0.00019206757,0.00030907596,0.000369629,0.0000969138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020899322,0.00020641966,0.00027749786,0.00022208344,0.000062557505,0.00029524034,0.0014395628,0.00011412752,0.000084767016],"category_scores_gemma":[0.0006022286,0.00021017123,0.000106137944,0.0005615013,0.000045662422,0.001061551,0.000156385,0.00022939511,0.000050450843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029782845,0.0001029504,0.009875934,0.000059429985,0.000046883877,0.000016852144,0.0009783134,0.00016528359,0.01036005,0.9734279,0.00020077502,0.00473585],"study_design_scores_gemma":[0.00074221875,0.00014947967,0.006693137,0.00044313408,0.000026458754,0.0000069470066,0.00007734325,0.8078748,0.020486549,0.15538745,0.0075483206,0.0005641476],"about_ca_topic_score_codex":0.000016789794,"about_ca_topic_score_gemma":0.000039379403,"teacher_disagreement_score":0.81804043,"about_ca_system_score_codex":0.000060298917,"about_ca_system_score_gemma":0.00012762903,"threshold_uncertainty_score":0.8570534},"labels":[],"label_agreement":null},{"id":"W3118942295","doi":"10.3917/comla1.206.0111","title":"La loi de Zipf 70 ans après : pluridisciplinarité, modèles et controverses","year":2020,"lang":"fr","type":"article","venue":"Communication & langages","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Zipf's law; Nomination; Humanities; Philosophy; Mathematics; Political science; Law","score_opus":0.09697734801810269,"score_gpt":0.3398042514465566,"score_spread":0.24282690342845392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118942295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057626935,0.02956664,0.78278184,0.16047801,0.00007622682,0.00035568216,0.00005611109,0.00095246494,0.019970305],"genre_scores_gemma":[0.8341204,0.0073141204,0.15279771,0.003655257,0.00008093751,0.0000521457,0.000053536634,0.000037653997,0.001888239],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996657,0.0018365844,0.0004100349,0.000439903,0.0002761566,0.00038028797],"domain_scores_gemma":[0.9960984,0.0014068526,0.00030181202,0.0017705407,0.00020315654,0.0002192555],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009768355,0.00028116247,0.00039135243,0.000090538924,0.0003902184,0.00038052825,0.002510069,0.0002143435,0.000077847464],"category_scores_gemma":[0.00069875584,0.0003055866,0.00019045964,0.0005658393,0.000434353,0.0011111916,0.0016150187,0.00092915935,0.0001306438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003915172,0.00047944288,0.0024980507,0.00018526625,0.00023498088,0.00006412748,0.046433162,0.002872282,0.0060749403,0.7954569,0.032783113,0.11287863],"study_design_scores_gemma":[0.0010138516,0.00023431549,0.006271809,0.00047523685,0.00023283428,0.00004955743,0.004206348,0.18508366,0.010006971,0.054493375,0.7369242,0.001007871],"about_ca_topic_score_codex":0.00028062766,"about_ca_topic_score_gemma":0.00037140556,"teacher_disagreement_score":0.8283577,"about_ca_system_score_codex":0.00013444589,"about_ca_system_score_gemma":0.00020417452,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null},{"id":"W3121259681","doi":"","title":"Overcoming the Invisibility of Metrology: A Reading Measurement Network for Education and the Social Sciences","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Invisibility; Reading (process); Metrology; Traceability; Quality (philosophy); Political science; Behavioural sciences; Social science; Engineering ethics; Public relations; Sociology; Computer science; Engineering; Epistemology; Law; Mathematics; Statistics","score_opus":0.021299118856972055,"score_gpt":0.3078997637470125,"score_spread":0.28660064489004045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121259681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048541665,0.0027712467,0.9399309,0.008149168,0.00007488327,0.00035256616,7.900145e-8,0.00002020318,0.00015927297],"genre_scores_gemma":[0.98444414,0.00023213033,0.014800549,0.0002920274,0.0001639671,0.00004501175,7.132837e-8,0.0000033244773,0.000018796653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831855,0.00023441785,0.00025463925,0.00017025131,0.00029068982,0.00073145283],"domain_scores_gemma":[0.99902076,0.00025156632,0.00030659037,0.0001699524,0.0002351194,0.000016033753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009886392,0.000078755,0.00016036721,0.0000566039,0.0008583935,0.000119698336,0.00072175177,0.000029209126,9.677809e-7],"category_scores_gemma":[0.00025747757,0.000041223237,0.00009662259,0.0003423137,0.00029957268,0.00039161366,0.00009846708,0.00042279466,2.9804147e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009509406,0.000019191453,0.0009148944,0.0000021899216,0.00006027136,6.485443e-9,0.00038894016,0.000034244847,0.00028320885,0.9009929,0.00022657814,0.09706809],"study_design_scores_gemma":[0.00021287573,0.00008897347,0.0010328871,0.000007896284,0.000028868644,0.00001764293,0.0005404487,0.006402551,0.0001464656,0.9913009,0.00016975698,0.000050762686],"about_ca_topic_score_codex":0.00010299476,"about_ca_topic_score_gemma":0.00020608095,"teacher_disagreement_score":0.9359025,"about_ca_system_score_codex":0.00032311986,"about_ca_system_score_gemma":0.000988786,"threshold_uncertainty_score":0.66021556},"labels":[],"label_agreement":null},{"id":"W3122916539","doi":"","title":"Mind the Gap: Accounting for Measurement Error and Misclassification in Variables Generated via Data Mining","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Econometrics; Computer science; Econometric model; Covariate; Data mining; Errors-in-variables models; Observational error; Variance (accounting); Inference; Parameterized complexity; Statistics; Machine learning; Artificial intelligence; Algorithm; Mathematics; Accounting; Economics","score_opus":0.09644917981351636,"score_gpt":0.33130341012797304,"score_spread":0.23485423031445668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122916539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017383052,0.0012041864,0.9788839,0.0022106075,0.00005770459,0.00016632237,9.0536344e-7,0.000018416864,0.00007487711],"genre_scores_gemma":[0.937748,0.00033971205,0.061659545,0.00003850937,0.00011610272,0.000014115697,0.0000032139976,0.000009847848,0.000070915405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981167,0.00006807711,0.00028701,0.00034662412,0.00029088263,0.0008907133],"domain_scores_gemma":[0.99827904,0.000059140075,0.00045223927,0.0010012193,0.00017757584,0.000030783747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059347698,0.000117364725,0.00014422358,0.00009581239,0.0007859765,0.0005400638,0.0021322346,0.00004674587,9.4138215e-7],"category_scores_gemma":[0.00040225187,0.0000863484,0.000029372408,0.000111938156,0.0000476669,0.0011451123,0.00029750483,0.00047167632,6.6159197e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022579488,0.000063424704,0.0032377082,0.00000804873,0.00017234436,0.000002087785,0.0003560582,0.00009682109,0.031684536,0.04300464,0.00018452387,0.92116725],"study_design_scores_gemma":[0.0010787403,0.00013937338,0.0043864544,0.00009431359,0.00009951375,0.00019664715,0.00053109555,0.7380668,0.0042093135,0.2464449,0.004324327,0.00042849974],"about_ca_topic_score_codex":0.000044127475,"about_ca_topic_score_gemma":0.0020674234,"teacher_disagreement_score":0.92073876,"about_ca_system_score_codex":0.00038047085,"about_ca_system_score_gemma":0.0006556287,"threshold_uncertainty_score":0.6045175},"labels":[],"label_agreement":null},{"id":"W3123195249","doi":"","title":"Contrasting Rule-Based and Similarity-Based Category Learning: The Effects of Mood and Prior Knowledge on Ambiguous Categorization","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; York University","funders":"","keywords":"Categorization; Similarity (geometry); Product (mathematics); Feature (linguistics); Product category; Concept learning; Mood; Phenomenon; Cognitive psychology; Psychology; Artificial intelligence; Computer science; Natural language processing; Social psychology; Mathematics; Linguistics; Epistemology","score_opus":0.013585126114174633,"score_gpt":0.24112069504931413,"score_spread":0.2275355689351395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123195249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105577454,0.00011687439,0.8915874,0.000085310516,0.00003265073,0.00028263897,1.9953059e-7,0.0002609111,0.0020566036],"genre_scores_gemma":[0.9758892,0.0000076068727,0.02388951,0.00011420719,0.000009573626,0.00002244055,0.0000016605721,0.000011272843,0.00005450557],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989693,0.00017298815,0.0002049338,0.0003305847,0.00014112542,0.00018102459],"domain_scores_gemma":[0.99885976,0.00047877096,0.00016139247,0.00031835117,0.00012164475,0.00006009987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033014422,0.00015689152,0.00021169175,0.00013626821,0.0001827372,0.00004793282,0.00028520369,0.00006754233,0.0000027745118],"category_scores_gemma":[0.0002774744,0.00011059695,0.000039227878,0.00028913264,0.00012902761,0.00016621161,0.00008815831,0.00017658691,0.0000013817717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018755856,0.0015129223,0.05019552,0.0011792907,0.00020139306,0.000029401665,0.007865846,0.0010126643,0.08239201,0.18421423,0.00008915797,0.67112],"study_design_scores_gemma":[0.0013722326,0.000991783,0.050310757,0.000099551,0.0000836611,0.0000027853819,0.00004981037,0.3377952,0.60057455,0.008278167,0.00006628819,0.00037523036],"about_ca_topic_score_codex":0.00009180542,"about_ca_topic_score_gemma":0.000032327207,"teacher_disagreement_score":0.8703118,"about_ca_system_score_codex":0.00002046,"about_ca_system_score_gemma":0.000055739478,"threshold_uncertainty_score":0.4510013},"labels":[],"label_agreement":null},{"id":"W3124677217","doi":"","title":"Information about information: a taxonomy of views","year":2010,"lang":"en","type":"article","venue":"MIS Quarterly","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Knowledge management; Taxonomy (biology); Information system; Computer science; Data science; Information retrieval; Business; Political science","score_opus":0.010706269992895189,"score_gpt":0.24259368547888452,"score_spread":0.23188741548598932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124677217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010595076,0.000010175445,0.97823125,0.00017503893,0.00011941968,0.0002053968,0.0000028716756,0.00019931188,0.010461463],"genre_scores_gemma":[0.70843416,0.0000019554843,0.29102263,0.0003632815,0.000030512501,0.00009279736,0.000014914904,0.000002579497,0.000037185997],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905777,0.000016355216,0.00050426583,0.00006965889,0.0002107848,0.00014113942],"domain_scores_gemma":[0.99878424,0.000025882413,0.00032382816,0.0006162828,0.00019575626,0.000053978696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002230748,0.00010064287,0.00015925725,0.0002158907,0.000050541385,0.0001317075,0.0006514516,0.000064103384,0.000040981722],"category_scores_gemma":[0.000022043827,0.00009178062,0.00007963565,0.00035073966,0.000039243503,0.0061291805,0.000024938634,0.00014421673,0.00021211385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001998357,0.000015528865,0.00013083698,0.000019833762,0.000008645737,1.9524691e-7,0.004516234,0.0000032807518,0.0010665399,0.030549169,0.0021820862,0.96150565],"study_design_scores_gemma":[0.0003330413,0.00025917735,0.0022511266,0.000019566618,0.0000092383325,0.000011803012,0.00029113158,0.010184556,0.0079675075,0.0048152003,0.9735839,0.00027375328],"about_ca_topic_score_codex":0.000029360266,"about_ca_topic_score_gemma":0.000030644936,"teacher_disagreement_score":0.9714018,"about_ca_system_score_codex":0.000013139307,"about_ca_system_score_gemma":0.00004091162,"threshold_uncertainty_score":0.44435078},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.026222151389128694,"score_gpt":0.3018622921912353,"score_spread":0.2756401408021066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125334212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016300601,0.000016856011,0.9941766,0.0011366395,0.0032435567,0.0008554814,0.000016379849,0.00006545175,0.000325982],"genre_scores_gemma":[0.8218882,0.000005290149,0.17626312,0.000318496,0.0008711318,0.00018488668,0.0000045321003,0.000014657184,0.000449692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787766,0.00023464735,0.0010233149,0.000074313895,0.0005775643,0.00021249485],"domain_scores_gemma":[0.9925618,0.0013568309,0.0041411794,0.00026174987,0.0016316359,0.00004676392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051340414,0.00012070218,0.00032051365,0.00021067543,0.00040173667,0.0006248638,0.0010302059,0.00023681144,6.557469e-7],"category_scores_gemma":[0.0019420693,0.00008434384,0.0003467242,0.00034306615,0.000012278744,0.0024507912,0.00006165054,0.00033008974,0.000005477131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030980267,0.000022085454,0.00025181123,0.000049311973,0.00021355624,3.397823e-8,0.002300001,0.00440332,0.0001885555,0.96792686,0.022273272,0.00234023],"study_design_scores_gemma":[0.0022125724,0.00030558702,0.0007432893,0.00022749003,0.00025180198,0.00004993411,0.0017491209,0.23620106,0.0017698321,0.22487324,0.53102535,0.0005907014],"about_ca_topic_score_codex":0.0000018374009,"about_ca_topic_score_gemma":5.5976983e-7,"teacher_disagreement_score":0.8217252,"about_ca_system_score_codex":0.00039018568,"about_ca_system_score_gemma":0.00011778892,"threshold_uncertainty_score":0.60255754},"labels":[],"label_agreement":null},{"id":"W3129531092","doi":"10.1109/icdmw51313.2020.00088","title":"Graph-based Topic Extraction Using Centroid Distance of Phrase Embeddings on Healthy Aging Open-ended Survey Questions","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Natural language processing; Phrase; Artificial intelligence; Information retrieval; Word (group theory); Graph; Centroid; Task (project management); Domain (mathematical analysis); Linguistics","score_opus":0.06804492174385719,"score_gpt":0.3786420053132639,"score_spread":0.31059708356940674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129531092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021425506,0.000037166188,0.9761625,0.0015225362,0.000058694804,0.00023730099,0.000008144814,0.0002323804,0.0003158],"genre_scores_gemma":[0.7968506,0.000010469397,0.20186426,0.0012113231,0.000017770775,0.00000696463,0.000008395762,0.000008536674,0.000021662547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984075,0.0002020816,0.0003793282,0.0004939965,0.00027634564,0.00024074041],"domain_scores_gemma":[0.9987983,0.0001569466,0.00027657338,0.0004941474,0.00012955187,0.00014447453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036217814,0.00015414534,0.00027658214,0.00013886995,0.0001592539,0.00012480844,0.0008172665,0.000042344087,0.000017026263],"category_scores_gemma":[0.00015421833,0.00015122186,0.000079821286,0.0010750927,0.000042934185,0.000803766,0.00015713826,0.00017125238,0.0000033494362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006141037,0.0022935662,0.059482787,0.0003855175,0.00021019923,0.000109237466,0.0017256188,0.061053008,0.31164008,0.51260763,0.004246243,0.045632016],"study_design_scores_gemma":[0.0011404183,0.0004495382,0.013541522,0.00016704363,0.000030804633,0.000004202849,0.000057204135,0.8536312,0.1221319,0.007025812,0.0011681971,0.00065214233],"about_ca_topic_score_codex":0.0006135452,"about_ca_topic_score_gemma":0.00028688842,"teacher_disagreement_score":0.7925782,"about_ca_system_score_codex":0.000120802826,"about_ca_system_score_gemma":0.0001098726,"threshold_uncertainty_score":0.6166648},"labels":[],"label_agreement":null},{"id":"W3149495681","doi":"10.18280/isi.260112","title":"Extractive Text Summarization Using Recent Approaches: A Survey","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Text graph; Multi-document summarization; Process (computing); Representation (politics); Natural language processing; Artificial intelligence; Data science","score_opus":0.06615902636918873,"score_gpt":0.27934401843601653,"score_spread":0.21318499206682778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149495681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013748893,0.000115113304,0.98051286,0.000038887207,0.00012619708,0.00018751492,0.000008823173,0.0003204244,0.0049413196],"genre_scores_gemma":[0.77519083,0.00009361384,0.22419094,0.00014466408,0.000026933036,0.000028828363,0.00027057176,0.000010843468,0.00004276295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983448,0.0002326365,0.0005654834,0.0002364248,0.00034899128,0.00027169898],"domain_scores_gemma":[0.99805963,0.00011655762,0.00041634735,0.0005332679,0.00080248836,0.00007168464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069690275,0.00017707262,0.00022511085,0.00025919726,0.00025632652,0.00052109495,0.0003785444,0.000113903334,0.000020801794],"category_scores_gemma":[0.00073180493,0.00018644451,0.00006567864,0.0016935025,0.00006271447,0.00796221,0.00021969594,0.00014465458,0.000033381235],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024486464,0.00012272355,0.006501911,0.00014248065,0.00012098805,0.000010805509,0.008085293,0.008121582,0.0017476428,0.038348593,0.00027222163,0.93650126],"study_design_scores_gemma":[0.00053961674,0.000076461045,0.03443089,0.00020554161,0.00004485629,0.00014023094,0.0012513731,0.8709875,0.05377592,0.02949624,0.008089374,0.00096202554],"about_ca_topic_score_codex":0.00008327725,"about_ca_topic_score_gemma":0.000057296926,"teacher_disagreement_score":0.93553925,"about_ca_system_score_codex":0.00051285536,"about_ca_system_score_gemma":0.00024213304,"threshold_uncertainty_score":0.76029867},"labels":[],"label_agreement":null},{"id":"W3152040157","doi":"10.22148/001c.22086","title":"An Institutional Perspective on Genres: Generic Subtitles in German Literature from 1500-2020","year":2021,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); German; Relation (database); Computer science; Poetry; Field (mathematics); Linguistics; Artificial intelligence; Philosophy","score_opus":0.018246796622688802,"score_gpt":0.32749123006626346,"score_spread":0.30924443344357466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152040157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8837528,0.00316813,0.10911946,0.0027193285,0.00023434026,0.00005341212,0.000015797601,0.00005405135,0.0008826338],"genre_scores_gemma":[0.92929965,0.00053177966,0.06912657,0.00051971804,0.00038989825,6.704493e-7,0.0000144096375,0.000005540188,0.000111741305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861115,0.00009566064,0.00040920902,0.0002586843,0.0004628324,0.0001624724],"domain_scores_gemma":[0.9983572,0.0000464455,0.0002806462,0.00029429563,0.00090157334,0.00011989235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013215347,0.00015759747,0.00030527933,0.00017785162,0.000076916716,0.00026636827,0.00062006665,0.00008482002,0.000026934424],"category_scores_gemma":[0.00011474938,0.000111922,0.00020264361,0.0010138426,0.000049883565,0.0012429599,0.00007577583,0.0004321056,0.000007435689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022400888,0.0024893072,0.008001218,0.00004481774,0.0012948588,0.017693363,0.033069644,0.06904971,0.14651306,0.6802204,0.011661452,0.029738132],"study_design_scores_gemma":[0.0047954023,0.0021392847,0.09484317,0.0020574017,0.00060566474,0.0033275231,0.010351163,0.34114784,0.1283394,0.36696473,0.042111255,0.0033171668],"about_ca_topic_score_codex":0.000016086933,"about_ca_topic_score_gemma":0.00008818674,"teacher_disagreement_score":0.3132557,"about_ca_system_score_codex":0.00035267492,"about_ca_system_score_gemma":0.00016105757,"threshold_uncertainty_score":0.4564047},"labels":[],"label_agreement":null},{"id":"W3160310472","doi":"10.32473/flairs.v34i1.128502","title":"Multilingual Automatic Term Extraction in Low-Resource Domains","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Task (project management); Term (time); Artificial intelligence; Resource (disambiguation); Raw data; Sequence labeling; Sequence (biology); Domain (mathematical analysis); Artificial neural network; Natural language processing; Deep learning; Information extraction; Machine learning; Engineering","score_opus":0.08710697055732607,"score_gpt":0.4004800386628963,"score_spread":0.3133730681055702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160310472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8505075,0.00008193103,0.13532215,0.0063548163,0.0005591424,0.0005470475,0.0000080201,0.00023532445,0.0063840486],"genre_scores_gemma":[0.9739368,0.00013060796,0.025188362,0.00008563096,0.00016451206,0.00006448942,0.0000028288935,0.000014117333,0.00041265215],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961391,0.00005852997,0.0007726431,0.0007010722,0.001793482,0.0005351656],"domain_scores_gemma":[0.9961059,0.000489856,0.00028781226,0.0003944755,0.0026197105,0.00010224884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020783371,0.00020419352,0.00027449653,0.00022212458,0.00026464788,0.0005162154,0.0031892771,0.00014106295,0.00008844407],"category_scores_gemma":[0.0017622143,0.00017904733,0.00030410153,0.0017938617,0.000421635,0.0010611374,0.0014547565,0.0008989691,0.000023691831],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002526952,0.00048025954,0.0025781132,0.00013117168,0.00010840782,0.000011412711,0.006400238,0.0003392325,0.50172347,0.34442088,0.0005724651,0.14320908],"study_design_scores_gemma":[0.000037715126,0.000023528431,0.0005776777,0.0002894874,0.0000044572,0.000010968437,0.0026127663,0.19104607,0.715722,0.089251384,0.00026952778,0.00015440118],"about_ca_topic_score_codex":0.000068458125,"about_ca_topic_score_gemma":0.000078039324,"teacher_disagreement_score":0.25516948,"about_ca_system_score_codex":0.00044391546,"about_ca_system_score_gemma":0.00039742416,"threshold_uncertainty_score":0.73013383},"labels":[],"label_agreement":null},{"id":"W3165419854","doi":"10.5281/zenodo.4622059","title":"Detecting Character References in Literary Novels using a Two Stage Contextual Deep Learning approach","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Character (mathematics); Artificial intelligence; Linguistics; Natural language processing; Deep learning; Computer science; Psychology; Literature; History; Art; Philosophy; Mathematics","score_opus":0.04695709435782621,"score_gpt":0.2825374789226426,"score_spread":0.23558038456481636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165419854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33885786,0.00007677271,0.63577396,0.00004690622,0.000041879335,0.0004027671,0.0000066931534,0.0011666071,0.023626534],"genre_scores_gemma":[0.9747291,0.000013370557,0.024230924,0.000070147486,0.000043796503,5.8668714e-8,0.00009359031,0.00037697385,0.00044200502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978129,0.00045427823,0.00032956642,0.0006212835,0.00036705253,0.0004149055],"domain_scores_gemma":[0.99885917,0.000044775505,0.00019736259,0.0005202792,0.00028400493,0.00009441657],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009610911,0.00016415206,0.00022047437,0.0004747056,0.0007297488,0.0010190748,0.0014989973,0.00005658375,0.0008791783],"category_scores_gemma":[0.00029172987,0.00017072567,0.00005324013,0.0010836902,0.0000602138,0.0012957952,0.0016567673,0.0005170479,0.0007906363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073554795,0.00029812628,0.0005437585,0.00013787266,0.00007625615,0.000044212815,0.01484828,0.0036383455,0.111477636,0.025418244,0.000118168406,0.84332556],"study_design_scores_gemma":[0.0017552208,0.00050720305,0.0023805923,0.00019363755,0.000015331092,0.00018964917,0.0012171499,0.70981604,0.005721226,0.0016179422,0.27559343,0.0009925873],"about_ca_topic_score_codex":0.000023377412,"about_ca_topic_score_gemma":6.2153595e-7,"teacher_disagreement_score":0.84233296,"about_ca_system_score_codex":0.00017284465,"about_ca_system_score_gemma":0.0000045008073,"threshold_uncertainty_score":0.99998736},"labels":[],"label_agreement":null},{"id":"W3168080743","doi":"10.1142/s0129183121501448","title":"Are all the word ranking methods the same?","year":2021,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Iran National Science Foundation","keywords":"Ranking (information retrieval); Word (group theory); Rank (graph theory); Computer science; Rank correlation; Artificial intelligence; Natural language processing; Sample (material); Information retrieval; Mathematics; Machine learning; Combinatorics; Physics","score_opus":0.051366036786578244,"score_gpt":0.38911578411534226,"score_spread":0.337749747328764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168080743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002519549,0.0005773618,0.983223,0.012836959,0.00043385773,0.000028051185,9.4907284e-7,0.000024606241,0.0003556188],"genre_scores_gemma":[0.6794349,0.000106999345,0.31600043,0.0036284868,0.0006641394,0.0000031728155,7.957443e-7,0.000011180459,0.0001499038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842596,0.00024245463,0.0003458462,0.00014685934,0.0007137642,0.00012511849],"domain_scores_gemma":[0.9973113,0.0005072622,0.00078289985,0.00039556262,0.00097134296,0.00003164573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007427929,0.00010252434,0.00016598291,0.00004459509,0.000082184924,0.00028460086,0.002319146,0.000024991712,0.0000070701776],"category_scores_gemma":[0.00019988632,0.000059092443,0.00026563535,0.00020788357,0.000050955856,0.00054608047,0.00042373227,0.00036747145,0.0000033974666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009365608,0.00008157813,0.00023266367,0.0000013501601,0.0004968717,0.00010917556,0.00117262,0.0059842533,0.008542156,0.04889051,0.00085332466,0.9336261],"study_design_scores_gemma":[0.00015210292,0.000008414563,0.0005903087,0.00005131774,0.00003697771,0.00019150272,0.00006561553,0.07083364,0.039252687,0.8783488,0.010365009,0.00010358036],"about_ca_topic_score_codex":0.0000022568672,"about_ca_topic_score_gemma":0.000005069564,"teacher_disagreement_score":0.9335226,"about_ca_system_score_codex":0.00007539458,"about_ca_system_score_gemma":0.00007283974,"threshold_uncertainty_score":0.4309589},"labels":[],"label_agreement":null},{"id":"W3176967269","doi":"","title":"TREC 2020 Podcasts Track Overview.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Operating system","score_opus":0.06050055887350622,"score_gpt":0.310150801677166,"score_spread":0.2496502428036598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176967269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012936906,0.0007891304,0.9662435,0.008811666,0.00013102769,0.00031389293,0.000009229618,0.0015228736,0.0092417635],"genre_scores_gemma":[0.9545207,0.00027510215,0.04237547,0.002239589,0.00013254101,0.0000054161133,0.0000061676224,0.000019574016,0.00042544087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975493,0.00011426064,0.0004415426,0.0008632253,0.0005900356,0.00044164658],"domain_scores_gemma":[0.99823606,0.00011633833,0.00020597476,0.00082771044,0.00025721383,0.00035671052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022632009,0.00030336838,0.00044696248,0.000075407195,0.00011026242,0.00026424875,0.0019538992,0.00012374706,0.00040979675],"category_scores_gemma":[0.00034797407,0.00028815726,0.00017787145,0.0015355616,0.00009898301,0.0009223288,0.00051467225,0.00039192932,0.00065645785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001976266,0.00023921632,0.0016485781,0.00014718957,0.00015384538,0.00040391993,0.0041794544,0.000054576696,0.068325475,0.40194783,0.017554604,0.5051477],"study_design_scores_gemma":[0.002590619,0.0022321648,0.013919223,0.00025908396,0.00017141829,0.000135353,0.00022947023,0.33514,0.30776224,0.09944484,0.23420131,0.00391429],"about_ca_topic_score_codex":0.000012358436,"about_ca_topic_score_gemma":0.0000066837633,"teacher_disagreement_score":0.9415838,"about_ca_system_score_codex":0.0000614885,"about_ca_system_score_gemma":0.0001693409,"threshold_uncertainty_score":0.9999571},"labels":[],"label_agreement":null},{"id":"W3177106525","doi":"","title":"The DELICES project: Indexing scientific literature through semantic expansion","year":2020,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; Natural language processing","score_opus":0.018038087111500255,"score_gpt":0.2554298647587292,"score_spread":0.23739177764722894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177106525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012398736,0.0021611622,0.94755924,0.027712068,0.0001144992,0.00037946974,0.0000042060888,0.00079488725,0.008875728],"genre_scores_gemma":[0.7563465,0.0004498083,0.24027283,0.00052442256,0.000029137524,0.000055221375,0.000041996253,0.000028316395,0.0022517452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99532086,0.0022251813,0.0004589605,0.00090928335,0.0006478753,0.0004378355],"domain_scores_gemma":[0.9945873,0.0010591501,0.00035448268,0.0021080666,0.0017592938,0.00013173404],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032590602,0.00025595856,0.00023720034,0.00012323199,0.0015038379,0.002443209,0.0029509705,0.000112094596,0.0000074536883],"category_scores_gemma":[0.0014725074,0.00020014941,0.00016976595,0.002626731,0.00032627583,0.001304624,0.0011584954,0.0004214345,0.00003626042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001251976,0.000268906,0.0007067114,0.00009721847,0.00007357468,0.000020846686,0.08131815,0.00005081629,0.040247604,0.684333,0.006209546,0.18666111],"study_design_scores_gemma":[0.00067173276,0.0000027883227,0.00057185563,0.0014851391,0.000047696267,0.0000345745,0.00058519334,0.2739337,0.4460319,0.042805385,0.23282172,0.0010083092],"about_ca_topic_score_codex":0.000106115804,"about_ca_topic_score_gemma":0.00026263396,"teacher_disagreement_score":0.7439478,"about_ca_system_score_codex":0.00005361703,"about_ca_system_score_gemma":0.00018325176,"threshold_uncertainty_score":0.9997961},"labels":[],"label_agreement":null},{"id":"W3188655801","doi":"10.1037/cbs0000294","title":"TMI? Accompanying details impact statements’ perceived veracity.","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Applied psychology; Social psychology","score_opus":0.10438393626355984,"score_gpt":0.328269907150494,"score_spread":0.22388597088693413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188655801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96146166,0.0003645346,0.035681162,0.000804911,0.0008986095,0.00019267513,0.000019323956,0.00004174378,0.0005353531],"genre_scores_gemma":[0.95448494,0.000034156124,0.04506932,0.0002196981,0.00008489149,0.000006778649,0.000004607754,0.000014057674,0.00008155113],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948844,0.00015548134,0.0012627386,0.0008984976,0.00080618064,0.001992724],"domain_scores_gemma":[0.992791,0.00007563066,0.0011234964,0.00077806634,0.0020399566,0.0031918585],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0036393814,0.00041225218,0.00065018114,0.0016865155,0.0027161285,0.0016091012,0.004399136,0.00007007665,0.00031283582],"category_scores_gemma":[0.000409717,0.00036851934,0.00039418013,0.0047286577,0.0030130849,0.005856323,0.00028803674,0.00041023403,0.000010343258],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000008170955,0.00026686784,0.8553756,0.000032782995,0.00014101656,0.006426432,0.010962403,0.006498937,0.03357932,0.013680015,0.00061687536,0.0724116],"study_design_scores_gemma":[0.0013689292,0.0012563223,0.9353906,0.00054345996,0.00018973969,0.006026579,0.004176681,0.021818338,0.009623509,0.014905658,0.0029595518,0.0017406279],"about_ca_topic_score_codex":0.034142762,"about_ca_topic_score_gemma":0.28336686,"teacher_disagreement_score":0.24922411,"about_ca_system_score_codex":0.004926541,"about_ca_system_score_gemma":0.009046825,"threshold_uncertainty_score":0.9998767},"labels":[],"label_agreement":null},{"id":"W3196840400","doi":"10.2139/ssrn.3908201","title":"Comparing Methods of Exploratory Data Analysis for the Moral Foundations Questionnaire with a Small Sample","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern Alberta Institute of Technology","funders":"","keywords":"Sample (material); Psychology; Chromatography","score_opus":0.11276888888840333,"score_gpt":0.3753692400134184,"score_spread":0.2626003511250151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196840400","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001327311,0.0025660952,0.9952882,0.0006132623,0.0000317433,0.00009276513,0.0000035093117,0.000057818117,0.00001927797],"genre_scores_gemma":[0.44717568,0.00036800088,0.55232245,0.00002916218,0.000037586586,0.000014287328,0.000016495509,0.000007416203,0.000028899969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809515,0.00025922683,0.00033983227,0.00034795614,0.00021427896,0.0007435441],"domain_scores_gemma":[0.9974672,0.00047064538,0.00031795594,0.0012533383,0.00044604318,0.000044791068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025997371,0.0001252647,0.0003095175,0.00018718529,0.00038341808,0.00015155505,0.0016264782,0.000030307398,0.00000200182],"category_scores_gemma":[0.0002685634,0.00008790883,0.00016314162,0.00157847,0.00007320848,0.0006766099,0.0003210241,0.00056342734,2.9691645e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023112843,0.000118146025,0.021515545,0.000009783504,0.0036098906,0.0000025229274,0.00034560813,0.010242613,0.00048348872,0.8460819,0.000018697448,0.11754868],"study_design_scores_gemma":[0.00044952653,0.0001766194,0.0022306722,0.000032889628,0.001462178,0.00014592454,0.0012359283,0.39590362,0.0025929855,0.594375,0.0011215222,0.00027314585],"about_ca_topic_score_codex":0.0000813197,"about_ca_topic_score_gemma":0.006194771,"teacher_disagreement_score":0.44584838,"about_ca_system_score_codex":0.00023479198,"about_ca_system_score_gemma":0.0017844336,"threshold_uncertainty_score":0.3584818},"labels":[],"label_agreement":null},{"id":"W3200955930","doi":"10.1109/access.2021.3111833","title":"Senti-COVID19: An Interactive Visual Analytics System for Detecting Public Sentiment and Insights Regarding COVID-19 From Social Media","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Sentiment analysis; Social media; Computer science; Coronavirus disease 2019 (COVID-19); Lexicon; Public opinion; Action (physics); Data science; Social media analytics; Artificial intelligence; World Wide Web; Political science; Medicine","score_opus":0.07433494689166144,"score_gpt":0.38851405342389667,"score_spread":0.31417910653223524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200955930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2826244,0.00006756216,0.71611285,0.0002365953,0.00038065674,0.00015620037,0.000009208267,0.00036606987,0.000046442918],"genre_scores_gemma":[0.9725773,0.00000942855,0.026631264,0.0003511943,0.00031604737,0.000052681462,0.00002954338,0.000022322689,0.00001024601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977624,0.00023258057,0.00042084788,0.00085525826,0.00038768226,0.00034127085],"domain_scores_gemma":[0.997653,0.0008937002,0.00036466308,0.00043925538,0.00038209668,0.00026725244],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033251994,0.00023025485,0.0004243261,0.0002962908,0.0005266529,0.0014423872,0.00085573207,0.00011685381,0.000004340855],"category_scores_gemma":[0.0004865866,0.00023238639,0.00013736727,0.00076938956,0.000055076795,0.0030362068,0.0005826155,0.00019044364,0.0000017183002],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005038541,0.0024025403,0.029881932,0.0020341822,0.006457731,0.0026857585,0.12620954,0.0029207016,0.27609965,0.069244355,0.003463343,0.47809643],"study_design_scores_gemma":[0.0018830472,0.0000778366,0.00077909743,0.0001268343,0.00028828194,0.00003186205,0.0060325526,0.5019114,0.4654958,0.020181604,0.002140294,0.0010513803],"about_ca_topic_score_codex":0.00008153058,"about_ca_topic_score_gemma":0.0006963587,"teacher_disagreement_score":0.6899529,"about_ca_system_score_codex":0.0004645401,"about_ca_system_score_gemma":0.00022314122,"threshold_uncertainty_score":0.9995942},"labels":[],"label_agreement":null},{"id":"W3201804497","doi":"","title":"A Basic Morphological Parser for Discourse Information Grammar","year":2004,"lang":"en","type":"article","venue":"Papers from the Annual Meetings of the Atlantic Provinces Linguistic Association (PAMAPLA)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Perspective (graphical); Parsing; Lexicon; Grammar; Meaning (existential); Artificial intelligence; Natural language processing; Linguistics; Rule-based machine translation; Epistemology","score_opus":0.006281533642535385,"score_gpt":0.23727348965213016,"score_spread":0.23099195600959477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201804497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5555781,0.0002548934,0.3964536,0.034139473,0.0021219845,0.0034429878,0.00045358806,0.0010521301,0.0065032784],"genre_scores_gemma":[0.96853906,0.00001923077,0.030163808,0.00081123604,0.00024540082,0.00006810258,0.00003511886,0.000009670885,0.000108369066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977685,0.00014029547,0.0006217002,0.00031955412,0.00076463266,0.0003852854],"domain_scores_gemma":[0.99603534,0.0013162624,0.0013690845,0.0006260867,0.0005964518,0.000056773206],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001262596,0.00022738708,0.00034937327,0.00005206758,0.00039728524,0.00016426994,0.0018892646,0.00015132612,0.000003811506],"category_scores_gemma":[0.010378172,0.00013578907,0.00027371754,0.0003649453,0.00013897035,0.0004577415,0.0004010013,0.0002544924,0.000012764884],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000530684,0.0012111416,0.2526939,0.00028646126,0.0019815452,0.000023871198,0.05950647,0.010819508,0.009712204,0.60479313,0.014214413,0.044226658],"study_design_scores_gemma":[0.0066684987,0.0011724464,0.10918776,0.0012138805,0.0018292343,0.000026435868,0.0074631223,0.015762728,0.01909448,0.717029,0.11776172,0.0027907097],"about_ca_topic_score_codex":0.001619761,"about_ca_topic_score_gemma":0.00019918355,"teacher_disagreement_score":0.41296098,"about_ca_system_score_codex":0.00031626967,"about_ca_system_score_gemma":0.00015855125,"threshold_uncertainty_score":0.9979578},"labels":[],"label_agreement":null},{"id":"W3210301698","doi":"","title":"A Semantic Metadata Enrichment Software Ecosystem Based on Topic Metadata Enrichment","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Metadata; Computer science; Information retrieval; Semantic grid; Scalability; Metadata modeling; World Wide Web; Annotation; Linked data; Metadata repository; Semantic Web; Database; Artificial intelligence","score_opus":0.01417168031758521,"score_gpt":0.27847943595544383,"score_spread":0.26430775563785863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210301698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027443531,0.0010223009,0.99275136,0.0023507776,0.00028928,0.00028840185,0.000006582393,0.00023303124,0.00031392326],"genre_scores_gemma":[0.9529382,0.0008165639,0.04305574,0.0004171402,0.00020611563,0.000037769078,0.000010038788,0.000031687396,0.0024867689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950604,0.00022627288,0.00060420664,0.0007844717,0.000984609,0.0023400849],"domain_scores_gemma":[0.99535507,0.00012936733,0.0008284273,0.0032877272,0.00015940286,0.00024002016],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028631461,0.00040186927,0.00056163117,0.00035298406,0.0011026189,0.0017226376,0.005002596,0.00009953595,0.000019287518],"category_scores_gemma":[0.00037120754,0.0003285703,0.00033201682,0.00023514965,0.0000423778,0.003330014,0.0006519331,0.0015062463,0.00004374159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055489887,0.0006478794,0.004097441,0.00005668725,0.0012918162,0.00017500839,0.00010313107,0.000869346,0.00063990976,0.7744157,0.0007954665,0.21685216],"study_design_scores_gemma":[0.005352173,0.0036033026,0.004270161,0.00055727625,0.0011452871,0.0011729879,0.00029069852,0.09325082,0.010100868,0.80098116,0.07597741,0.0032978475],"about_ca_topic_score_codex":0.000059176564,"about_ca_topic_score_gemma":0.00070257747,"teacher_disagreement_score":0.9501938,"about_ca_system_score_codex":0.0015599715,"about_ca_system_score_gemma":0.0016018846,"threshold_uncertainty_score":0.9999166},"labels":[],"label_agreement":null},{"id":"W3214508694","doi":"10.1002/mus.27456","title":"Combining multiple measures into a summary index: A step toward more reliable measurement","year":2021,"lang":"en","type":"letter","venue":"Muscle & Nerve","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Index (typography); Computer science; Statistics; Psychology; Mathematics; World Wide Web","score_opus":0.046154923928692346,"score_gpt":0.26447309893444293,"score_spread":0.21831817500575057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214508694","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000116852854,0.0041546053,0.8194787,0.17204663,0.0007217128,0.0006937185,0.000010956351,0.0015049209,0.0012718949],"genre_scores_gemma":[0.11162502,0.00038892275,0.36909282,0.5107252,0.0032108144,0.0012681605,0.00052020955,0.00049398746,0.002674875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930887,0.0003572461,0.0009196075,0.001804631,0.0028152554,0.0010145274],"domain_scores_gemma":[0.99524814,0.00016733806,0.00058243563,0.002758705,0.0010668183,0.00017657793],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011288142,0.00082597666,0.0011661334,0.0005423904,0.00030354213,0.0005895933,0.0029963336,0.00087925536,0.000024461626],"category_scores_gemma":[0.00037789185,0.0008374622,0.0006469902,0.001210787,0.000111626716,0.0007571005,0.0016796874,0.0025099902,0.000030784915],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008495219,0.00013218801,0.0006823013,0.0003107067,0.00035118987,0.0017212045,0.0013560549,0.00025110313,0.0013399133,0.00014990782,0.9484166,0.04528034],"study_design_scores_gemma":[0.00063355593,0.00010481658,0.0004071176,0.00083338516,0.000116307456,0.000018579198,0.00010191353,0.014951487,0.0022164567,0.0020243898,0.977319,0.0012729745],"about_ca_topic_score_codex":0.0016666009,"about_ca_topic_score_gemma":0.0003776009,"teacher_disagreement_score":0.45038587,"about_ca_system_score_codex":0.00071098295,"about_ca_system_score_gemma":0.00046087013,"threshold_uncertainty_score":0.99979126},"labels":[],"label_agreement":null},{"id":"W3217598503","doi":"10.32920/ryerson.14645355.v1","title":"Microblog summarization based on sentiment and aspect analysis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Automatic summarization; Microblogging; Sentiment analysis; Social media; Computer science; Information retrieval; Baseline (sea); Cluster analysis; Multi-document summarization; Annotation; Natural language processing; Data science; Artificial intelligence; World Wide Web","score_opus":0.009684912507483769,"score_gpt":0.263804563741241,"score_spread":0.25411965123375724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217598503","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020731548,0.000097831566,0.99356055,0.0006950179,0.00006007805,0.00017362734,0.0000031479576,0.00043359655,0.0029029828],"genre_scores_gemma":[0.4978348,0.000056015684,0.5009136,0.0005385749,0.000017251432,0.000025458145,0.00017133572,0.0000103285965,0.00043264084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979254,0.00012638752,0.00032382214,0.0010847581,0.00034829756,0.00019135971],"domain_scores_gemma":[0.99799824,0.000081777114,0.00021509988,0.0014704688,0.00015836352,0.0000760464],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025817545,0.00027586566,0.00049054454,0.0007929966,0.000072911316,0.000512609,0.00063242414,0.00017432777,0.0000862262],"category_scores_gemma":[0.000028223607,0.00026184038,0.00031731676,0.0012108175,0.000031203293,0.00014449157,0.0012807732,0.00027956563,0.000004400512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032819276,0.0020692693,0.048681274,0.00046317474,0.010295144,0.000425824,0.001079622,0.6953448,0.019275855,0.08338958,0.0035721925,0.13537045],"study_design_scores_gemma":[0.00009265813,0.000024890913,0.0026462278,0.000043007472,0.0005021999,6.728733e-7,0.0000067734222,0.9689038,0.024536626,0.0027075293,0.0001620364,0.00037359475],"about_ca_topic_score_codex":0.0000914314,"about_ca_topic_score_gemma":0.000118817734,"teacher_disagreement_score":0.49576163,"about_ca_system_score_codex":0.00012565452,"about_ca_system_score_gemma":0.000084005966,"threshold_uncertainty_score":0.9999834},"labels":[],"label_agreement":null},{"id":"W342307487","doi":"10.1007/978-3-319-13332-4_21","title":"A Comparison of Graph-Based and Statistical Metrics for Learning Domain Keywords","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Pointwise mutual information; Graph; Pointwise; Artificial intelligence; Phrase; Machine learning; Data mining; Mutual information; Theoretical computer science; Mathematics","score_opus":0.021132709711514663,"score_gpt":0.3197664553226307,"score_spread":0.29863374561111605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W342307487","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052398682,0.00034454878,0.9984719,0.00016071716,0.00018221473,0.00038048084,0.000006253546,0.00015450818,0.00024693928],"genre_scores_gemma":[0.23640281,0.000009310094,0.76329947,0.00016679459,0.00005709383,0.000011106,0.0000066513876,0.000020925598,0.000025850246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966995,0.000061964856,0.00068809185,0.0012198539,0.0008462685,0.000484324],"domain_scores_gemma":[0.9956162,0.0025127004,0.00055399636,0.0008258763,0.0003450609,0.00014618755],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013491978,0.00042118318,0.0009392519,0.0015986967,0.00020905623,0.00021190003,0.0017627393,0.00026127548,0.000003868874],"category_scores_gemma":[0.00043829405,0.00039172548,0.00013811019,0.0009503125,0.000991425,0.0001920216,0.00061745435,0.0006411768,0.0000012127342],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011823661,0.00003443021,0.00075881317,0.00011672033,0.000016596474,0.0000062593103,0.00026480618,0.030857773,0.00019299709,0.17754954,0.000018402312,0.79017186],"study_design_scores_gemma":[0.00021763553,0.0004319885,0.000057969777,0.00014336119,0.000016168136,0.0000035528012,1.6026111e-7,0.67065716,0.001972927,0.32486734,0.0012783525,0.00035341355],"about_ca_topic_score_codex":0.000008269635,"about_ca_topic_score_gemma":0.00002946699,"teacher_disagreement_score":0.7898184,"about_ca_system_score_codex":0.00012398284,"about_ca_system_score_gemma":0.00021733198,"threshold_uncertainty_score":0.9998535},"labels":[],"label_agreement":null},{"id":"W366205791","doi":"10.1007/978-94-017-9112-0_34","title":"Understanding Design Concept Identification","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Identification (biology); Computer science; Brainstorming; Selection (genetic algorithm); Process (computing); Identifier; Workflow; Cognitive science; Artificial intelligence; Programming language; Psychology","score_opus":0.1505184642011906,"score_gpt":0.2905078990430491,"score_spread":0.13998943484185847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W366205791","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.6559347e-9,0.00005003854,0.68026876,0.00012457995,0.00007121427,0.0001360084,4.2278302e-7,0.0005659059,0.31878304],"genre_scores_gemma":[0.0067127296,0.000055240755,0.28485957,0.00022589433,0.00007629608,0.000008799641,0.000010502992,0.000034053017,0.70801693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854434,0.000026590915,0.00035627454,0.00056343316,0.0003439035,0.00016545813],"domain_scores_gemma":[0.99836916,0.00014782489,0.0003312422,0.001003146,0.00008717506,0.00006147969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003172948,0.00024018716,0.00028761025,0.0002516328,0.00010393411,0.00019101432,0.0010089853,0.00020575902,0.0001505882],"category_scores_gemma":[0.000018845305,0.00023062639,0.0001331065,0.000057323734,0.00008252847,0.00027057112,0.00018527366,0.00018689805,0.00024691303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6704554e-7,0.0000013454121,1.03356406e-7,0.0000025988816,0.000021682115,0.0000021585872,0.000027304499,0.00005192464,0.00007417899,0.9846404,0.007898415,0.00727953],"study_design_scores_gemma":[0.000048081885,0.000028632674,4.2273106e-7,0.000038187372,0.000026652406,0.0000038871967,0.0000024498565,0.014743221,0.0021903266,0.9459599,0.036619272,0.00033893134],"about_ca_topic_score_codex":0.0000014902954,"about_ca_topic_score_gemma":0.0000025228012,"teacher_disagreement_score":0.39540923,"about_ca_system_score_codex":0.0002967277,"about_ca_system_score_gemma":0.000038474456,"threshold_uncertainty_score":0.9404671},"labels":[],"label_agreement":null},{"id":"W36643226","doi":"10.1007/1-4020-3670-1_10","title":"A Cognitive Framework for Human Information Behavior: The Place of Metaphor in Human Information Organizing Behavior","year":2006,"lang":"en","type":"book-chapter","venue":"Information science and knowledge management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Nexus (standard); Metaphor; Unconscious mind; Perspective (graphical); Cognitive science; Cognition; Psychology; Sociology; Social psychology; Computer science; Psychoanalysis; Artificial intelligence; Linguistics; Philosophy; Neuroscience","score_opus":0.0241227843392514,"score_gpt":0.31908846873074403,"score_spread":0.2949656843914926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36643226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012314547,0.000066612396,0.69151074,0.00006784287,0.00017561532,0.0037601043,0.000050702736,0.00019108556,0.30294582],"genre_scores_gemma":[0.9331828,0.00018118494,0.05742637,0.0007982056,0.0000880827,0.002329898,0.00069708953,0.000036738456,0.0052596303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708647,0.000018550174,0.0013758704,0.00023943004,0.00093619764,0.0003434572],"domain_scores_gemma":[0.9965589,0.00010879132,0.0012537418,0.0005997448,0.0014114897,0.000067328816],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018796048,0.0003441588,0.00037962294,0.0022078913,0.0006538312,0.0007630287,0.0012897709,0.00018781566,0.000009827003],"category_scores_gemma":[0.000104137886,0.00029172262,0.000109873996,0.0009212572,0.00043625658,0.0141221825,0.000834198,0.00031197182,0.000042408392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043475634,0.000028744671,0.00003740249,0.00015849904,0.000018046858,3.90656e-7,0.0037355737,0.000017178503,0.000009883928,0.8800731,0.00037998927,0.1155369],"study_design_scores_gemma":[0.0062412275,0.0013687571,0.01756905,0.004400663,0.0022429095,0.000040307124,0.0137658315,0.019017134,0.008459206,0.21051787,0.71089745,0.0054795947],"about_ca_topic_score_codex":0.000024653173,"about_ca_topic_score_gemma":0.000035573485,"teacher_disagreement_score":0.93195134,"about_ca_system_score_codex":0.0003353667,"about_ca_system_score_gemma":0.00013403285,"threshold_uncertainty_score":0.9999535},"labels":[],"label_agreement":null},{"id":"W4210562377","doi":"10.1109/icmla52953.2021.00204","title":"Sentiment Analysis of StockTwits Using Transformer Models","year":2021,"lang":"en","type":"article","venue":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Transformer; Electrical engineering; Engineering; Voltage","score_opus":0.053578207070827055,"score_gpt":0.35676368059054697,"score_spread":0.3031854735197199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210562377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010255512,0.000119130855,0.9821824,0.00078340457,0.000034891196,0.000118671924,0.000025720883,0.000067373476,0.006412898],"genre_scores_gemma":[0.9559717,0.00037354973,0.042151764,0.00008012186,0.000033567183,0.00005932069,0.000078527446,0.000009733567,0.0012416996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849564,0.00007811756,0.00035544424,0.00052078156,0.00039543625,0.00015458449],"domain_scores_gemma":[0.9988575,0.00007172866,0.00021474839,0.00034852762,0.0004355646,0.000071943075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018588082,0.00016187382,0.00029785547,0.0004497551,0.00014699643,0.000120390185,0.00041799335,0.000057427565,0.00013681539],"category_scores_gemma":[0.000015528813,0.00016424603,0.00015523343,0.0010581003,0.000053897158,0.00033594077,0.00007411812,0.0002511926,0.000005226397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000143735015,0.0003065567,0.0029473251,0.00001613051,0.0013684969,0.000007271925,0.00040692982,0.16153024,0.05469625,0.6868464,0.000020732636,0.091839306],"study_design_scores_gemma":[0.00015284512,0.000023457314,0.00018845254,0.000024689514,0.00018225647,0.000005115941,0.00005260462,0.9798771,0.0102596665,0.006885325,0.002180644,0.0001678206],"about_ca_topic_score_codex":0.00006619528,"about_ca_topic_score_gemma":0.00004118657,"teacher_disagreement_score":0.9457162,"about_ca_system_score_codex":0.000052188458,"about_ca_system_score_gemma":0.000076970566,"threshold_uncertainty_score":0.66977584},"labels":[],"label_agreement":null},{"id":"W4211085863","doi":"10.1017/cbo9780511500107.002","title":"Preliminaries","year":2002,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sketch; Foundation (evidence); Epistemology; Empirical research; Reading (process); Domain (mathematical analysis); Computer science; Term (time); Management science; Linguistics; Mathematics; Philosophy; Engineering; History; Algorithm","score_opus":0.022315069497845428,"score_gpt":0.20147244822639773,"score_spread":0.1791573787285523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211085863","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012302056,0.0001705827,0.20332076,0.000027770951,0.00008309382,0.00020790474,0.000022887538,0.0007839883,0.7953818],"genre_scores_gemma":[0.00024487925,0.00023317973,0.013022525,0.00007464519,0.000064072075,8.764082e-7,0.000010264945,0.00003673188,0.9863128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828523,0.000028682898,0.00020922653,0.0007835879,0.0003717844,0.00032150603],"domain_scores_gemma":[0.9978119,0.00007083694,0.0002939572,0.0014707296,0.00019336652,0.00015917135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006751056,0.00042987458,0.00046556472,0.00031941762,0.00021832393,0.00011516898,0.0020500713,0.0003648343,0.000005633715],"category_scores_gemma":[0.000009294425,0.00051590014,0.0003075921,0.000017994125,0.0002505422,0.00035540157,0.0013017636,0.00048445564,0.000045558805],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060108464,0.0000065374024,2.8336183e-7,0.00002061965,0.00008002772,0.00030837025,0.000032171178,0.000002054339,0.000011070436,0.946427,0.046831407,0.006274486],"study_design_scores_gemma":[0.00015367001,0.000059372695,0.0000022331387,0.00008601645,0.00011652519,0.000019905554,0.0000027016383,0.0009023109,0.0006718495,0.00028372914,0.99715865,0.00054301653],"about_ca_topic_score_codex":0.000024452711,"about_ca_topic_score_gemma":6.3968207e-7,"teacher_disagreement_score":0.9503273,"about_ca_system_score_codex":0.00021910058,"about_ca_system_score_gemma":0.000049457314,"threshold_uncertainty_score":0.9997293},"labels":[],"label_agreement":null},{"id":"W4213159392","doi":"10.21203/rs.3.rs-1041491/v1","title":"A Proposed Method for Residual Citation Allocation Based on Citation Contexts’ Similarity","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Citation; Residual; Similarity (geometry); Computer science; Information retrieval; Data science; Artificial intelligence; Algorithm; World Wide Web","score_opus":0.11728681695612835,"score_gpt":0.47453324176773076,"score_spread":0.3572464248116024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213159392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010535097,0.00012324749,0.9893625,0.005269981,0.00011678908,0.0031162286,0.000038987328,0.00044587202,0.00047292016],"genre_scores_gemma":[0.32494882,0.000024595513,0.67254144,0.00018354149,0.00012105923,0.0011897748,0.00076568685,0.00003671119,0.00018834868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99272156,0.002372991,0.00057711964,0.0015472218,0.0021700696,0.0006110522],"domain_scores_gemma":[0.99017966,0.002944215,0.00031965028,0.0018444413,0.004548103,0.0001639068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006939133,0.00033604781,0.0004924777,0.00131149,0.0004151328,0.0008720888,0.0013890679,0.00047406796,0.000019316263],"category_scores_gemma":[0.0050509283,0.0003463936,0.00029690017,0.0013772075,0.00009382105,0.00040100943,0.0007463918,0.001309641,0.000009178873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085303566,0.002493799,0.0005428544,0.0067600356,0.00047570668,0.000116740775,0.0075718127,0.09641708,0.028264765,0.20601566,0.014381602,0.6361069],"study_design_scores_gemma":[0.0006269104,0.0005795728,0.0018544008,0.000804129,0.000027392982,7.4039883e-7,0.00025333575,0.8674147,0.039288145,0.088002354,0.00069702195,0.00045130664],"about_ca_topic_score_codex":0.0001545699,"about_ca_topic_score_gemma":0.00024527754,"teacher_disagreement_score":0.77099764,"about_ca_system_score_codex":0.00076826196,"about_ca_system_score_gemma":0.0012983484,"threshold_uncertainty_score":0.9998988},"labels":[],"label_agreement":null},{"id":"W4220686815","doi":"10.29173/cais1293","title":"Correlation of term usage and term indexing frequencies","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Zipf's law; Term (time); Search engine indexing; Information retrieval; Rank (graph theory); Computer science; Cluster analysis; Index (typography); Plot (graphics); Word (group theory); Data mining; Statistics; Mathematics; Artificial intelligence; World Wide Web","score_opus":0.01800631411748159,"score_gpt":0.24861207457086676,"score_spread":0.23060576045338516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220686815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99005824,0.00015090717,0.0062025785,0.00046606094,0.00006510258,0.00024935737,0.000039466464,0.000077329656,0.0026909641],"genre_scores_gemma":[0.993354,0.000047406702,0.006280183,0.000072639756,0.000016761298,0.000030986397,0.0000018634261,0.000011882588,0.00018428199],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983007,0.000031833322,0.00051139516,0.00033890991,0.00056006736,0.00025713138],"domain_scores_gemma":[0.9886244,0.00013290423,0.0010712653,0.0002702798,0.009837379,0.00006377054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006496315,0.00019510543,0.00041584033,0.00026986326,0.00019932125,0.0006806156,0.0021773633,0.000070503505,0.000012212015],"category_scores_gemma":[0.0030553513,0.00016783566,0.00012441202,0.0006541689,0.00036357986,0.0079583805,0.0017775416,0.00029269754,2.1272741e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005657315,0.00017164045,0.5848889,0.00028711464,0.00011722713,0.0000022747142,0.049877346,0.00006108738,0.23140992,0.10476738,0.00036749113,0.02799308],"study_design_scores_gemma":[0.001148879,0.0012167185,0.50760484,0.0005572981,0.00021806067,0.00014596432,0.0045052995,0.017423265,0.36057892,0.09862392,0.0069422615,0.0010345685],"about_ca_topic_score_codex":0.00007274271,"about_ca_topic_score_gemma":0.0000043426553,"teacher_disagreement_score":0.129169,"about_ca_system_score_codex":0.000067829016,"about_ca_system_score_gemma":0.00013339038,"threshold_uncertainty_score":0.68441397},"labels":[],"label_agreement":null},{"id":"W4220849857","doi":"10.29173/cais1282","title":"IdeaMap: A sophisticated graphical idea processor","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science","score_opus":0.01780833033444457,"score_gpt":0.2552334052985238,"score_spread":0.23742507496407922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220849857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95975465,0.0003433439,0.020973485,0.010757149,0.00019636919,0.00092870643,0.00015353161,0.00063680497,0.006255968],"genre_scores_gemma":[0.9874897,0.000038140613,0.011595821,0.00038368962,0.00003801111,0.00015521237,0.0000034182683,0.000025024978,0.00027098364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971177,0.00004187638,0.00070767547,0.0006153114,0.0009988943,0.00051854725],"domain_scores_gemma":[0.97087395,0.0001573519,0.0010731524,0.0004750665,0.02726999,0.00015051509],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008618517,0.0003219471,0.0006023451,0.0003368104,0.0003511324,0.0013818743,0.0056936187,0.00010649918,0.000028111252],"category_scores_gemma":[0.0075568436,0.00026863,0.00034251242,0.0019778986,0.0004740446,0.0075072777,0.0029031402,0.0005634487,0.000001726698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024598037,0.0009073188,0.05645503,0.00055176707,0.00041193594,0.000011433485,0.028055666,0.00005793965,0.09642835,0.78962255,0.009423046,0.017828964],"study_design_scores_gemma":[0.0019212223,0.0019378917,0.04275845,0.00041014652,0.00043018305,0.00031847417,0.0028212862,0.031628743,0.20932436,0.5595146,0.1468897,0.0020449688],"about_ca_topic_score_codex":0.00005949506,"about_ca_topic_score_gemma":0.0000039979423,"teacher_disagreement_score":0.230108,"about_ca_system_score_codex":0.000102446575,"about_ca_system_score_gemma":0.00030732082,"threshold_uncertainty_score":0.9999766},"labels":[],"label_agreement":null},{"id":"W4220959518","doi":"10.5281/zenodo.6366635","title":"Identifying science in the news: An assessment of the precision and recall of Altmetric.com news mention data","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Recall; Computer science; Altmetrics; Fake news; Data science; Information retrieval; Psychology; Internet privacy; Cognitive psychology","score_opus":0.09913731076647833,"score_gpt":0.3735945198395886,"score_spread":0.2744572090731102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220959518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10584329,0.00014482875,0.88002336,0.0017356656,0.0001288894,0.001087404,0.000076180164,0.00026694604,0.0106934635],"genre_scores_gemma":[0.9864698,0.000081656646,0.013187406,0.000059901842,0.0000089125515,7.303098e-8,0.00007071944,0.00008119582,0.000040320618],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973969,0.0008319289,0.00028051483,0.00042681408,0.0009052172,0.00015866007],"domain_scores_gemma":[0.99795437,0.00005046422,0.0002331948,0.0015072742,0.00021743156,0.00003729191],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0037555965,0.00006465272,0.000102173406,0.00040966284,0.0012660704,0.0004022146,0.005939522,0.000012452758,0.0001798577],"category_scores_gemma":[0.0004906478,0.000048416798,0.00002165963,0.0032624737,0.00019658379,0.0010612039,0.008950164,0.00020641721,0.000005133032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001924511,0.0005898405,0.0005461066,0.00004669916,0.000019793364,0.000004366463,0.0044029276,0.0007575131,0.04791496,0.043992493,0.010508717,0.8911973],"study_design_scores_gemma":[0.0015978221,0.0017729397,0.0969134,0.00015506493,0.00007179075,0.0001880295,0.0072156037,0.35545892,0.008403953,0.023587374,0.5039699,0.0006651837],"about_ca_topic_score_codex":0.00006594067,"about_ca_topic_score_gemma":0.0000029207451,"teacher_disagreement_score":0.89053214,"about_ca_system_score_codex":0.000112570844,"about_ca_system_score_gemma":0.00001247793,"threshold_uncertainty_score":0.9994388},"labels":[],"label_agreement":null},{"id":"W4221028329","doi":"10.1037/cep0000277","title":"Beauty and truth, truth and beauty: Chiastic structure increases the subjective accuracy of statements.","year":2022,"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":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Beauty; Happiness; Fluency; Psychology; PsycINFO; Cognitive psychology; Computer science; Social psychology; Linguistics; Aesthetics; Philosophy; MEDLINE; Mathematics education; Law","score_opus":0.022957224937724587,"score_gpt":0.3252512354830567,"score_spread":0.3022940105453321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221028329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887013,0.0065880166,0.0021217642,0.0007320619,0.0010143579,0.0003516905,0.00016841765,0.000026330536,0.00029604728],"genre_scores_gemma":[0.9924946,0.000068779016,0.0060557593,0.0011942137,0.00008427518,0.00004362345,0.000012125464,0.000031290492,0.000015346373],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970376,0.00038966804,0.0007584503,0.0006737978,0.00017304055,0.0009674565],"domain_scores_gemma":[0.99700314,0.0003552047,0.0008210664,0.0007784072,0.00009401591,0.00094814535],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090908026,0.0003566416,0.00054250634,0.0006338499,0.00058256043,0.00008558924,0.0016457578,0.00010107705,0.00016925983],"category_scores_gemma":[0.00028799762,0.00032306142,0.00014446133,0.0006008873,0.00069313153,0.0006066399,0.00026313163,0.00064572424,6.364149e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001435841,0.0023914294,0.14491917,0.00013833953,0.003177868,0.004768874,0.11182172,0.00063491147,0.50978416,0.13755207,0.017309248,0.06606633],"study_design_scores_gemma":[0.019019095,0.019105203,0.43447083,0.0004285772,0.00070062623,0.038760882,0.116949454,0.0016270097,0.17175531,0.17158158,0.020902742,0.004698674],"about_ca_topic_score_codex":0.004824775,"about_ca_topic_score_gemma":0.006652857,"teacher_disagreement_score":0.33802888,"about_ca_system_score_codex":0.0011070061,"about_ca_system_score_gemma":0.00042588924,"threshold_uncertainty_score":0.99992216},"labels":[],"label_agreement":null},{"id":"W4229010387","doi":"10.16995/dscn.8106","title":"Concept Detection in Philosophical Corpora","year":2022,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Cosine similarity; Natural language processing; Document retrieval; Information retrieval; Similarity (geometry); Artificial intelligence; Word (group theory); Embedding; Linguistics; Pattern recognition (psychology); Philosophy; Image (mathematics)","score_opus":0.025000278519651958,"score_gpt":0.2731868783958897,"score_spread":0.24818659987623773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229010387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3199833,0.0017229605,0.6625121,0.0073023583,0.0004200128,0.00060369394,0.000024358684,0.0012145438,0.006216642],"genre_scores_gemma":[0.99889857,0.00004489709,0.0002851221,0.0002991314,0.00006134211,0.00025078046,0.000007814532,0.000015672196,0.00013667886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998402,0.00009125641,0.00033508523,0.0005296886,0.00034110303,0.00030085523],"domain_scores_gemma":[0.99915725,0.00012624291,0.00014790565,0.00042385122,0.000088816174,0.00005595072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022500083,0.00019389039,0.00033445525,0.00018748872,0.00029261276,0.0000879666,0.00064770796,0.00004095789,0.0000045733277],"category_scores_gemma":[0.00012526836,0.00020216906,0.000116043884,0.00093601,0.0001368806,0.00081705174,0.0012973634,0.00035348494,0.000008025851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020132195,0.0028454901,0.0074541206,0.00010706471,0.00082468527,0.0017147536,0.398585,0.00890175,0.005331435,0.091646954,0.0030355575,0.47935188],"study_design_scores_gemma":[0.0010380171,0.0006702849,0.000499884,0.000028460623,2.5050377e-7,0.00012570154,0.07694628,0.0073981546,0.0136385085,0.8802648,0.018390214,0.0009994187],"about_ca_topic_score_codex":0.000020673162,"about_ca_topic_score_gemma":0.000051528146,"teacher_disagreement_score":0.78861785,"about_ca_system_score_codex":0.00032298357,"about_ca_system_score_gemma":0.00004253142,"threshold_uncertainty_score":0.82442147},"labels":[],"label_agreement":null},{"id":"W4229813582","doi":"10.1017/cbo9781139979573.006","title":"Path analysis and maximum likelihood","year":2016,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Personality psychology; Discipline; Epistemology; Path (computing); Sociology; History; Psychology; Social science; Social psychology; Computer science; Philosophy; Personality","score_opus":0.01060950749121917,"score_gpt":0.2000616385044859,"score_spread":0.18945213101326674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229813582","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009522493,0.000115898154,0.44021046,0.000021948532,0.00002946294,0.00012322857,0.000052520325,0.00031648309,0.5591205],"genre_scores_gemma":[0.0012862202,0.00034796502,0.013963263,0.00007366033,0.000054240074,8.968541e-7,0.000012254809,0.000031224663,0.9842303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980294,0.000041046118,0.00022799216,0.0009917737,0.00035127264,0.00035853148],"domain_scores_gemma":[0.99774617,0.00008389808,0.00033976464,0.0013867298,0.00019641913,0.00024702566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001287402,0.00043855212,0.00066488324,0.0007772029,0.00018371451,0.000104257466,0.0013436251,0.0003322061,0.0000032114876],"category_scores_gemma":[0.0000068578197,0.0004327068,0.00043002155,0.000052024294,0.00022070651,0.0003228301,0.00141019,0.00030854385,0.000011575403],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008604136,0.000005457129,0.000011737754,0.000020584437,0.00079878484,0.00023361867,0.000020906198,1.6793584e-7,0.00006223684,0.9608355,0.0019452297,0.036057185],"study_design_scores_gemma":[0.00047768294,0.00008352479,0.0000823926,0.00015439383,0.0021958966,0.000016905253,0.000005292707,0.00063144235,0.0010390315,0.0033547564,0.9907857,0.0011729924],"about_ca_topic_score_codex":0.00004860792,"about_ca_topic_score_gemma":0.0000064026835,"teacher_disagreement_score":0.98884046,"about_ca_system_score_codex":0.00017531276,"about_ca_system_score_gemma":0.00006796416,"threshold_uncertainty_score":0.9998125},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Capital Medical University","keywords":"Count data; Statistics; Negative binomial distribution; Poisson regression; Akaike information criterion; Mathematics; Regression analysis; Linear regression; Poisson distribution; Overdispersion; Log-normal distribution; Generalized linear model; Binomial regression; Regression diagnostic; Econometrics; Polynomial regression; Population","score_opus":0.103223804081119,"score_gpt":0.3570945740796192,"score_spread":0.2538707699985002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W423015428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17380138,0.0037154844,0.8218133,0.000059706494,0.00016024518,0.000112353264,0.0000011187186,0.000042383173,0.00029405425],"genre_scores_gemma":[0.68673,0.002247306,0.31082717,0.00009233856,0.000042733995,0.0000029471632,7.0284295e-7,0.000010189707,0.000046578996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996476,0.00010515386,0.0016057367,0.0001951677,0.0012315819,0.0003863743],"domain_scores_gemma":[0.9949323,0.0012002634,0.0015050469,0.00037619343,0.0017142985,0.0002719241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060026147,0.00025620664,0.0007645148,0.0047702654,0.000095942305,0.00017513546,0.0008552774,0.00017694189,5.2453373e-7],"category_scores_gemma":[0.002962127,0.00019221741,0.000105454244,0.006009157,0.000101941405,0.005555848,0.00041682617,0.0006421939,0.0000012358203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034110877,0.0000925449,0.014880593,0.000034874352,0.000067810586,0.00004908803,0.0030228484,0.96374387,0.000006136033,0.0015121952,0.0007795466,0.015469374],"study_design_scores_gemma":[0.0009498698,0.000508794,0.00043741913,0.00020656371,0.000025689204,0.00007024848,0.00094119983,0.98872674,0.0002075702,0.005726562,0.001970956,0.0002283904],"about_ca_topic_score_codex":0.000041235755,"about_ca_topic_score_gemma":0.000008155375,"teacher_disagreement_score":0.51292866,"about_ca_system_score_codex":0.00061564107,"about_ca_system_score_gemma":0.00042554547,"threshold_uncertainty_score":0.7838399},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4231486013","doi":"10.1007/978-1-4614-6170-8_110113","title":"Automatic Document Topic Identification","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Information retrieval; Natural language processing; Biology","score_opus":0.010640889070436843,"score_gpt":0.2615044887871174,"score_spread":0.25086359971668054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231486013","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013459252,0.000049282375,0.6509895,0.00025966717,0.000086356325,0.00012457711,1.743704e-7,0.00068770396,0.34780142],"genre_scores_gemma":[0.0038235455,0.000047902555,0.1333153,0.00027381326,0.0000697911,0.000020939779,0.00000915571,0.000018856623,0.8624207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856365,0.0000132140885,0.00042966587,0.0004873972,0.00036343708,0.00014266603],"domain_scores_gemma":[0.9981107,0.00004565429,0.000305631,0.0013947523,0.00008850308,0.00005477097],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020876966,0.00022042256,0.0002865249,0.00021606799,0.00005646667,0.00017578677,0.0010825181,0.00014810365,0.000547323],"category_scores_gemma":[0.0000125050265,0.0001981831,0.0001499766,0.00004106802,0.000031027466,0.00023142935,0.00027368413,0.000143677,0.00096111436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.2510514e-8,0.0000015591735,3.7249845e-7,0.000010739699,0.000016025644,0.0000013956646,0.000011478552,0.0000010482959,0.000020504429,0.77886164,0.0018963999,0.21917881],"study_design_scores_gemma":[0.000039602368,0.000021652939,0.000017694723,0.000050461684,0.000029766916,0.0000039480046,3.6340185e-7,0.009524558,0.00084297586,0.7532469,0.2359248,0.00029728955],"about_ca_topic_score_codex":0.0000039404736,"about_ca_topic_score_gemma":0.000007909453,"teacher_disagreement_score":0.51767415,"about_ca_system_score_codex":0.0001162622,"about_ca_system_score_gemma":0.000025247156,"threshold_uncertainty_score":0.9998168},"labels":[],"label_agreement":null},{"id":"W4231667695","doi":"10.2196/preprints.16891","title":"Using the Kano Model to Display the Association between Percentages of Keywords within Abstracts and Article Citations: A Bibliometric Study for JMIR Journals (Preprint)","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citation; Association (psychology); Library science; Odds; Medicine; Psychology; Computer science; Logistic regression","score_opus":0.10961414235828783,"score_gpt":0.4221488472155437,"score_spread":0.3125347048572559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231667695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4778483,0.000049787024,0.5200799,0.00038783695,0.000030444278,0.0015143672,0.000007880413,0.000042645177,0.000038819075],"genre_scores_gemma":[0.8437512,0.00002524204,0.15582912,0.00008421497,0.000032485375,0.00016499915,0.0000012473952,0.000013006447,0.00009848649],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975315,0.00018150143,0.00077320944,0.00052619335,0.0007469881,0.00024065933],"domain_scores_gemma":[0.9961064,0.0012245156,0.0009885626,0.0010231361,0.0005898975,0.00006747241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037259615,0.00020858871,0.000408501,0.0046827565,0.00022106495,0.00063165976,0.0013042495,0.0001187027,0.0000021888898],"category_scores_gemma":[0.0007199445,0.00012534231,0.00014762835,0.008663279,0.000027039941,0.00047041132,0.0014507533,0.00039153144,0.0000018880493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000111658055,0.00028664668,0.26875436,0.00006484038,0.00057720445,4.0984625e-7,0.01314528,0.70297873,0.002560922,0.0018688205,0.00015410467,0.009597497],"study_design_scores_gemma":[0.00022095194,0.000086100816,0.3831618,0.00009148195,0.00019013495,7.8773724e-7,0.0010312668,0.58659965,0.0023739634,0.026009023,0.000006170812,0.00022867593],"about_ca_topic_score_codex":0.00010019539,"about_ca_topic_score_gemma":0.000057536916,"teacher_disagreement_score":0.36590293,"about_ca_system_score_codex":0.00019973166,"about_ca_system_score_gemma":0.00011067379,"threshold_uncertainty_score":0.60911095},"labels":[],"label_agreement":null},{"id":"W4233701208","doi":"10.1007/978-1-4939-7131-2_101352","title":"Time-Sensitive Recommendation","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.01645824349576573,"score_gpt":0.2625762804319835,"score_spread":0.24611803693621775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233701208","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5113417e-7,0.0000036806425,0.4785004,0.00025201292,0.000038977643,0.00006742012,0.0000018143769,0.00043024853,0.5207053],"genre_scores_gemma":[0.000035295096,0.000027852722,0.2138873,0.00057323603,0.00013040786,0.0000027180947,0.000045991044,0.000022034397,0.78527516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891526,0.000012992842,0.00023620266,0.00051542185,0.00017524896,0.00014489204],"domain_scores_gemma":[0.99878234,0.00006221986,0.00021068894,0.0006576518,0.00023349897,0.000053585925],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014961895,0.00023133203,0.00026691862,0.00021557651,0.00006127743,0.000063043044,0.0004991354,0.0001933217,0.003519446],"category_scores_gemma":[0.00001275439,0.0002151308,0.0001292072,0.00004630855,0.00008137412,0.0003513652,0.00035995975,0.00016641869,0.0056142434],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022403774,0.000008967477,9.339788e-8,0.0000035314015,0.000092811555,0.000011134128,0.00010131131,5.0018076e-7,0.000116082556,0.62759686,0.15805334,0.21401311],"study_design_scores_gemma":[0.00004206515,0.000071289105,5.406352e-7,0.0000338703,0.000021612424,0.000008680278,0.0000012117696,0.006218171,0.0026104061,0.24685462,0.74376315,0.0003743623],"about_ca_topic_score_codex":0.0000019103384,"about_ca_topic_score_gemma":0.000006600047,"teacher_disagreement_score":0.5857098,"about_ca_system_score_codex":0.00009958598,"about_ca_system_score_gemma":0.00003121518,"threshold_uncertainty_score":0.99739146},"labels":[],"label_agreement":null},{"id":"W4235659173","doi":"10.4018/9781605661728.ch009.ch000","title":"A Model for Estimating the Savings from Dimensional vs. Keyword Search","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Metadata; Computer science; Zipf's law; Process (computing); Keyword search; Information retrieval; Search cost; Search engine; Data mining; World Wide Web; Economics; Mathematics; Statistics; Microeconomics","score_opus":0.04719463325982439,"score_gpt":0.2919141828493511,"score_spread":0.2447195495895267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235659173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002454286,0.00010034054,0.7546495,0.00013938974,0.00011565156,0.0004387106,0.00008553575,0.0003722846,0.244074],"genre_scores_gemma":[0.029003305,0.0000012247051,0.9367914,0.001271093,0.00021662463,0.00008293949,0.000009423212,0.000055749013,0.032568194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751925,0.000020880674,0.0004703423,0.00090162834,0.0006292832,0.00045862046],"domain_scores_gemma":[0.99773616,0.0001927733,0.0003097942,0.0013438017,0.0002807041,0.00013674694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027476836,0.00047444156,0.0005222316,0.00007444656,0.0002991728,0.00017745272,0.0021144387,0.0003060128,0.000010861592],"category_scores_gemma":[0.000036550085,0.00036611696,0.00040551263,0.000031568896,0.00017074478,0.00016202434,0.001149499,0.00041236446,0.000050456467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017187656,0.0000063783964,0.0000016358001,0.000007917402,0.00008634826,0.000008569024,0.00018104972,0.0006954222,0.00002407053,0.9660546,0.001709682,0.031207118],"study_design_scores_gemma":[0.000082395156,0.00003032589,0.0000014734311,0.000094397685,0.000044933793,0.000005073013,4.819552e-7,0.40509754,0.000060940412,0.593389,0.0009478256,0.0002456088],"about_ca_topic_score_codex":0.00022080757,"about_ca_topic_score_gemma":0.00011296307,"teacher_disagreement_score":0.40440214,"about_ca_system_score_codex":0.0002295951,"about_ca_system_score_gemma":0.0002599021,"threshold_uncertainty_score":0.99987906},"labels":[],"label_agreement":null},{"id":"W4236185729","doi":"10.1007/978-1-4614-6170-8_100575","title":"Time-Sensitive Recommendation","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.01281652761943931,"score_gpt":0.2481755232703999,"score_spread":0.2353589956509606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236185729","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.8384243e-8,0.0000032384114,0.5065041,0.0003674781,0.000029322611,0.00005925864,9.630066e-7,0.00040968563,0.49262586],"genre_scores_gemma":[0.00012365551,0.000026845119,0.18043488,0.0008384672,0.00008787342,0.0000031888083,0.000051071213,0.000023817604,0.8184102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893177,0.000017750443,0.00024461796,0.00049181783,0.00017428481,0.00013975338],"domain_scores_gemma":[0.9988145,0.00009765535,0.00022360221,0.00065621774,0.00015255627,0.000055437155],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017873896,0.00023447956,0.00030937564,0.00021130747,0.00005333969,0.00005881811,0.0004809784,0.00018940859,0.000743824],"category_scores_gemma":[0.000014880641,0.00021883684,0.00014166233,0.000036953432,0.000044863107,0.00019243779,0.0002940973,0.00020284172,0.0026322745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.512092e-7,0.0000019831664,4.350695e-8,0.0000018032808,0.000026515934,0.0000025921506,0.000012488457,0.0000014439888,0.000036251662,0.7359542,0.020112246,0.24384984],"study_design_scores_gemma":[0.000045092085,0.00004542304,6.3762224e-7,0.000030707073,0.000020641071,0.0000071182126,4.0617925e-7,0.01494816,0.0012374255,0.1504814,0.8328153,0.00036768423],"about_ca_topic_score_codex":0.0000023161654,"about_ca_topic_score_gemma":0.000004928867,"teacher_disagreement_score":0.8127031,"about_ca_system_score_codex":0.0000846099,"about_ca_system_score_gemma":0.000022186341,"threshold_uncertainty_score":0.99814427},"labels":[],"label_agreement":null},{"id":"W4236530352","doi":"10.32920/ryerson.14649648","title":"Fuzzy Thesauri Recommendation System For Web 2.0 Social networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; World Wide Web; The Internet; Scalability; Set (abstract data type); Node (physics); Social network (sociolinguistics); Recommender system; Order (exchange); Database; Social media","score_opus":0.026919574988326124,"score_gpt":0.30151589840289234,"score_spread":0.2745963234145662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236530352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013953498,0.00007991564,0.98374975,0.0015283334,0.0007652893,0.0005355949,0.0000066099583,0.0014891934,0.011705791],"genre_scores_gemma":[0.5358954,0.00003674361,0.4623083,0.00024209877,0.00054526655,0.00040150233,0.00023730194,0.000027993032,0.00030539688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979655,0.00014460002,0.00048885675,0.0008805892,0.00019777656,0.0003226523],"domain_scores_gemma":[0.99826765,0.00014674346,0.00040997352,0.00079062476,0.00032983243,0.00005515006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057488785,0.00029246358,0.0005183459,0.00015158551,0.00021056585,0.00053294085,0.0012546064,0.0003997933,0.000014855495],"category_scores_gemma":[0.000027868491,0.0002836385,0.00041814486,0.00029430052,0.000021597694,0.00032262708,0.0017876634,0.00040023177,0.000004192518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013770255,0.00014693863,0.00007037672,0.0005585473,0.00049231783,0.000011093644,0.0006482521,0.004172554,0.00038324005,0.39593366,0.02585069,0.5717186],"study_design_scores_gemma":[0.000286092,0.000035542645,0.00008305132,0.00019325681,0.00011086296,0.0000069391517,0.00025001244,0.96042025,0.0017803737,0.02477045,0.011194274,0.0008688724],"about_ca_topic_score_codex":0.00002105985,"about_ca_topic_score_gemma":0.00005055467,"teacher_disagreement_score":0.95624775,"about_ca_system_score_codex":0.00031712663,"about_ca_system_score_gemma":0.00015550759,"threshold_uncertainty_score":0.99996156},"labels":[],"label_agreement":null},{"id":"W4238322342","doi":"10.31234/osf.io/svmtd","title":"The Semantic Librarian: A Search Engine Built from Vector-Space Models of Semantics","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Semantics (computer science); Space (punctuation); Computer science; Cognition; Semantic space; Information retrieval; World Wide Web; Cognitive science; Artificial intelligence; Psychology; Programming language","score_opus":0.031083942001109043,"score_gpt":0.281068873984278,"score_spread":0.24998493198316896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238322342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037747873,0.0010179913,0.98769486,0.0037051626,0.0003080365,0.00056092185,0.000012010288,0.0005944877,0.0023317474],"genre_scores_gemma":[0.69858503,0.0006504519,0.29910627,0.00005855157,0.00008317595,0.000022476486,0.000015650616,0.00003619785,0.0014421837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690175,0.00018715396,0.0006063572,0.0009686338,0.0008604565,0.00047563296],"domain_scores_gemma":[0.99431455,0.0007752475,0.0003556286,0.0041480972,0.00030186938,0.000104597166],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052187394,0.0004212303,0.00074393733,0.00023540352,0.000104404506,0.00041829076,0.004820498,0.0003365835,0.000018220157],"category_scores_gemma":[0.00006117978,0.0003008927,0.000353878,0.00053006376,0.00012372047,0.0005651642,0.006501568,0.0009509806,0.000037850637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002144053,0.00019622619,0.000402424,0.00028734386,0.0008420343,0.000026952252,0.0017235207,0.3224166,0.0030222489,0.6535135,0.0036774103,0.013870326],"study_design_scores_gemma":[0.000087683795,0.000028020162,0.00011047786,0.00012930861,0.000039277817,0.0000011457104,0.000022941553,0.809734,0.021736864,0.16745311,0.0003619399,0.00029525466],"about_ca_topic_score_codex":0.00069627014,"about_ca_topic_score_gemma":0.00006469607,"teacher_disagreement_score":0.6948103,"about_ca_system_score_codex":0.000070883565,"about_ca_system_score_gemma":0.0003369992,"threshold_uncertainty_score":0.9999443},"labels":[],"label_agreement":null},{"id":"W4239379014","doi":"10.4018/9781591405573.ch105","title":"Hierarchical Document Clustering","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Document clustering; Cluster analysis; Hierarchy; Hierarchical clustering; Computer science; Directory; Information retrieval; Tree (set theory); Subject (documents); Similarity (geometry); Complete-linkage clustering; Cluster (spacecraft); Fuzzy clustering; Artificial intelligence; World Wide Web; Canopy clustering algorithm; Mathematics; Combinatorics","score_opus":0.02025228869145076,"score_gpt":0.26863962020140814,"score_spread":0.24838733150995737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239379014","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012643159,0.00010611706,0.41736346,0.00003693134,0.00014234103,0.00015169905,0.000004651903,0.00053631084,0.58165723],"genre_scores_gemma":[0.084769025,0.00004743769,0.4998452,0.002107991,0.0006397279,0.00009365625,0.000005778049,0.00015147713,0.4123397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976413,0.000022156115,0.0004920561,0.0008749492,0.0005240881,0.0004454238],"domain_scores_gemma":[0.9979175,0.000026054624,0.00027137672,0.0014658523,0.000093582865,0.00022564942],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014022073,0.0005055546,0.0005475691,0.00013109221,0.00010309104,0.00016002075,0.0018667108,0.00036606236,0.00004765934],"category_scores_gemma":[0.000009006889,0.0004927001,0.00035154665,0.000029726156,0.00012310366,0.00017165205,0.0015198871,0.00044354564,0.00029560772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005155928,0.0000043624905,0.0000012594178,0.00000981099,0.00006201008,0.000096916316,0.000038080037,0.00000184203,0.000008279593,0.92994684,0.000541814,0.06928363],"study_design_scores_gemma":[0.000099268844,0.000079838974,0.0000045769716,0.0001109484,0.000035899167,0.000052111416,3.612231e-7,0.00016166443,0.00014592615,0.93787444,0.060951646,0.0004832983],"about_ca_topic_score_codex":0.000037702335,"about_ca_topic_score_gemma":0.000067489185,"teacher_disagreement_score":0.16931753,"about_ca_system_score_codex":0.00035828125,"about_ca_system_score_gemma":0.00011473713,"threshold_uncertainty_score":0.99975246},"labels":[],"label_agreement":null},{"id":"W4239534043","doi":"10.1007/978-1-4939-7131-2_101211","title":"Social Trends Discovery","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data science; Computer science","score_opus":0.023970749127788078,"score_gpt":0.2956227825873088,"score_spread":0.2716520334595207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239534043","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.7960638e-7,0.000025005065,0.44083324,0.00023490816,0.000048814385,0.000020515228,0.0000018892335,0.00042637065,0.558409],"genre_scores_gemma":[0.0005224201,0.000020790936,0.049492955,0.0003075292,0.0004807276,0.0000043572704,0.000013426658,0.000029273475,0.9491285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985981,0.0000071230697,0.00025439152,0.0005765981,0.00035440573,0.00020939056],"domain_scores_gemma":[0.9989322,0.000022879276,0.00019016393,0.00073143595,0.00007914878,0.000044214656],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008357978,0.00029010698,0.00035558591,0.0003340098,0.00011134885,0.00020544694,0.0012246418,0.0002563637,0.0009448623],"category_scores_gemma":[0.000003315876,0.0002514653,0.00032170487,0.000081577615,0.0001325559,0.00071365095,0.00058920245,0.00020571354,0.00038346343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.84031e-7,0.0000040944906,3.0413383e-7,0.0000018430474,0.000034369972,0.0000070072933,0.000039688985,4.272687e-8,0.000007465849,0.8661911,0.06831848,0.06539493],"study_design_scores_gemma":[0.000037597838,0.000035400848,0.000004730661,0.000011540428,0.000021454005,0.0000028285972,5.886477e-7,0.00012233235,0.00018775041,0.45339793,0.54585505,0.00032277335],"about_ca_topic_score_codex":0.0000032001165,"about_ca_topic_score_gemma":0.000025328032,"teacher_disagreement_score":0.4775366,"about_ca_system_score_codex":0.00008488089,"about_ca_system_score_gemma":0.0000373849,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W4242274911","doi":"10.1002/asi.1101","title":"User preferences in the classification of electronic bookmarks: Implications for a shared system","year":2001,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Computer science; Context (archaeology); The Internet; World Wide Web; Documentation; Sample (material); Information retrieval; Artificial intelligence","score_opus":0.018552468412853438,"score_gpt":0.3082505032618173,"score_spread":0.28969803484896384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242274911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17791995,0.00005601559,0.80867296,0.012696781,0.000024778123,0.00047287604,0.000004369089,0.000034453904,0.00011780318],"genre_scores_gemma":[0.96336144,0.00011006216,0.03613846,0.0003049411,0.000006946927,0.000073181734,4.3849374e-7,0.0000013133555,0.0000031860084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999044,0.0000138509,0.00043183097,0.000084594954,0.00024567812,0.00018003561],"domain_scores_gemma":[0.997446,0.00011912138,0.0012147164,0.0003331152,0.00087174634,0.000015306294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016086387,0.000058846992,0.0001595543,0.00028976912,0.00022335062,0.00007698849,0.0016685091,0.00003203092,8.974283e-8],"category_scores_gemma":[0.0002454409,0.00003348912,0.00011972439,0.0031025612,0.0006270936,0.0018078381,0.000087661916,0.00011824067,1.0957451e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017597818,0.000039048784,0.0060972753,0.00002987664,0.000035623347,2.0157676e-8,0.0017264881,0.000050818675,0.008576924,0.8146317,0.0015503954,0.16724423],"study_design_scores_gemma":[0.002442497,0.0029977523,0.27451155,0.00028797274,0.00022963776,0.00066929974,0.06411948,0.2036648,0.01195646,0.2614478,0.17691655,0.00075619214],"about_ca_topic_score_codex":0.0000042274432,"about_ca_topic_score_gemma":0.000004426876,"teacher_disagreement_score":0.7854415,"about_ca_system_score_codex":0.000142846,"about_ca_system_score_gemma":0.00027969322,"threshold_uncertainty_score":0.31005326},"labels":[],"label_agreement":null},{"id":"W4243718109","doi":"10.1007/978-1-4939-7131-2_100365","title":"Exemplar-Based Topic Detection","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.016549681423278943,"score_gpt":0.24968843038963545,"score_spread":0.2331387489663565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243718109","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014700717,0.00002759842,0.60433084,0.00009116062,0.00009989044,0.00008201939,4.7650283e-7,0.0006081684,0.3947584],"genre_scores_gemma":[0.0038181902,0.000013519443,0.18307975,0.00059077766,0.00023659151,0.000014682261,0.0000046588702,0.000034058066,0.81220776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987498,0.000009210235,0.00024154922,0.0005383266,0.00028645695,0.00017464369],"domain_scores_gemma":[0.99853677,0.00003182839,0.00015999528,0.0010904819,0.000119623954,0.00006131631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103802944,0.00025052758,0.00025688816,0.0002697841,0.000081065606,0.00008281574,0.0007980857,0.00025927514,0.0008007711],"category_scores_gemma":[0.000009837451,0.00022935185,0.0001831763,0.000060478644,0.000045622863,0.00021796755,0.00018271508,0.00019961309,0.0005203759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049645623,0.000020506555,0.0000025536006,0.000028237271,0.00007966176,0.00004364933,0.000043577722,0.0000058126648,0.0016684367,0.64307624,0.009584127,0.34544224],"study_design_scores_gemma":[0.00008665032,0.000140086,0.0000034286338,0.00004294356,0.000026287078,0.000007644828,4.938515e-7,0.0037448343,0.035030108,0.2907014,0.66977465,0.00044145933],"about_ca_topic_score_codex":0.0000061878627,"about_ca_topic_score_gemma":0.00010729609,"teacher_disagreement_score":0.6601905,"about_ca_system_score_codex":0.00011725814,"about_ca_system_score_gemma":0.00004689893,"threshold_uncertainty_score":0.93526965},"labels":[],"label_agreement":null},{"id":"W4244554860","doi":"10.1007/978-1-4614-6170-8_100407","title":"Topic Identification","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Biology; Botany","score_opus":0.013984898188822318,"score_gpt":0.2539511684350372,"score_spread":0.23996627024621486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244554860","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0816209e-7,0.000035337984,0.5404519,0.00014877923,0.00005421886,0.00004661781,1.6573267e-7,0.0003449612,0.45891795],"genre_scores_gemma":[0.0013042368,0.00004710039,0.07377354,0.0002508327,0.00008376597,0.00000606196,0.0000071675395,0.000013411649,0.9245139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990062,0.0000062407803,0.0002552841,0.0004071636,0.0002256095,0.000099476274],"domain_scores_gemma":[0.99852407,0.000028190516,0.00018353073,0.0011355373,0.00009093769,0.00003770966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012105495,0.00015427773,0.00019529068,0.00016035713,0.0000404181,0.000094081,0.00093318,0.0001443202,0.00017829999],"category_scores_gemma":[0.000009723175,0.0001425677,0.00011824238,0.000029190847,0.000025797592,0.00014900276,0.00020283631,0.00013128614,0.00075761793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.8571914e-8,9.41696e-7,5.038395e-7,0.0000030695635,0.000008007426,9.84101e-7,0.000004687499,5.8816994e-7,0.000043585605,0.87634397,0.0029090906,0.12068454],"study_design_scores_gemma":[0.000015559794,0.000008554895,0.000007834737,0.0000118283615,0.000009438676,0.0000017938905,9.57805e-8,0.001012593,0.0008116484,0.4793622,0.5185996,0.00015884884],"about_ca_topic_score_codex":0.0000022095148,"about_ca_topic_score_gemma":0.0000070472115,"teacher_disagreement_score":0.5156905,"about_ca_system_score_codex":0.00004530235,"about_ca_system_score_gemma":0.000015583213,"threshold_uncertainty_score":0.9737899},"labels":[],"label_agreement":null},{"id":"W4244585827","doi":"10.3410/f.726430947.793521386","title":"Faculty Opinions recommendation of Organizing conceptual knowledge in humans with a gridlike code.","year":2016,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"","keywords":"Code (set theory); Computer science; World Wide Web; Knowledge management; Data science; Programming language","score_opus":0.03418532190945529,"score_gpt":0.3600720609278439,"score_spread":0.3258867390183886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244585827","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.51396e-7,0.00080931495,0.008412632,0.08025841,0.00032802048,0.001067447,0.908941,0.00010623715,0.00007671437],"genre_scores_gemma":[0.000019021389,0.000293474,0.0078133065,0.0014794754,0.00015410327,0.00023453507,0.98947924,0.000027877202,0.00049896823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949316,0.0005794655,0.0017551566,0.0010079578,0.0012832164,0.00044260232],"domain_scores_gemma":[0.9893626,0.0002487388,0.0018774366,0.0023574398,0.005918718,0.0002350396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014604261,0.0005981629,0.0011992222,0.00070162304,0.0002218022,0.0001467439,0.003972686,0.0005699679,0.00015091902],"category_scores_gemma":[0.0028134775,0.00034319525,0.00040623045,0.0042678225,0.00060041394,0.0009472159,0.0011316901,0.0010230985,0.000035351513],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048104093,0.00030343217,0.0000089955165,0.0014824084,0.000079402984,4.4916436e-7,0.00028596882,6.578503e-8,0.0000029673065,0.0034004583,0.99195725,0.0024738214],"study_design_scores_gemma":[0.00060989155,0.0001441514,0.00038900922,0.0133000575,0.00007627068,0.000017401195,0.000033092467,0.00001398487,0.00005162769,0.0000982065,0.98486525,0.00040107252],"about_ca_topic_score_codex":0.000029657089,"about_ca_topic_score_gemma":0.00006783322,"teacher_disagreement_score":0.080538265,"about_ca_system_score_codex":0.00024871228,"about_ca_system_score_gemma":0.0006435906,"threshold_uncertainty_score":0.999902},"labels":[],"label_agreement":null},{"id":"W4245167715","doi":"10.1353/scp.0.0082","title":"Academic Search Engine Optimization ( ASEO ): Optimizing Scholarly Literature for Google Scholar &amp; Co.","year":2010,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Computer science; Information retrieval; Mathematics; Artificial intelligence","score_opus":0.031066419338067825,"score_gpt":0.3222108468978427,"score_spread":0.2911444275597749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245167715","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02974896,0.0017517911,0.9595239,0.0071914266,0.0007541754,0.00032952576,0.000016280117,0.00026605633,0.0004178634],"genre_scores_gemma":[0.070530824,0.00028157368,0.92674774,0.0009182465,0.0011160738,0.000015366177,0.000037755475,0.00006135825,0.00029103996],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949989,0.0002992934,0.0013492984,0.00064925343,0.0019539287,0.0007493578],"domain_scores_gemma":[0.9893008,0.0005157547,0.0011918081,0.0010197489,0.0073609753,0.0006109401],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.013935222,0.00038841838,0.0006024827,0.0020423513,0.0007692972,0.086746484,0.005178427,0.000913442,0.00002925353],"category_scores_gemma":[0.016809413,0.00035588993,0.0004369713,0.0025370137,0.000067379784,0.35957772,0.00054039655,0.014651058,0.000007667641],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003206318,0.0006311938,0.008652884,0.0002817841,0.00080009416,0.00020918545,0.0071632415,0.11234448,0.5295895,0.056394525,0.037473373,0.24613912],"study_design_scores_gemma":[0.01029006,0.0015027272,0.002966792,0.0028298516,0.0004789938,0.0034186938,0.000706518,0.26712322,0.11905401,0.050327737,0.5371332,0.004168151],"about_ca_topic_score_codex":0.000004997771,"about_ca_topic_score_gemma":0.0000025393995,"teacher_disagreement_score":0.49965987,"about_ca_system_score_codex":0.00026657697,"about_ca_system_score_gemma":0.000482619,"threshold_uncertainty_score":0.9998893},"labels":[{"model":"gemma","categories":["scholarly_communication"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["scholarly_communication"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4246171214","doi":"10.1007/978-1-4614-6170-8_100791","title":"Social Trends Discovery","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data science; Computer science","score_opus":0.018764718986644377,"score_gpt":0.28038641787090857,"score_spread":0.2616216988842642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246171214","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.714433e-8,0.000020898353,0.49752447,0.00032632175,0.00003476194,0.000017108076,9.4734526e-7,0.00038561804,0.5016898],"genre_scores_gemma":[0.0017822806,0.000019184838,0.037847646,0.00043169258,0.00030928297,0.000004906058,0.000014317754,0.000030339796,0.95956033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986223,0.0000097747225,0.00026357576,0.0005499735,0.0003524603,0.00020189802],"domain_scores_gemma":[0.99893475,0.00003613232,0.00020196033,0.0007298254,0.000051537852,0.0000457754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010020951,0.00029411435,0.00041275335,0.00032761204,0.000096694464,0.00019164769,0.0011801632,0.00025114257,0.00019776452],"category_scores_gemma":[0.000003879634,0.00025585052,0.00035315563,0.00006490236,0.000072541574,0.00038964796,0.00048053826,0.00025150098,0.00017897767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9647952e-7,0.0000021301976,3.3794274e-7,0.0000022267218,0.000023115437,0.0000038437506,0.000011467021,2.976912e-7,0.0000055127275,0.8046485,0.020699898,0.17460227],"study_design_scores_gemma":[0.000043836164,0.000024356212,0.000006101776,0.000011346417,0.000022257225,0.0000025128904,2.128898e-7,0.0003252933,0.00009638806,0.34164405,0.65747905,0.00034460516],"about_ca_topic_score_codex":0.000003873541,"about_ca_topic_score_gemma":0.00001886512,"teacher_disagreement_score":0.6367791,"about_ca_system_score_codex":0.000071831215,"about_ca_system_score_gemma":0.000026464197,"threshold_uncertainty_score":0.9999894},"labels":[],"label_agreement":null},{"id":"W4246558970","doi":"10.36227/techrxiv.12100692","title":"Deep Learning for text in limted data settings","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Sequence (biology); Deep learning; Transfer of learning; Sequence learning; Natural language processing; Recurrent neural network; Machine learning; Sentiment analysis; Artificial neural network","score_opus":0.05509319530841789,"score_gpt":0.34010155808589826,"score_spread":0.2850083627774804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246558970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007525236,0.00016086618,0.9929267,0.0037598172,0.000069568356,0.00047222903,0.0000034437655,0.0011515529,0.0013805632],"genre_scores_gemma":[0.09836517,0.000065546585,0.9000415,0.0007087291,0.00007954457,0.000096478194,0.00029174838,0.000027515103,0.00032377505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974372,0.00007581031,0.00045247152,0.0014720412,0.00024385187,0.0003186433],"domain_scores_gemma":[0.9971873,0.00025711703,0.00028292811,0.002098339,0.00009452134,0.00007975684],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00053250504,0.000265936,0.00046322984,0.00024085166,0.00006213163,0.0002499164,0.0050995783,0.00020553239,0.000014844676],"category_scores_gemma":[0.00068724935,0.00026619592,0.00010618882,0.00048008308,0.000025386506,0.00048534817,0.011406377,0.00087044237,0.000023487595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023200822,0.00015034399,0.0014878984,0.0005500279,0.00020954163,0.000063750456,0.0020389503,0.019733181,0.001540986,0.046187364,0.013754751,0.91426],"study_design_scores_gemma":[0.00010934352,0.000025881658,0.00012385081,0.000062608124,0.000014336763,0.0000010875514,0.000025748364,0.94292706,0.00069550704,0.037288155,0.01841177,0.00031463103],"about_ca_topic_score_codex":0.000058311285,"about_ca_topic_score_gemma":0.000099858415,"teacher_disagreement_score":0.9231939,"about_ca_system_score_codex":0.00007906302,"about_ca_system_score_gemma":0.00008520015,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W4246957940","doi":"10.1002/asi.21222","title":"Individual differences in the interpretation of text: Implications for information science","year":2009,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretation (philosophy); Computer science; Meaning (existential); Cohesion (chemistry); Natural language processing; Linguistics; Search engine indexing; Information retrieval; Artificial intelligence; Psychology","score_opus":0.013594081527149957,"score_gpt":0.3118840206932907,"score_spread":0.2982899391661407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246957940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19534509,0.000020427171,0.7865559,0.017489033,0.000046753146,0.00040562946,0.0000070510005,0.000026497226,0.000103611725],"genre_scores_gemma":[0.93188137,0.000046497273,0.066613965,0.0014308459,0.0000059972003,0.000019720557,5.1006634e-7,6.804459e-7,4.4188474e-7],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986099,0.000010653072,0.00057257136,0.00008350987,0.0005272306,0.00019613026],"domain_scores_gemma":[0.9965479,0.00015570366,0.0014967108,0.0003152906,0.0014588278,0.000025610096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027383773,0.00007510768,0.00018377707,0.0008004019,0.00040167634,0.00021846188,0.002572218,0.000031759413,6.0262565e-8],"category_scores_gemma":[0.0009842339,0.000043535456,0.000115662624,0.0060247756,0.0018805503,0.008082084,0.00014703812,0.00014114183,1.4392657e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009863696,0.000026975793,0.0021234693,0.0000083722,0.000009794351,6.976539e-9,0.0063116024,0.000060651495,0.0027650814,0.23262206,0.00028243134,0.7557797],"study_design_scores_gemma":[0.0015280793,0.003193871,0.4580285,0.00014246786,0.00011205925,0.00017612182,0.029440189,0.13874371,0.022337716,0.33737049,0.008395646,0.0005311701],"about_ca_topic_score_codex":0.0000025970476,"about_ca_topic_score_gemma":8.7287344e-7,"teacher_disagreement_score":0.7552485,"about_ca_system_score_codex":0.00008906281,"about_ca_system_score_gemma":0.00038322408,"threshold_uncertainty_score":0.6928966},"labels":[],"label_agreement":null},{"id":"W4247024223","doi":"10.22360/springsim.2017.cns.009","title":"A Comparative Study On Content-Based Papepr-To-Paper Recommendation Approaches in Scientific Literature","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); tf–idf; Word embedding; Word (group theory); Domain (mathematical analysis); Representation (politics); Term (time); Recommender system; Embedding; Data mining; Artificial intelligence; Mathematics","score_opus":0.20708297861746142,"score_gpt":0.37094591894310536,"score_spread":0.16386294032564394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247024223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2766084,0.000015392297,0.70130175,0.006018193,0.00024806726,0.0016903459,0.000004992656,0.00041096378,0.013701867],"genre_scores_gemma":[0.93173003,2.3036573e-7,0.06712158,0.000409011,0.0000134146585,0.00012579525,0.000011063832,0.000005701785,0.0005831811],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983279,0.0001450608,0.00026225412,0.000759902,0.00027130375,0.000233543],"domain_scores_gemma":[0.99807817,0.000079409096,0.00016468915,0.001467037,0.00013107395,0.000079626625],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00069166813,0.00018064522,0.00028106777,0.0003924106,0.0004561333,0.0015620558,0.0013192373,0.00004592517,0.00001730242],"category_scores_gemma":[0.00009276406,0.00014273112,0.00006004148,0.00051948766,0.000068414956,0.001317869,0.00027314224,0.00019276356,0.000054822074],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054538075,0.018463539,0.14252797,0.00006581022,0.00037863792,0.00017506909,0.0797495,0.002368785,0.047843877,0.23643145,0.008714975,0.46273503],"study_design_scores_gemma":[0.0065661822,0.0030786477,0.5757176,0.00055509235,0.00005346355,0.000004287626,0.0071462165,0.24028608,0.13968325,0.012515213,0.011747956,0.0026459927],"about_ca_topic_score_codex":0.000028584136,"about_ca_topic_score_gemma":0.0005585778,"teacher_disagreement_score":0.6551216,"about_ca_system_score_codex":0.00008323067,"about_ca_system_score_gemma":0.000031689102,"threshold_uncertainty_score":0.9994744},"labels":[],"label_agreement":null},{"id":"W4247874641","doi":"10.1016/b0-08-044854-2/00963-9","title":"Indexing, Automatic","year":2006,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Search engine indexing; Computer science; Automatic indexing; Information retrieval; Index (typography); Vocabulary; Task (project management); Natural language processing; World Wide Web; Linguistics","score_opus":0.010951203903698793,"score_gpt":0.24686742240760456,"score_spread":0.23591621850390576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247874641","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012451505,0.00050873874,0.05741947,0.000048369406,0.00013379905,0.00032482183,0.0000032192675,0.001322969,0.94023734],"genre_scores_gemma":[0.00015516444,0.000015348429,0.09448056,0.00031770545,0.00015960452,0.00003604934,0.000011311355,0.000072206494,0.9047521],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99757296,0.000024468607,0.0006204136,0.0007687382,0.0005875767,0.0004258574],"domain_scores_gemma":[0.9974655,0.00006376364,0.0004978978,0.0017344244,0.00011803674,0.000120413424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025339363,0.0005309442,0.00067340455,0.0004191636,0.00012396384,0.00016700641,0.0016933376,0.00036918488,0.00009038922],"category_scores_gemma":[0.000012854693,0.0005136382,0.00037881636,0.0000385507,0.00012109485,0.00018381298,0.00057124277,0.0005454661,0.00034977423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.0073847e-7,0.0000042465454,0.0000014137087,0.000025048677,0.000042265856,0.00004498124,0.000031840438,0.0000018217338,0.0000074973477,0.09262009,0.0012796712,0.9059409],"study_design_scores_gemma":[0.00006274493,0.000025198187,0.0000055742466,0.0002054649,0.000045088673,0.000015422282,1.9660865e-7,0.0011029175,0.00009944353,0.21708563,0.78088665,0.00046568055],"about_ca_topic_score_codex":6.441132e-7,"about_ca_topic_score_gemma":0.00001757668,"teacher_disagreement_score":0.90547526,"about_ca_system_score_codex":0.00019657753,"about_ca_system_score_gemma":0.00012907902,"threshold_uncertainty_score":0.99973154},"labels":[],"label_agreement":null},{"id":"W4247975909","doi":"10.1007/978-1-4614-6170-8_100216","title":"Content-Based Filtering","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.046991318907752676,"score_gpt":0.2502640339573551,"score_spread":0.2032727150496024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247975909","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0504753e-7,0.0000329022,0.5919513,0.00013825926,0.000049009792,0.00006587088,7.203158e-7,0.0006449091,0.4071168],"genre_scores_gemma":[0.0008332781,0.000009544662,0.3822581,0.0009958093,0.000057854497,0.000007990485,0.0000070695546,0.000028430266,0.61580193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870306,0.000008405843,0.00028867088,0.00051992823,0.00028410382,0.00019583892],"domain_scores_gemma":[0.9983497,0.00007357202,0.00019625894,0.0011895219,0.00011122264,0.00007967952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012193638,0.00028443572,0.00037764947,0.00022179105,0.0000494252,0.00009757811,0.0011691848,0.00017418462,0.00029068932],"category_scores_gemma":[0.00001391747,0.00025328255,0.0002316551,0.000029579687,0.000046919416,0.00012340548,0.00029357363,0.00020806961,0.00032655575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.681668e-7,0.0000022912993,0.0000010602338,0.00000900837,0.000019665493,0.000010416606,0.000002675593,0.000008242546,0.0003489707,0.9443824,0.0014161323,0.05379843],"study_design_scores_gemma":[0.00020238638,0.000106086554,0.0000035405646,0.0001909559,0.00003547985,0.000006595528,5.9884553e-7,0.019123532,0.014551571,0.08238228,0.88249475,0.00090225536],"about_ca_topic_score_codex":0.0000067827405,"about_ca_topic_score_gemma":0.000012277987,"teacher_disagreement_score":0.8810786,"about_ca_system_score_codex":0.00006092815,"about_ca_system_score_gemma":0.000031930012,"threshold_uncertainty_score":0.99999195},"labels":[],"label_agreement":null},{"id":"W4248679402","doi":"10.1016/j.jda.2004.04.010","title":"Editorial","year":2004,"lang":"es","type":"editorial","venue":"Journal of Discrete Algorithms","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.007218399082258171,"score_gpt":0.29535023212277245,"score_spread":0.28813183304051426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248679402","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005425033,0.001256583,0.3622487,0.00032746972,0.6355927,0.00016204613,0.00006271536,0.00008148687,0.0002629198],"genre_scores_gemma":[0.00013987397,0.0030530344,0.15322174,0.000032490218,0.8430799,0.0000067010837,0.000028640598,0.00010217984,0.00033543096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98909485,0.00033747323,0.0029461945,0.0009487039,0.0056681093,0.0010046607],"domain_scores_gemma":[0.98790884,0.00081008225,0.0054643694,0.0014354141,0.0037175063,0.0006637889],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0022794716,0.0010975652,0.0023619458,0.001142554,0.00031134952,0.00113732,0.0053875432,0.0017676058,0.00005480864],"category_scores_gemma":[0.0017631466,0.00092129805,0.0019310977,0.0012657514,0.00036156696,0.0027997915,0.0009135308,0.0043248525,0.000084498315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008859282,0.00017779162,0.00000439336,0.00007800443,0.0006040254,0.00026872146,0.00024984212,0.00028219956,0.00017234289,0.00058884267,0.97958136,0.017903887],"study_design_scores_gemma":[0.0018693542,0.0017934414,0.00000842702,0.0012151764,0.0006092833,0.00009996269,0.000035903002,0.00055592955,0.0009450436,0.018394545,0.97347766,0.0009952475],"about_ca_topic_score_codex":0.000092634655,"about_ca_topic_score_gemma":0.000006707265,"teacher_disagreement_score":0.20902693,"about_ca_system_score_codex":0.0012929699,"about_ca_system_score_gemma":0.0033344016,"threshold_uncertainty_score":0.9999938},"labels":[],"label_agreement":null},{"id":"W4248953021","doi":"10.4018/9781591406907.ch003.ch000","title":"Dominant Meanings Approach Towards Individualized Web Search for Learning Environments","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Meaning (existential); Computer science; Set (abstract data type); The Internet; Information retrieval; Resource (disambiguation); Search engine; World Wide Web; Semantic search; Web search query; Hypermedia; Psychology","score_opus":0.035756497399137215,"score_gpt":0.276887220525089,"score_spread":0.2411307231259518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248953021","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010939035,0.00011768025,0.46861765,0.000010178584,0.000059057755,0.0005444344,0.000026625044,0.00024675214,0.53036666],"genre_scores_gemma":[0.09691239,0.00006593876,0.6501446,0.00034918686,0.00026732316,0.0003539838,0.000045501383,0.00020084539,0.25166026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963518,0.00006436997,0.0006201533,0.0013161696,0.0009261184,0.0007214041],"domain_scores_gemma":[0.99800235,0.000049782542,0.000490747,0.0011295378,0.0000904954,0.0002370714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006235957,0.0006991918,0.000902498,0.00022439468,0.0002587243,0.0001846879,0.0022000796,0.0005690654,0.000019610192],"category_scores_gemma":[0.00002701678,0.0006705526,0.0005401715,0.000048290312,0.00020242712,0.00021048372,0.0013580124,0.0006253102,0.00008473848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025125926,0.000021138698,0.000008965721,0.00003208649,0.00019097143,0.00001631735,0.00029057948,0.000009345077,0.00016836029,0.92815,0.0002767619,0.07081037],"study_design_scores_gemma":[0.0012823185,0.00044896427,0.000014586394,0.00018446302,0.0002805013,0.00005963225,0.00001825434,0.0026512248,0.004822998,0.70971876,0.27893758,0.0015807083],"about_ca_topic_score_codex":0.00003946947,"about_ca_topic_score_gemma":0.000004667382,"teacher_disagreement_score":0.27870643,"about_ca_system_score_codex":0.00045327947,"about_ca_system_score_gemma":0.00022177273,"threshold_uncertainty_score":0.99957454},"labels":[],"label_agreement":null},{"id":"W4249665032","doi":"10.1007/978-1-4614-6170-8_110065","title":"Sentiment-Emotion-Intent Analysis","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sentiment analysis; Psychology; Natural language processing; Computer science","score_opus":0.013139370942909396,"score_gpt":0.2503086469972744,"score_spread":0.237169276054365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249665032","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.2288344e-7,0.00004382868,0.5765989,0.00021701986,0.000051015075,0.000081419006,0.000001260068,0.00052524934,0.422481],"genre_scores_gemma":[0.0024726377,0.00007394286,0.157833,0.00048612803,0.00007432855,0.00000768212,0.000041899424,0.000027228212,0.8389832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772555,0.000020445857,0.0005059011,0.0009002763,0.0005817455,0.0002660866],"domain_scores_gemma":[0.99729294,0.000058127487,0.00037464648,0.0019021416,0.00023937083,0.0001327876],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023430139,0.0004034193,0.0007293704,0.0010397272,0.000084364736,0.00015874814,0.0013961169,0.00023355916,0.0012174475],"category_scores_gemma":[0.0000109181865,0.00035846254,0.0009418146,0.00028491087,0.00005912052,0.00018449391,0.0005743534,0.0002596408,0.0008396623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.6201487e-7,0.000008791527,0.000014188358,0.0000048613674,0.0011515765,0.000008550577,0.000014119847,0.000071525326,0.000013855432,0.9673851,0.004415672,0.026911262],"study_design_scores_gemma":[0.00015411827,0.00009237376,0.000051041698,0.000062292725,0.0025106473,0.000008718917,0.0000025795482,0.0902782,0.0010083386,0.29101047,0.6134331,0.0013880666],"about_ca_topic_score_codex":0.00001626852,"about_ca_topic_score_gemma":0.00003570917,"teacher_disagreement_score":0.6763747,"about_ca_system_score_codex":0.0001363077,"about_ca_system_score_gemma":0.000025424382,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W4250002556","doi":"10.1007/978-1-4939-7131-2_100048","title":"Automatic Document Topic Identification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Information retrieval; Natural language processing; World Wide Web; Biology","score_opus":0.013628153498928994,"score_gpt":0.27614683076420066,"score_spread":0.26251867726527167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250002556","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005160888,0.000057937785,0.6176416,0.00018873627,0.0001178626,0.00014661285,3.3167987e-7,0.0007499454,0.3810918],"genre_scores_gemma":[0.0011678811,0.000049889768,0.16075815,0.00019171133,0.00010219084,0.000018086093,0.000008331828,0.000017607532,0.8376862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99855196,0.0000098172495,0.00041557493,0.0005096289,0.00036534242,0.00014765258],"domain_scores_gemma":[0.9980981,0.00002972096,0.00028880796,0.0013976723,0.00013271559,0.000053027652],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017623244,0.00021760375,0.0002489622,0.00022020692,0.00006444378,0.00018777772,0.0011213263,0.00015101423,0.0024038018],"category_scores_gemma":[0.000010796833,0.00019498615,0.00013739306,0.000050912753,0.00005469832,0.00041041325,0.00033173533,0.000118992946,0.0019793862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.049626e-8,0.0000036738575,4.31666e-7,0.000011411485,0.000029596074,0.0000031313502,0.000047171972,2.1407709e-7,0.000034781646,0.8769959,0.0077519054,0.115121655],"study_design_scores_gemma":[0.000032518525,0.000029178944,0.000013262172,0.000048604485,0.000027282736,0.0000041839107,9.021989e-7,0.003617555,0.0015049565,0.83125776,0.16319849,0.00026530703],"about_ca_topic_score_codex":0.0000032811631,"about_ca_topic_score_gemma":0.00001044347,"teacher_disagreement_score":0.45688346,"about_ca_system_score_codex":0.0001357972,"about_ca_system_score_gemma":0.000034945384,"threshold_uncertainty_score":0.9987977},"labels":[],"label_agreement":null},{"id":"W4250951234","doi":"10.32920/ryerson.14645355","title":"Microblog summarization based on sentiment and aspect analysis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Automatic summarization; Microblogging; Sentiment analysis; Social media; Computer science; Information retrieval; Baseline (sea); Cluster analysis; Multi-document summarization; Annotation; Data science; Natural language processing; Artificial intelligence; World Wide Web","score_opus":0.009684912507483769,"score_gpt":0.263804563741241,"score_spread":0.25411965123375724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250951234","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020731548,0.000097831566,0.99356055,0.0006950179,0.00006007805,0.00017362734,0.0000031479576,0.00043359655,0.0029029828],"genre_scores_gemma":[0.4978348,0.000056015684,0.5009136,0.0005385749,0.000017251432,0.000025458145,0.00017133572,0.0000103285965,0.00043264084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979254,0.00012638752,0.00032382214,0.0010847581,0.00034829756,0.00019135971],"domain_scores_gemma":[0.99799824,0.000081777114,0.00021509988,0.0014704688,0.00015836352,0.0000760464],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025817545,0.00027586566,0.00049054454,0.0007929966,0.000072911316,0.000512609,0.00063242414,0.00017432777,0.0000862262],"category_scores_gemma":[0.000028223607,0.00026184038,0.00031731676,0.0012108175,0.000031203293,0.00014449157,0.0012807732,0.00027956563,0.000004400512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032819276,0.0020692693,0.048681274,0.00046317474,0.010295144,0.000425824,0.001079622,0.6953448,0.019275855,0.08338958,0.0035721925,0.13537045],"study_design_scores_gemma":[0.00009265813,0.000024890913,0.0026462278,0.000043007472,0.0005021999,6.728733e-7,0.0000067734222,0.9689038,0.024536626,0.0027075293,0.0001620364,0.00037359475],"about_ca_topic_score_codex":0.0000914314,"about_ca_topic_score_gemma":0.000118817734,"teacher_disagreement_score":0.49576163,"about_ca_system_score_codex":0.00012565452,"about_ca_system_score_gemma":0.000084005966,"threshold_uncertainty_score":0.9999834},"labels":[],"label_agreement":null},{"id":"W4251063661","doi":"10.1007/978-1-4939-7131-2_101113","title":"Social Indexing","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Search engine indexing; Computer science; Information retrieval","score_opus":0.029386760224444655,"score_gpt":0.2976400481211125,"score_spread":0.26825328789666786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251063661","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.72531e-7,0.000013880473,0.47088385,0.00012000977,0.0000310718,0.000037736805,2.8899743e-7,0.00048291712,0.52843004],"genre_scores_gemma":[0.00037162498,0.000011873711,0.13486806,0.00040498195,0.0003937438,0.0000032483474,0.0000030905678,0.000025069536,0.8639183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988471,0.0000054930565,0.00021695778,0.0004496753,0.00030431387,0.00017642636],"domain_scores_gemma":[0.99910766,0.000022315246,0.0001701866,0.0005366063,0.00012230664,0.0000409005],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010659093,0.00021913543,0.00027191293,0.00019347295,0.00011905006,0.000094842915,0.0010843179,0.00026309773,0.0009170472],"category_scores_gemma":[0.0000055629075,0.00020496732,0.00017786157,0.000045466135,0.00009116648,0.00025900223,0.0005698433,0.00022542996,0.00080884906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7299757e-7,0.0000022221586,3.2913e-7,0.0000021937374,0.000023524315,0.000005878847,0.00006264106,5.357347e-8,0.000009572088,0.9519936,0.02381145,0.024088271],"study_design_scores_gemma":[0.00002004787,0.0000143796815,0.000001082217,0.00001131515,0.0000081387625,0.0000020245943,4.475204e-7,0.00018966108,0.00022854797,0.55197614,0.4473484,0.00019985597],"about_ca_topic_score_codex":0.0000021895514,"about_ca_topic_score_gemma":0.000012104629,"teacher_disagreement_score":0.42353693,"about_ca_system_score_codex":0.00007411902,"about_ca_system_score_gemma":0.000041802716,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W4251440222","doi":"10.1007/978-1-4939-7131-2_100201","title":"Content-Based Filtering","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.06038741613714324,"score_gpt":0.26616976127405756,"score_spread":0.20578234513691432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251440222","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.749041e-7,0.000035795474,0.587387,0.00009059288,0.00006248659,0.000071786424,0.0000013031987,0.0006483392,0.4117019],"genre_scores_gemma":[0.00022956142,0.000009654679,0.41214165,0.0006628922,0.00008384726,0.000006630703,0.000006195734,0.000025619785,0.58683395],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986814,0.000006136891,0.00027866714,0.0005450113,0.00028567496,0.0002030798],"domain_scores_gemma":[0.99832875,0.00004670614,0.00018484783,0.001192127,0.0001705675,0.00007698559],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000101854224,0.00028058415,0.0003255432,0.00022618467,0.000056859753,0.00010459734,0.0012132667,0.00017779662,0.0013839309],"category_scores_gemma":[0.000011909109,0.00024896293,0.00021113327,0.000037133428,0.00008547406,0.00022576452,0.00035970213,0.00017040367,0.000699031],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023457092,0.000008956517,0.0000019516567,0.000015199373,0.000059481154,0.00003864343,0.00001880442,0.0000024315614,0.0009631085,0.9531441,0.009920772,0.03582423],"study_design_scores_gemma":[0.00021008948,0.00018605676,0.0000033298077,0.00023477772,0.000041369345,0.0000089705945,0.0000019973631,0.008775763,0.034083873,0.15852223,0.796909,0.001022569],"about_ca_topic_score_codex":0.000005599707,"about_ca_topic_score_gemma":0.000016466254,"teacher_disagreement_score":0.7946218,"about_ca_system_score_codex":0.00007187894,"about_ca_system_score_gemma":0.000045030356,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W4253452607","doi":"10.1007/978-1-4939-7131-2_101061","title":"Sentiment-Emotion-Intent Analysis","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sentiment analysis; Psychology; Computer science; Cognitive psychology; Natural language processing","score_opus":0.016776002897686302,"score_gpt":0.26446226045971055,"score_spread":0.24768625756202425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253452607","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011400728,0.00004748251,0.5722853,0.00014542647,0.00006412782,0.000088284374,0.000002206809,0.0005278282,0.4268382],"genre_scores_gemma":[0.0007575187,0.00007706905,0.18809496,0.00034077337,0.000108867185,0.0000066429025,0.000038176997,0.000025450232,0.8105505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997694,0.000015201102,0.00048935256,0.0009412717,0.0005848017,0.0002753739],"domain_scores_gemma":[0.9972148,0.000037876565,0.0003540444,0.001906,0.00035870983,0.00012856869],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019790122,0.00039827442,0.00063394045,0.0010597399,0.00009624555,0.00016957235,0.0014461591,0.0002381438,0.0053282348],"category_scores_gemma":[0.000009431064,0.00035269288,0.00086302654,0.00035301686,0.00010409645,0.00032701832,0.0006959303,0.00021514416,0.0017289985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013670483,0.00002878622,0.000022899361,0.000007184589,0.0029550209,0.000026665317,0.00008058671,0.00002038229,0.00003268675,0.9556,0.025008388,0.016216038],"study_design_scores_gemma":[0.0001438671,0.00014134751,0.000043528926,0.000068177906,0.0026154441,0.000010497492,0.0000072709636,0.039474446,0.0020460237,0.4721647,0.4818766,0.0014081135],"about_ca_topic_score_codex":0.000013542929,"about_ca_topic_score_gemma":0.000047129142,"teacher_disagreement_score":0.48343533,"about_ca_system_score_codex":0.00015910863,"about_ca_system_score_gemma":0.000035167686,"threshold_uncertainty_score":0.99989253},"labels":[],"label_agreement":null},{"id":"W4254172015","doi":"10.1007/978-1-4939-7131-2_101361","title":"Topic Identification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Biology; Botany","score_opus":0.018762735002870085,"score_gpt":0.2712372913040963,"score_spread":0.2524745563012262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254172015","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4613498e-7,0.000039339433,0.5265979,0.00009731044,0.000071020695,0.000051902363,3.1339232e-7,0.00035321747,0.4727885],"genre_scores_gemma":[0.00036315245,0.000050506627,0.094167106,0.0001733593,0.00013082512,0.0000052915484,0.000006633951,0.000012755787,0.9050904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989914,0.0000045041675,0.00024611267,0.00042772465,0.00022693974,0.00010332255],"domain_scores_gemma":[0.99849313,0.00001759464,0.00017244965,0.0011381732,0.00014223093,0.000036402856],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000100610065,0.00015211513,0.0001672786,0.00016387453,0.000046709505,0.000101224985,0.0009704713,0.00014745847,0.00091817626],"category_scores_gemma":[0.000008280278,0.00014004073,0.00010739352,0.00003696285,0.00004811433,0.00028083188,0.00025076934,0.00010677035,0.0016887399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0962325e-7,0.0000019704298,4.852294e-7,0.000002664355,0.000012788152,0.0000019528036,0.00001813879,8.315298e-8,0.000063589636,0.94640917,0.011157572,0.04233151],"study_design_scores_gemma":[0.000013268449,0.00001256754,0.0000060671123,0.000012011449,0.000009084026,0.0000020237785,2.7728643e-7,0.00036864885,0.0016351978,0.5858769,0.41191545,0.000148511],"about_ca_topic_score_codex":0.0000017999226,"about_ca_topic_score_gemma":0.0000095744,"teacher_disagreement_score":0.43243083,"about_ca_system_score_codex":0.00005364275,"about_ca_system_score_gemma":0.000022281676,"threshold_uncertainty_score":0.9999951},"labels":[],"label_agreement":null},{"id":"W4254928945","doi":"10.32920/ryerson.14649648.v1","title":"Fuzzy Thesauri Recommendation System For Web 2.0 Social networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; World Wide Web; The Internet; Scalability; Set (abstract data type); Node (physics); Social network (sociolinguistics); Order (exchange); Domain (mathematical analysis); Database; Social media","score_opus":0.026919574988326124,"score_gpt":0.30151589840289234,"score_spread":0.2745963234145662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254928945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013953498,0.00007991564,0.98374975,0.0015283334,0.0007652893,0.0005355949,0.0000066099583,0.0014891934,0.011705791],"genre_scores_gemma":[0.5358954,0.00003674361,0.4623083,0.00024209877,0.00054526655,0.00040150233,0.00023730194,0.000027993032,0.00030539688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979655,0.00014460002,0.00048885675,0.0008805892,0.00019777656,0.0003226523],"domain_scores_gemma":[0.99826765,0.00014674346,0.00040997352,0.00079062476,0.00032983243,0.00005515006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057488785,0.00029246358,0.0005183459,0.00015158551,0.00021056585,0.00053294085,0.0012546064,0.0003997933,0.000014855495],"category_scores_gemma":[0.000027868491,0.0002836385,0.00041814486,0.00029430052,0.000021597694,0.00032262708,0.0017876634,0.00040023177,0.000004192518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013770255,0.00014693863,0.00007037672,0.0005585473,0.00049231783,0.000011093644,0.0006482521,0.004172554,0.00038324005,0.39593366,0.02585069,0.5717186],"study_design_scores_gemma":[0.000286092,0.000035542645,0.00008305132,0.00019325681,0.00011086296,0.0000069391517,0.00025001244,0.96042025,0.0017803737,0.02477045,0.011194274,0.0008688724],"about_ca_topic_score_codex":0.00002105985,"about_ca_topic_score_gemma":0.00005055467,"teacher_disagreement_score":0.95624775,"about_ca_system_score_codex":0.00031712663,"about_ca_system_score_gemma":0.00015550759,"threshold_uncertainty_score":0.99996156},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014728942334229727,"score_gpt":0.2612281464799091,"score_spread":0.24649920414567938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255165398","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.825625e-7,0.00020759618,0.2556575,0.00006990276,0.00014007243,0.00015743505,0.000011617235,0.0008982154,0.7428567],"genre_scores_gemma":[0.10534163,0.00003249164,0.38194832,0.0031020779,0.0006623414,0.000054431464,0.0000078670055,0.00014976737,0.5087011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979367,0.0000092138,0.00038332012,0.0007833321,0.00052294385,0.00036446005],"domain_scores_gemma":[0.99796206,0.000017483195,0.000270224,0.001458815,0.00013013839,0.00016129717],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000082701634,0.00046445383,0.00049644144,0.00011185522,0.000089821035,0.00015036896,0.0017457292,0.00038498268,0.000032296473],"category_scores_gemma":[0.000010074711,0.000466316,0.000354541,0.00003760803,0.00010224722,0.00014531438,0.0006374099,0.00032357304,0.00047951296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014483534,0.0000041533885,0.0000010611346,0.000007104262,0.00004658915,0.0001088475,0.000012927569,0.000006129679,0.000009736801,0.97416586,0.0008654149,0.024770727],"study_design_scores_gemma":[0.000107564825,0.00004849753,0.00000315944,0.000109009554,0.000032018947,0.000033449192,3.443112e-7,0.000037978152,0.0002417881,0.94361925,0.055321563,0.0004453513],"about_ca_topic_score_codex":0.00003248463,"about_ca_topic_score_gemma":0.000036546095,"teacher_disagreement_score":0.2341556,"about_ca_system_score_codex":0.0005838915,"about_ca_system_score_gemma":0.0002626255,"threshold_uncertainty_score":0.99977887},"labels":[],"label_agreement":null},{"id":"W4256499950","doi":"10.1007/978-1-4614-6170-8_100872","title":"Social Indexing","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Search engine indexing; Computer science; Information retrieval","score_opus":0.022375741178368,"score_gpt":0.28043612194115036,"score_spread":0.25806038076278237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256499950","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.0247972e-8,0.000012062909,0.50350416,0.00017811617,0.000022854932,0.00003274634,1.4691528e-7,0.00045623948,0.49579364],"genre_scores_gemma":[0.0013896389,0.00001128414,0.107915774,0.0005987127,0.0002560793,0.000003803316,0.0000034150721,0.00002690931,0.8897944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998867,0.000007651236,0.00022517065,0.00042786702,0.00030254156,0.00016979678],"domain_scores_gemma":[0.99912703,0.0000360162,0.00018127619,0.0005353624,0.00007789429,0.000042406205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012880008,0.00022230456,0.00031799905,0.00018946792,0.000102725644,0.00008813152,0.0010426972,0.0002574599,0.00017647276],"category_scores_gemma":[0.0000065541894,0.00020871712,0.00019612056,0.000035778714,0.000048454727,0.00013689022,0.00045995688,0.0002781856,0.00036195424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6155501e-7,0.0000011742706,3.8413077e-7,0.0000028135012,0.000016299904,0.0000032817727,0.000017821798,4.3185273e-7,0.0000072979533,0.91326314,0.006887484,0.07979973],"study_design_scores_gemma":[0.000023356613,0.000009641679,0.0000013974403,0.000011031674,0.000008388603,0.0000017745499,1.5212267e-7,0.0005242088,0.00011215392,0.4629496,0.53614604,0.00021222876],"about_ca_topic_score_codex":0.000002682569,"about_ca_topic_score_gemma":0.000008881886,"teacher_disagreement_score":0.52925855,"about_ca_system_score_codex":0.00006230301,"about_ca_system_score_gemma":0.000029096313,"threshold_uncertainty_score":0.8511237},"labels":[],"label_agreement":null},{"id":"W4288751120","doi":"10.5539/ijel.v12n5p59","title":"Teaching Complex Sentences in ESL Reading: Structural Analysis","year":2022,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Jilin Office of Philosophy and Social Science","keywords":"Conceptualization; Reading (process); Test (biology); Second language; Cognition; Linguistics; Psychology; Empirical research; Mathematics education; Computer science; Artificial intelligence; Mathematics","score_opus":0.019093918799176143,"score_gpt":0.32839580407688956,"score_spread":0.3093018852777134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288751120","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09787002,0.00032538766,0.83012736,0.0006804669,0.02395164,0.00020869948,0.000064319334,0.0003264433,0.046445664],"genre_scores_gemma":[0.9059645,0.0000070535184,0.0921845,0.0001919972,0.0015811656,0.0000016588253,0.000009441515,0.0000062203853,0.000053474676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977891,0.0001617724,0.00069860823,0.00019595638,0.0009912717,0.0001632967],"domain_scores_gemma":[0.9938432,0.00024763664,0.00067074725,0.00021156615,0.004963546,0.000063299216],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00087348715,0.0001170173,0.0002947222,0.0012141933,0.00011731504,0.00014237176,0.0020648255,0.000023071136,0.00006859469],"category_scores_gemma":[0.014165406,0.00011585929,0.00022941346,0.0006773553,0.000034261804,0.00019794742,0.0005061664,0.00061341387,3.7692232e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012288254,0.0004490036,0.15173136,0.00001087149,0.003199253,0.001367753,0.01173104,0.24670717,0.00027962658,0.5596741,0.0072314437,0.017495496],"study_design_scores_gemma":[0.0012774082,0.00035076775,0.017199252,0.000042911193,0.00039274956,0.000047486803,0.0022695789,0.43363222,0.00043467953,0.09084899,0.45276165,0.00074228714],"about_ca_topic_score_codex":0.00007674847,"about_ca_topic_score_gemma":0.000026632892,"teacher_disagreement_score":0.80809444,"about_ca_system_score_codex":0.00032722857,"about_ca_system_score_gemma":0.00007199173,"threshold_uncertainty_score":0.9941387},"labels":[],"label_agreement":null},{"id":"W4292200231","doi":"10.7287/peerj-cs.1066v0.2/reviews/2","title":"Peer Review #2 of \"Causal graph extraction from news: a comparative study of time-series causality learning techniques (v0.2)\"","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Causality (physics); Series (stratigraphy); Graph; Computer science; Time series; Psychology; Data science; Theoretical computer science; Machine learning; Physics; Geology","score_opus":0.06287932553139104,"score_gpt":0.4000561116054687,"score_spread":0.3371767860740777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292200231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000119894066,0.25357115,0.6491208,0.041824054,0.0009912841,0.010736505,0.0005238392,0.0038107329,0.0393017],"genre_scores_gemma":[0.00073772634,0.2661713,0.36263663,0.0021904553,0.0002681082,0.0023086013,0.0033716636,0.00016149417,0.36215404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914768,0.001686942,0.0021617364,0.0012898839,0.003045683,0.0003389573],"domain_scores_gemma":[0.9916428,0.00049019814,0.0029941113,0.002116101,0.0026599949,0.00009679227],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00288741,0.00071059994,0.0032467141,0.0005005879,0.00018199025,0.00005501187,0.0021920674,0.00019687533,0.0022128471],"category_scores_gemma":[0.00081451953,0.0006379927,0.00060603215,0.001982962,0.00016076212,0.00096864754,0.001374647,0.0014198966,0.000013244839],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001855651,0.0009898872,0.00010094724,0.0065039108,0.00066073576,0.000019501738,0.0007946988,0.000010745732,0.00031233634,0.00055139425,0.97510344,0.01493385],"study_design_scores_gemma":[0.00013690413,0.0012362255,0.000049828777,0.011566458,0.00087762886,0.000009869584,0.00036418496,0.000058981434,0.0031549076,0.0018555473,0.9799186,0.0007708547],"about_ca_topic_score_codex":0.0044644447,"about_ca_topic_score_gemma":0.00069534534,"teacher_disagreement_score":0.3228523,"about_ca_system_score_codex":0.00019446059,"about_ca_system_score_gemma":0.00023379322,"threshold_uncertainty_score":0.99960715},"labels":[],"label_agreement":null},{"id":"W4293863311","doi":"10.1109/siu55565.2022.9864851","title":"Automatic Keyword Extraction From Dialogue Text","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Keyword extraction; Dialog box; Recall; Word (group theory); Natural language processing; Precision and recall; Information retrieval; Process (computing); Artificial intelligence; Customer service; Service (business); World Wide Web; Linguistics","score_opus":0.029836366513141047,"score_gpt":0.3031218038835432,"score_spread":0.2732854373704022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016536304,0.00246305,0.98784727,0.0034846514,0.000016677164,0.00047941448,0.00003255653,0.00078195723,0.0032407755],"genre_scores_gemma":[0.83830637,0.00043616732,0.15774636,0.0002512427,0.000025093086,0.002806944,0.00019765751,0.000017630566,0.00021250863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979523,0.00027797214,0.0004993174,0.00061000313,0.00039573174,0.00026468944],"domain_scores_gemma":[0.99673647,0.00032602937,0.0004247856,0.0021692775,0.00022878584,0.000114676535],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004192215,0.00022338613,0.00026869963,0.00026697738,0.0024577165,0.00042263145,0.0029582784,0.00006150726,0.00021721519],"category_scores_gemma":[0.000017160219,0.00025047603,0.00006895451,0.0013796899,0.00024130865,0.00077295746,0.0016702535,0.0006331018,0.000028056154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021795129,0.00023390434,0.00016414345,0.000012026722,0.000022367964,6.145645e-7,0.00074308325,0.000067536625,0.00378089,0.056736227,0.00027787779,0.93795913],"study_design_scores_gemma":[0.000241289,0.00006739349,0.0009868108,0.00003500596,0.00007608043,0.000022693968,0.0011338076,0.7714795,0.000607021,0.13447855,0.090342015,0.000529857],"about_ca_topic_score_codex":0.00012190672,"about_ca_topic_score_gemma":0.00006246403,"teacher_disagreement_score":0.9374293,"about_ca_system_score_codex":0.0001375837,"about_ca_system_score_gemma":0.00028212162,"threshold_uncertainty_score":0.99999475},"labels":[],"label_agreement":null},{"id":"W4297993723","doi":"10.1007/978-1-4614-7163-9_352-1","title":"Automatic Document Topic Identification Using Social Knowledge Network","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identification (biology); Computer science; Social knowledge; Data science; Information retrieval; Sociology; Social science; Biology","score_opus":0.04112207874473995,"score_gpt":0.33929912789038236,"score_spread":0.2981770491456424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297993723","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000075797716,0.00025961446,0.66691804,0.00010727851,0.00032054895,0.00020840937,4.6214836e-7,0.0005265282,0.33165154],"genre_scores_gemma":[0.008252596,0.000060859697,0.17226401,0.00007628474,0.0009492518,0.000019867899,0.000012689276,0.00004437514,0.81832004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983648,0.000024422146,0.0004857396,0.0005640068,0.0003000686,0.00026094742],"domain_scores_gemma":[0.9978054,0.000036809222,0.0006814437,0.0012715393,0.00015140905,0.00005336481],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031859617,0.00029524515,0.0004291855,0.0001517453,0.00053152145,0.00047231428,0.0015681391,0.00025314104,0.00019982379],"category_scores_gemma":[0.0000117982445,0.00028978902,0.00024060726,0.000033760825,0.00008096109,0.0005810429,0.00062896946,0.00022133748,0.00022361854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9447894e-7,0.000006003336,0.0000016282156,0.000022117814,0.000055842003,0.0000041543076,0.000116756484,0.000006673174,0.000020668853,0.7984463,0.0028562206,0.19846343],"study_design_scores_gemma":[0.00007255039,0.000013032916,0.000058460577,0.00013822771,0.00009999459,0.000005036939,0.0000010401902,0.041142832,0.00013025467,0.8668517,0.09099692,0.00048994337],"about_ca_topic_score_codex":0.000009029271,"about_ca_topic_score_gemma":0.000039532406,"teacher_disagreement_score":0.49465403,"about_ca_system_score_codex":0.00028386322,"about_ca_system_score_gemma":0.00010160591,"threshold_uncertainty_score":0.9999554},"labels":[],"label_agreement":null},{"id":"W4298195797","doi":"","title":"1 Exact versus Estimated Pruning of Subject Hierarchies","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pruning; Subject (documents); Computer science; Artificial intelligence; Horticulture; World Wide Web; Biology","score_opus":0.03281499216325376,"score_gpt":0.3134140566580464,"score_spread":0.28059906449479266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298195797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030321248,0.000031841497,0.9607035,0.00024301278,0.00004354958,0.000048897713,4.6327366e-7,0.0005475326,0.008059986],"genre_scores_gemma":[0.67857033,0.000017783193,0.3210546,0.000010619908,0.0000058192018,0.000003473137,2.1201748e-7,0.0000040153323,0.00033313106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924874,0.000031096086,0.00017108001,0.00021370627,0.00016856601,0.00016682186],"domain_scores_gemma":[0.9990298,0.00028092234,0.00008419311,0.000499305,0.00006725834,0.000038505066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013648492,0.000086541295,0.00014596555,0.00016261103,0.000035249504,0.000018978837,0.0005779197,0.000026523478,0.000040284816],"category_scores_gemma":[0.00012959584,0.000052753072,0.000055666344,0.0003890567,0.000071699906,0.0005287911,0.00020106765,0.000034403416,0.000019084104],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048518323,0.00005958337,0.0032407544,0.000010948217,0.00007936242,0.00001062994,0.00023567214,0.000035457837,0.18620963,0.29427257,0.0006486426,0.5151482],"study_design_scores_gemma":[0.00085742486,0.00030335624,0.0045415703,0.00009415378,0.000015399512,0.000004220375,0.000013905202,0.011302171,0.95350903,0.027834466,0.0012047729,0.00031949725],"about_ca_topic_score_codex":0.000020634374,"about_ca_topic_score_gemma":0.000010892226,"teacher_disagreement_score":0.7672994,"about_ca_system_score_codex":0.000027426368,"about_ca_system_score_gemma":0.00002719178,"threshold_uncertainty_score":0.21512078},"labels":[],"label_agreement":null},{"id":"W4298371492","doi":"","title":"Output Keywords in Context in an HTML File with Python","year":2012,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Python (programming language); Computer science; Programming language; Operating system; Information retrieval; Database","score_opus":0.22058783022283282,"score_gpt":0.5482749587316242,"score_spread":0.32768712850879145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298371492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8844764,0.012109369,0.09443945,0.00025190893,0.00034264298,0.00094908255,0.00003688567,0.00026517315,0.007129045],"genre_scores_gemma":[0.9827985,0.00069144665,0.015699586,0.00035175373,0.00008962023,0.00009288895,0.000010813031,0.000043561966,0.00022184126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966868,0.0004076892,0.0008976827,0.000581722,0.00073636486,0.00068971794],"domain_scores_gemma":[0.99731106,0.000318154,0.0007439979,0.0010600159,0.00023041446,0.00033635687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017205847,0.00036078208,0.00087722647,0.0016018967,0.00011059208,0.0010021399,0.0051995846,0.0001231727,0.0025825542],"category_scores_gemma":[0.00019468676,0.0003095731,0.00011397718,0.0025624922,0.00012172519,0.012052564,0.0012978504,0.0005711788,0.000018251762],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008443936,0.00062702823,0.8626152,0.000022488553,0.000043885917,0.000067842644,0.0010121142,0.00024324816,0.0045022294,0.00093639037,0.008639403,0.12120573],"study_design_scores_gemma":[0.0006769866,0.0000378185,0.9647106,0.0005319496,0.000021516635,0.000022612889,0.00015607718,0.0019357584,0.015134438,0.0073284362,0.008721589,0.0007221936],"about_ca_topic_score_codex":0.0009032867,"about_ca_topic_score_gemma":0.0013933197,"teacher_disagreement_score":0.12048353,"about_ca_system_score_codex":0.00021689254,"about_ca_system_score_gemma":0.00012654351,"threshold_uncertainty_score":0.9999356},"labels":[],"label_agreement":null},{"id":"W4299291826","doi":"","title":"Application of Trend Detection Methods in Monitoring Physiological Signals","year":2004,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Computer science","score_opus":0.2818971117291039,"score_gpt":0.615143491350574,"score_spread":0.3332463796214701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299291826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20639788,0.0019809091,0.7909357,0.000029344761,0.00008837979,0.00024301006,0.0000013214546,0.000072821196,0.00025063488],"genre_scores_gemma":[0.8557812,0.0009874024,0.14305893,0.000021000991,0.000058079106,0.00006976092,0.0000010066852,0.0000136354565,0.000009013664],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99752617,0.00035266866,0.00090357655,0.0005036484,0.00044551588,0.00026843324],"domain_scores_gemma":[0.9978194,0.0002665589,0.0009998858,0.00062833435,0.00018030047,0.00010550527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015824623,0.00022165896,0.00068409403,0.0009846912,0.00010047755,0.00029135833,0.0032477865,0.00011603683,0.00009720588],"category_scores_gemma":[0.00020521946,0.00019909741,0.00018182759,0.0023738714,0.00008601036,0.002747209,0.00088649814,0.00032552928,0.0000025168388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016119917,0.00014309677,0.012819218,0.000013757669,0.000028096607,0.0000029893745,0.00006849953,0.004288073,0.7729245,0.00024446394,0.000017220764,0.20943396],"study_design_scores_gemma":[0.00018197625,0.000013772388,0.19417837,0.00009834358,0.000014394827,0.0000027415629,0.00001321379,0.0013271425,0.72170943,0.082193695,0.00009393981,0.00017298768],"about_ca_topic_score_codex":0.00043292987,"about_ca_topic_score_gemma":0.000026654132,"teacher_disagreement_score":0.6493833,"about_ca_system_score_codex":0.00018085916,"about_ca_system_score_gemma":0.000044167078,"threshold_uncertainty_score":0.81189567},"labels":[],"label_agreement":null},{"id":"W4299335947","doi":"10.1007/978-3-031-01880-0_3","title":"Mining Text Conversations","year":2011,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Linguistics; Philosophy","score_opus":0.060711542777487804,"score_gpt":0.2734736238599594,"score_spread":0.21276208108247158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299335947","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9539381e-7,0.00019051743,0.37477082,0.00035184686,0.00011828551,0.00032186243,0.000058917063,0.00047513633,0.6237124],"genre_scores_gemma":[0.010260861,0.002710593,0.4653215,0.0030139172,0.00031548098,0.00023289268,0.00063482585,0.000263073,0.51724684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698806,0.00004284989,0.000444595,0.0015410953,0.000627283,0.00035612556],"domain_scores_gemma":[0.9927807,0.00029084517,0.00039499576,0.0063814744,0.000054145574,0.00009786022],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00036742794,0.0005411314,0.0004976907,0.0007394264,0.00018656827,0.0002203998,0.006129147,0.00020443645,0.0007580015],"category_scores_gemma":[0.000084604275,0.0005071689,0.00016308982,0.00011601003,0.00010001676,0.00054366264,0.003131927,0.000289222,0.00063181284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005204965,0.000024464754,5.916217e-7,0.000035733636,0.0004464709,0.00006093699,0.000040608815,0.000010189406,0.0000014223684,0.56821615,0.048267186,0.38289103],"study_design_scores_gemma":[0.000072588846,0.000037420537,0.000013646601,0.00027059985,0.00033376104,0.0000021630456,0.0000064835112,0.00061010505,0.00041748642,0.08014992,0.9174407,0.00064512645],"about_ca_topic_score_codex":0.000011518328,"about_ca_topic_score_gemma":0.000044849832,"teacher_disagreement_score":0.8691735,"about_ca_system_score_codex":0.0001422046,"about_ca_system_score_gemma":0.000030417821,"threshold_uncertainty_score":0.999738},"labels":[],"label_agreement":null},{"id":"W4300501538","doi":"10.1007/978-1-4614-6170-8_352","title":"Automatic Document Topic Identification Using Social Knowledge Network","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identification (biology); Computer science; Social knowledge; Data science; Social network analysis; Information retrieval; World Wide Web; Social media; Sociology; Social science; Biology","score_opus":0.02634131939976245,"score_gpt":0.30789046175082113,"score_spread":0.28154914235105866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300501538","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009476425,0.00017069324,0.8094549,0.000094886665,0.00025371517,0.00019096259,2.4924478e-7,0.00066256657,0.18916252],"genre_scores_gemma":[0.013420883,0.000038201302,0.2832554,0.00021592632,0.0012304619,0.000024307345,0.000017090204,0.00005927625,0.7017385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826777,0.00003928927,0.0005638467,0.00055936986,0.00030744218,0.00026229487],"domain_scores_gemma":[0.9984821,0.000058902628,0.0004589861,0.0008016669,0.00014381365,0.00005449769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036879443,0.00029753475,0.0004368171,0.00017730771,0.00023669237,0.00023035887,0.0009921483,0.00024621922,0.00023776623],"category_scores_gemma":[0.000008338441,0.00029124395,0.00023005146,0.00009958578,0.000055380784,0.00025520954,0.00044243937,0.00020913553,0.0002777641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4390936e-7,0.0000038131714,9.728158e-7,0.000021755368,0.000037862297,0.000001175732,0.000078442165,0.000017053504,0.00001938565,0.8411605,0.00293227,0.15572664],"study_design_scores_gemma":[0.000073748255,0.00001808658,0.00002780395,0.00011050802,0.00009808942,0.0000044591125,0.0000010935339,0.1079691,0.00013739124,0.77097166,0.120070614,0.00051745086],"about_ca_topic_score_codex":0.000005019126,"about_ca_topic_score_gemma":0.000020292215,"teacher_disagreement_score":0.5261995,"about_ca_system_score_codex":0.00028133902,"about_ca_system_score_gemma":0.00006609743,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W4307128390","doi":"10.1007/s11042-022-14043-z","title":"Systematic review of content analysis algorithms based on deep neural networks","year":2022,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Deep learning; Artificial neural network; Support vector machine; Subject (documents); The Internet; Algorithm; Data mining; World Wide Web","score_opus":0.0293709047354469,"score_gpt":0.2849881205764562,"score_spread":0.2556172158410093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307128390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018350316,0.0049347663,0.99342966,0.00038756995,0.000011057136,0.0010320734,0.000022131391,0.00009655668,0.00006785341],"genre_scores_gemma":[0.6601039,0.0020737783,0.31767187,0.0049019777,0.00006582497,0.014670596,0.0003777253,0.000029605333,0.00010469572],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986923,0.00011644967,0.00045859304,0.00031352293,0.0002881926,0.00013097248],"domain_scores_gemma":[0.9983847,0.00036093377,0.00030988138,0.000783584,0.00009485563,0.00006601061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037142012,0.00011267553,0.00047812093,0.00015623293,0.00017077358,0.0000331665,0.00055389316,0.000018482782,0.000023362902],"category_scores_gemma":[0.00005536454,0.000096471376,0.00018839173,0.0014260183,0.000036686903,0.00009575371,0.0001618531,0.000121397956,0.000001303626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001794015,0.0021572497,0.0016207313,0.07242973,0.0024756603,0.000018900431,0.00057237694,0.35245845,0.00050221325,0.033352807,0.00056741503,0.53382653],"study_design_scores_gemma":[0.00007703941,0.000031067524,0.00017487459,0.00044544067,0.00033117647,9.696817e-7,0.000016634025,0.99863917,0.00003472599,0.00007213475,0.00007849121,0.00009829883],"about_ca_topic_score_codex":0.000009495005,"about_ca_topic_score_gemma":0.0000022848765,"teacher_disagreement_score":0.67575777,"about_ca_system_score_codex":0.000036698973,"about_ca_system_score_gemma":0.000009193058,"threshold_uncertainty_score":0.39339888},"labels":[],"label_agreement":null},{"id":"W4307260180","doi":"10.5539/ells.v12n4p29","title":"A Study on Lexical Chunks in Different Moves of Abstracts of Native and Chinese Applied Linguistic Journals","year":2022,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Norm (philosophy); Perspective (graphical); Linguistics; Computer science; Natural language processing; Significant difference; Artificial intelligence; Psychology; Mathematics; Epistemology; Statistics; Philosophy","score_opus":0.011140211545487234,"score_gpt":0.3197886199857754,"score_spread":0.3086484084402882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307260180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98904747,0.009935705,0.000110253335,0.000026892725,0.00005253029,0.00017997473,0.000012060281,0.000028269014,0.0006068373],"genre_scores_gemma":[0.99912405,0.00009648061,0.0006199308,0.000027563787,0.00006875531,0.0000328765,0.0000014771906,0.0000048196275,0.00002402454],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9989995,0.00008737439,0.000314584,0.00024651608,0.00024435463,0.000107677646],"domain_scores_gemma":[0.999231,0.00027676945,0.0001751418,0.00018642879,0.00010409623,0.000026593767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003065813,0.0001449471,0.00042046956,0.00024211101,0.00007582916,0.000034381825,0.00018272089,0.0000224362,0.0000016197221],"category_scores_gemma":[0.0005816838,0.00009761812,0.00003528086,0.00040429266,0.00005441521,0.00007533258,0.00037374962,0.00031777483,1.3526068e-8],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004609678,0.0004914327,0.0049643596,0.000052319952,0.00016852633,0.00016923693,0.9860047,0.00003783162,0.0009134538,0.0034476253,0.000017516719,0.0036868872],"study_design_scores_gemma":[0.003834826,0.002977145,0.49903965,0.00069799426,0.0001245276,0.000022566308,0.45694253,0.00023324607,0.00900167,0.026038809,0.00014875237,0.00093827915],"about_ca_topic_score_codex":0.0000032915468,"about_ca_topic_score_gemma":0.000010784049,"teacher_disagreement_score":0.5290622,"about_ca_system_score_codex":0.000017072192,"about_ca_system_score_gemma":0.000005356462,"threshold_uncertainty_score":0.39807513},"labels":[],"label_agreement":null},{"id":"W4307381099","doi":"10.1115/1.4056076","title":"A Hybrid Semantic Networks Construction Framework for Engineering Design","year":2022,"lang":"en","type":"article","venue":"Journal of Mechanical Design","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bombardier (Canada); Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Word2vec; Information retrieval; Natural language processing; Artificial intelligence; Key (lock); Phrase; Thesaurus; Parsing","score_opus":0.024840125948536396,"score_gpt":0.2625807066213537,"score_spread":0.23774058067281728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307381099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007798997,0.00020822609,0.9984194,0.00033934752,0.0005816758,0.00026114253,5.377545e-7,0.00011024392,0.000001409252],"genre_scores_gemma":[0.21618994,0.000027143618,0.78344846,0.00014043269,0.0001420106,0.000031922147,2.0740936e-7,0.000015516005,0.0000043899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823296,0.00025708895,0.0005650136,0.00022095577,0.00044226693,0.00028171568],"domain_scores_gemma":[0.99770874,0.0012089735,0.0004997643,0.00030083666,0.00016219878,0.0001195029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021513128,0.00014621337,0.00035763264,0.00022924588,0.0001800688,0.0000802081,0.00095315254,0.000055018216,0.000019653959],"category_scores_gemma":[0.00049494504,0.00013974405,0.00024637958,0.00040438047,0.000013111342,0.0003547354,0.00018393275,0.0005942903,7.934627e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010732361,0.00008036187,0.0000010777215,0.000008188689,0.00011073241,0.00009298932,0.00002986898,0.7185278,0.003698449,0.23585969,0.0011778431,0.040305715],"study_design_scores_gemma":[0.00018863176,0.0005985608,8.36421e-7,0.000027296965,0.000038488415,0.000517962,0.000007490544,0.7248951,0.009360417,0.2637861,0.00045699973,0.00012209026],"about_ca_topic_score_codex":3.5259816e-7,"about_ca_topic_score_gemma":1.8053052e-8,"teacher_disagreement_score":0.21611194,"about_ca_system_score_codex":0.00016647278,"about_ca_system_score_gemma":0.000085331114,"threshold_uncertainty_score":0.56985974},"labels":[],"label_agreement":null},{"id":"W4307873956","doi":"10.32604/cmc.2023.026607","title":"Identification and Visualization of Spatial and Temporal Trends in Textile Industry","year":2022,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Computer science; Data science; Visualization; Phrase; Field (mathematics); Identification (biology); Key (lock); Subject (documents); Textile; Information retrieval; Artificial intelligence; World Wide Web; Geography","score_opus":0.011372053583374715,"score_gpt":0.2688125094646664,"score_spread":0.25744045588129166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307873956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79095596,0.0001452541,0.20470282,0.00036308053,0.0023166537,0.0008206577,0.000119569784,0.0005234704,0.000052543637],"genre_scores_gemma":[0.98082566,0.000046941645,0.01773647,0.00025749058,0.00036567647,0.00019115131,0.0002601838,0.00008690405,0.00022950057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99286586,0.0012087359,0.0025057455,0.0017977244,0.00078044675,0.0008415167],"domain_scores_gemma":[0.9960357,0.00024619856,0.0018596842,0.0013677605,0.00027801289,0.00021264104],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002409213,0.0008209698,0.0017896396,0.0014545675,0.00035105576,0.0011990783,0.0018108913,0.00038860785,0.0003758178],"category_scores_gemma":[0.000080130936,0.0009123136,0.00014771555,0.0010114587,0.0003114013,0.0014513597,0.0036394538,0.0003789028,0.000011614393],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027068448,0.0005142639,0.007530718,0.00027004562,0.00019644512,0.00011501517,0.0029610232,0.00010726302,0.8883655,0.012523175,0.003070853,0.084075],"study_design_scores_gemma":[0.006297751,0.001141,0.16760094,0.00070686365,0.00022406528,0.00032785736,0.00034462177,0.01408333,0.78947395,0.006284584,0.010222914,0.0032921184],"about_ca_topic_score_codex":0.0009719684,"about_ca_topic_score_gemma":0.00007987673,"teacher_disagreement_score":0.18986975,"about_ca_system_score_codex":0.00022269478,"about_ca_system_score_gemma":0.00008988578,"threshold_uncertainty_score":0.99983776},"labels":[],"label_agreement":null},{"id":"W4310007486","doi":"10.1109/acii55700.2022.9953882","title":"Choose or Fuse: Enriching Data Views with Multi-label Emotion Dynamics","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuse (electrical); Dynamics (music); Computer science; Artificial intelligence; Human–computer interaction; Psychology; Electrical engineering; Engineering","score_opus":0.10012331492029614,"score_gpt":0.3502092798871958,"score_spread":0.25008596496689967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310007486","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019768358,0.000049023507,0.9959612,0.00045895122,0.000057624555,0.0002053404,0.000011391867,0.00070921594,0.00057041494],"genre_scores_gemma":[0.070018195,0.000023264656,0.92619586,0.0005084944,0.00001654669,0.000035323734,0.0000910217,0.000016807478,0.0030944995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983831,0.00010929102,0.00023561469,0.00064505875,0.00039086447,0.00023608451],"domain_scores_gemma":[0.99770886,0.000055070945,0.00014807764,0.0019806826,0.00004557108,0.000061748135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004943502,0.00015068456,0.0001885632,0.00015584643,0.00034230071,0.00011846604,0.0026131151,0.000021952366,0.00009029567],"category_scores_gemma":[0.000042958207,0.00010910723,0.00002284679,0.0010136517,0.000022992373,0.0013108314,0.002673321,0.00026122216,0.000012783001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020289976,0.0005131871,0.00068953435,0.000013040157,0.000054529508,0.000068129724,0.00048026093,0.0007832547,0.0005240741,0.023192765,0.0019685833,0.9716923],"study_design_scores_gemma":[0.00032477494,0.00009664658,0.00020011085,0.0000047178987,0.00001278232,0.000034671233,0.0001129285,0.9941044,0.000094402014,0.000502634,0.0043127765,0.00019918993],"about_ca_topic_score_codex":0.00006627856,"about_ca_topic_score_gemma":0.00060491945,"teacher_disagreement_score":0.9933211,"about_ca_system_score_codex":0.00017567752,"about_ca_system_score_gemma":0.000065488915,"threshold_uncertainty_score":0.48558614},"labels":[],"label_agreement":null},{"id":"W4312527591","doi":"10.1007/978-3-031-19745-1_12","title":"Measuring the Big Five Factors from Handwriting Using Ensemble Learning Model AvgMlSC","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence","score_opus":0.05032433373247846,"score_gpt":0.26457773012523367,"score_spread":0.2142533963927552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312527591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019749182,0.00052110263,0.99497443,0.00015896023,0.000530023,0.00029010553,0.0000051542147,0.00041319392,0.0011321022],"genre_scores_gemma":[0.50432825,0.00004188385,0.49471793,0.00036218378,0.00026900755,0.00000961278,0.000006929842,0.00005567489,0.00020853928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949799,0.000112596535,0.00063285825,0.0018485191,0.001627061,0.00079904095],"domain_scores_gemma":[0.9964444,0.0010584431,0.000587104,0.0015469289,0.0002302304,0.00013286034],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011369128,0.00065417134,0.00067299133,0.0008346963,0.0015177431,0.00080410513,0.004805285,0.00022399481,0.000021190705],"category_scores_gemma":[0.00023579216,0.0005353864,0.0002741538,0.00094058044,0.0004986439,0.00088324596,0.004008303,0.0021161577,0.000004990131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017682265,0.000008197284,0.00008251902,0.0000062570034,0.000018703946,0.000027589118,0.0018720279,0.78405887,0.0014406699,0.0031315684,0.0000013858846,0.20935047],"study_design_scores_gemma":[0.00008357548,0.000035802303,0.000013463985,0.00017227161,0.000019700587,0.000012522996,0.0000022456986,0.8674131,0.004749074,0.1266876,0.0002553755,0.0005552554],"about_ca_topic_score_codex":0.0002936603,"about_ca_topic_score_gemma":0.00015724743,"teacher_disagreement_score":0.5023533,"about_ca_system_score_codex":0.00079214957,"about_ca_system_score_gemma":0.00056639424,"threshold_uncertainty_score":0.99978215},"labels":[],"label_agreement":null},{"id":"W4312876730","doi":"10.2139/ssrn.4241291","title":"Language Models for Automated Market Research: A New Way to Generate Perceptual Maps","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Perception; Computer science; Cognitive science; Artificial intelligence; Natural language processing; Data science; Psychology; Neuroscience","score_opus":0.03884540882691364,"score_gpt":0.34335700007021086,"score_spread":0.30451159124329724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312876730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012632894,0.0010368505,0.98191625,0.0026368764,0.00009118025,0.00038139557,0.0000083637215,0.0006143044,0.00068189716],"genre_scores_gemma":[0.80334526,0.00035394856,0.170974,0.0006832675,0.00041100587,0.00020292882,0.000013659656,0.00007008251,0.023945833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99514645,0.00041994033,0.00033172083,0.00048460113,0.0008284109,0.0027888534],"domain_scores_gemma":[0.998798,0.000115547045,0.000111364156,0.0005500237,0.00019168272,0.00023335448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051723258,0.00017971704,0.00023953886,0.0006063355,0.0008834388,0.00020916395,0.001989525,0.00004461194,0.00008058208],"category_scores_gemma":[0.00009889499,0.00017431626,0.00017346394,0.0012006911,0.000026882824,0.00055306277,0.0007012835,0.0018651733,0.000015374693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018496605,0.00017059033,0.0000106154175,0.0000065046956,0.00025574394,0.00004848523,0.0067537855,0.02685867,0.012349018,0.61053914,0.1417399,0.20108256],"study_design_scores_gemma":[0.0005168734,0.0009342345,0.000010936082,0.000006718652,0.000014313964,0.00037995182,0.002330662,0.40095198,0.00063338765,0.5837335,0.010183437,0.00030400846],"about_ca_topic_score_codex":0.00010256618,"about_ca_topic_score_gemma":0.00027439644,"teacher_disagreement_score":0.81094223,"about_ca_system_score_codex":0.0020440281,"about_ca_system_score_gemma":0.0019757613,"threshold_uncertainty_score":0.8103354},"labels":[],"label_agreement":null},{"id":"W4312991542","doi":"10.1115/detc2022-90688","title":"Knowledge Extraction Method to Support Domain Integrated Design Methodology","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Computer science; Domain (mathematical analysis); Domain knowledge; Focus (optics); Artificial intelligence; Machine learning; Data mining","score_opus":0.14133252813912373,"score_gpt":0.44001695740530955,"score_spread":0.2986844292661858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312991542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007451125,0.000021357759,0.99236894,0.00070002826,0.00017510867,0.00029250194,0.000001091968,0.0008966553,0.0054697837],"genre_scores_gemma":[0.008613054,0.0000012189414,0.9866695,0.0006942719,0.00002104574,0.00027452703,0.000004536444,0.000014471605,0.0037073784],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959591,0.0025624174,0.0003249425,0.00060664205,0.00023101397,0.00031586626],"domain_scores_gemma":[0.99813896,0.0008688638,0.00010400456,0.0006553295,0.00011625211,0.00011660279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004662073,0.00016314496,0.0002895253,0.0005201343,0.00024667394,0.000050500672,0.0011672085,0.00004802871,0.00083206635],"category_scores_gemma":[0.00012780646,0.00015189548,0.00010210067,0.0018513411,0.00001719003,0.0003637869,0.00078226795,0.00030343395,0.00010124261],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033956243,0.00017601953,0.000021167167,0.0000025678162,0.000049149367,0.000041932657,0.0014154132,0.002675256,0.12190992,0.2019081,0.025020907,0.6467456],"study_design_scores_gemma":[0.00028898517,0.0012349612,0.0000789748,0.0000026011146,0.000029175928,0.00027000834,0.00060339505,0.049362138,0.26177707,0.21736844,0.46837893,0.00060531887],"about_ca_topic_score_codex":0.000053453554,"about_ca_topic_score_gemma":0.000028396438,"teacher_disagreement_score":0.6461403,"about_ca_system_score_codex":0.00028254397,"about_ca_system_score_gemma":0.00013756359,"threshold_uncertainty_score":0.9110543},"labels":[],"label_agreement":null},{"id":"W4316664928","doi":"10.21203/rs.3.rs-2428155/v1","title":"EmoAtlas: An emotional profiling tool merging psychological lexicons, artificial intelligence and network science","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Profiling (computer programming); Emotional intelligence; Psychological science; Artificial intelligence; Computer science; Psychology; Data science; Cognitive science; Social psychology","score_opus":0.23669094474095342,"score_gpt":0.49690815325457166,"score_spread":0.26021720851361824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316664928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0675477,0.00028992834,0.92818785,0.0011691559,0.00037594105,0.0009676671,0.000011419152,0.0011508233,0.00029953071],"genre_scores_gemma":[0.6927204,0.00033649584,0.30600494,0.00004140928,0.0005539198,0.0002077338,0.000029582976,0.000031776683,0.00007372402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923305,0.00064267125,0.0006741482,0.002451641,0.0024987455,0.0014023294],"domain_scores_gemma":[0.9958542,0.0006121216,0.00018530872,0.0019139847,0.0010743218,0.00036004293],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008754552,0.00035624293,0.00046504982,0.001139991,0.001235828,0.0016383929,0.0037539003,0.00032176866,0.000020641874],"category_scores_gemma":[0.0014624838,0.00033280926,0.00013626325,0.0035480675,0.001464842,0.0009967997,0.0074928068,0.0023302867,0.00007089243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030281668,0.0002770024,0.0025460573,0.00021793268,0.000036489506,0.00016024358,0.0005303785,0.024868779,0.0019156974,0.6768776,0.00026817239,0.29227132],"study_design_scores_gemma":[0.0000238246,0.00022470947,0.0029984317,0.00045566543,0.000004844149,0.00001461112,0.0001748463,0.3191208,0.0027290098,0.67374927,0.000074690106,0.00042930542],"about_ca_topic_score_codex":0.000046583493,"about_ca_topic_score_gemma":0.000034444045,"teacher_disagreement_score":0.62517273,"about_ca_system_score_codex":0.00031003784,"about_ca_system_score_gemma":0.00056056946,"threshold_uncertainty_score":0.9999714},"labels":[],"label_agreement":null},{"id":"W4320558549","doi":"10.48550/arxiv.2302.04983","title":"CREDENCE: Counterfactual Explanations for Document Ranking","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; University of Waterloo","funders":"","keywords":"Credence; Counterfactual thinking; Ranking (information retrieval); Information retrieval; Computer science; Attribution; Machine learning; Psychology; Social psychology","score_opus":0.13831414081683752,"score_gpt":0.24837989918099043,"score_spread":0.11006575836415292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320558549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009263458,0.000027772216,0.9880554,0.00023054046,0.000404411,0.00050424447,0.000027816075,0.0011353003,0.0003510245],"genre_scores_gemma":[0.9599088,0.00019160076,0.03636212,0.00007519893,0.00007260532,0.000015046781,0.000050063467,0.000026769767,0.003297837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980326,0.00006234776,0.00025290786,0.0011397662,0.00014565287,0.00036670308],"domain_scores_gemma":[0.99781764,0.00030671977,0.00029897474,0.0012210233,0.00025283266,0.00010279484],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003570743,0.00029114154,0.00034083918,0.00048490887,0.00025655006,0.00021017613,0.0022559727,0.00021416733,0.000018771167],"category_scores_gemma":[0.00007793275,0.00034835367,0.00028918582,0.0006279889,0.0000726729,0.00061388564,0.001742286,0.0003511559,0.00006510982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023967319,0.00006546345,0.00035527383,0.000092434064,0.0002790654,0.00012529151,0.00058906747,0.24819261,0.00006595143,0.7445979,0.003748276,0.0018646712],"study_design_scores_gemma":[0.000378739,0.00005493027,0.00013179547,0.0001305022,0.00012114258,0.0000018568106,0.00013839094,0.39380875,0.0006568627,0.60048974,0.00349935,0.0005879405],"about_ca_topic_score_codex":0.00008146151,"about_ca_topic_score_gemma":0.00008364689,"teacher_disagreement_score":0.9516933,"about_ca_system_score_codex":0.00039559463,"about_ca_system_score_gemma":0.00015793316,"threshold_uncertainty_score":0.9998968},"labels":[],"label_agreement":null},{"id":"W4321488394","doi":"10.1145/3539597.3573033","title":"DisKeyword: Tweet Corpora Exploration for Keyword Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Social media; Selection (genetic algorithm); Information retrieval; Task (project management); License; GRASP; Keyword search; Artificial intelligence; World Wide Web; Natural language processing","score_opus":0.04859705573421192,"score_gpt":0.32179649944986105,"score_spread":0.27319944371564914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321488394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013802177,0.0000066810676,0.9938809,0.0009202903,0.00013593759,0.0002705187,9.734708e-7,0.00248462,0.00091982196],"genre_scores_gemma":[0.52549964,0.00005315832,0.4654914,0.00019066547,0.00014443745,0.00046158384,0.000054135293,0.000022400907,0.0080825975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909925,0.000022365071,0.00017950906,0.00032024432,0.00016932355,0.00020927712],"domain_scores_gemma":[0.99936885,0.000086429936,0.000083571875,0.0002886758,0.00012902774,0.00004344842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002349626,0.00009617185,0.000115661656,0.00023251199,0.0001340384,0.00013224794,0.00034102093,0.000043997803,0.000007065101],"category_scores_gemma":[0.000049216254,0.00008840494,0.00006387207,0.0014481556,0.000014028499,0.0012491039,0.00009454546,0.00005022406,0.000099335215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010897801,0.000054323653,0.0009360071,0.000013717607,0.000033405664,0.0000023809416,0.00026087882,0.006560773,0.0056613437,0.7694439,0.06957329,0.14744906],"study_design_scores_gemma":[0.00014895362,0.00011253831,0.00044313123,0.000004888907,0.000008458312,0.0000013432469,0.000038408238,0.75241685,0.013511814,0.20206635,0.031040506,0.00020674603],"about_ca_topic_score_codex":0.000014271003,"about_ca_topic_score_gemma":0.00002733968,"teacher_disagreement_score":0.7458561,"about_ca_system_score_codex":0.000040861247,"about_ca_system_score_gemma":0.0000217802,"threshold_uncertainty_score":0.3605049},"labels":[],"label_agreement":null},{"id":"W4322630579","doi":"10.21203/rs.3.rs-2497596/v1","title":"Systematic Review using a Spiral approach with Machine Learning","year":2023,"lang":"en","type":"review","venue":"Research Square","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Spiral (railway); Computer science; Artificial intelligence; Engineering; Mechanical engineering","score_opus":0.21997874520230526,"score_gpt":0.4883235181318533,"score_spread":0.26834477292954806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322630579","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9143934e-8,0.8233141,0.17160581,0.00001171029,0.000010573497,0.0040171,0.000005082142,0.0007413922,0.00029425116],"genre_scores_gemma":[5.896994e-7,0.95763975,0.03987527,0.000012821963,0.00005539017,0.001262556,0.000066212866,0.00012788679,0.00095953874],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9909881,0.0032876946,0.0011563366,0.0012274493,0.0023358755,0.0010045945],"domain_scores_gemma":[0.9954352,0.000877398,0.0006716809,0.0022358748,0.00055318617,0.0002266931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061842403,0.0005931002,0.0039238106,0.0013691598,0.0004356295,0.000394817,0.0031115038,0.00022129552,0.000007768536],"category_scores_gemma":[0.0014037843,0.00037864048,0.0007023316,0.007732911,0.00012859546,0.00044133252,0.0015660783,0.0022753442,0.00023175907],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4916434e-7,0.000027538908,5.343251e-7,0.9689293,0.00020444428,0.000100822115,0.000023048151,0.0000112798,4.4444608e-8,0.0010736672,0.000043062253,0.029585931],"study_design_scores_gemma":[0.000042124328,0.00012841482,3.2502697e-8,0.94595724,0.0006161696,0.0001570863,0.000012906582,0.012305352,1.983981e-7,0.00010494279,0.040218882,0.00045662627],"about_ca_topic_score_codex":0.00005454585,"about_ca_topic_score_gemma":0.00000649045,"teacher_disagreement_score":0.13432567,"about_ca_system_score_codex":0.00057710905,"about_ca_system_score_gemma":0.0005805263,"threshold_uncertainty_score":0.99986655},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10331513278271896,"score_gpt":0.2758739453762855,"score_spread":0.17255881259356654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322751637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5915803,0.000020647381,0.40780178,0.00006226628,0.000045139455,0.00013854959,0.00000113497,0.000009577985,0.000340626],"genre_scores_gemma":[0.9585967,1.5282897e-7,0.041353922,0.000020478386,0.000015054012,0.0000017924345,2.640555e-7,0.000008333154,0.0000032938694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943043,0.004037138,0.00069413777,0.00016337639,0.0006892469,0.00011178983],"domain_scores_gemma":[0.99807274,0.00031245916,0.0010568185,0.00030705094,0.00021196574,0.00003897277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005321373,0.00010119552,0.0002779581,0.0002011071,0.00018161527,0.000021699983,0.0011275077,0.000004608787,0.000005694137],"category_scores_gemma":[0.00024193292,0.00007516953,0.00011817906,0.0005128438,0.000026638703,0.00018381065,0.00060778233,0.00027408372,1.3149725e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031827617,0.00015791488,0.0023849194,0.0000063219723,0.00008022134,0.0000072340727,0.012970868,0.98029065,0.0022487007,0.000082682585,0.000018837676,0.0014333944],"study_design_scores_gemma":[0.000537235,0.0008646654,0.018123982,0.00006744446,0.000034490058,0.000009905712,0.007941086,0.9709042,0.0013067541,0.00011035511,0.000006491233,0.00009339986],"about_ca_topic_score_codex":0.0000023887696,"about_ca_topic_score_gemma":6.9379746e-7,"teacher_disagreement_score":0.36701643,"about_ca_system_score_codex":0.00007010536,"about_ca_system_score_gemma":0.000041664523,"threshold_uncertainty_score":0.30653244},"labels":[],"label_agreement":null},{"id":"W4322764463","doi":"10.1038/s41597-023-02015-3","title":"The Three Terms Task - an open benchmark to compare human and artificial semantic representations","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"","keywords":"Computer science; Semantic memory; Natural language processing; Artificial intelligence; Semantic similarity; Task (project management); Benchmark (surveying); Word (group theory); Similarity (geometry); Associative property; Noun; Representation (politics); Cognition; Linguistics; Psychology; Mathematics","score_opus":0.14608141974920205,"score_gpt":0.4256313126982627,"score_spread":0.27954989294906063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322764463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17579252,0.0000860263,0.7963852,0.01414136,0.002382418,0.0032222548,0.001645191,0.0021539766,0.004191012],"genre_scores_gemma":[0.95876473,0.00000442477,0.035988793,0.00013659403,0.00008868626,0.000082386985,0.0026092445,0.000018263043,0.0023068846],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99752355,0.00008811398,0.0003051647,0.0012752996,0.00045103062,0.000356831],"domain_scores_gemma":[0.99381554,0.000117021176,0.000096965574,0.005727247,0.00008674231,0.00015651232],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00216942,0.00012079532,0.00015365459,0.00022370304,0.0022210635,0.0049931067,0.009421047,0.000016429882,0.000013556624],"category_scores_gemma":[0.00017966355,0.00009184183,0.000018841112,0.0021587822,0.00031119288,0.0022756506,0.010258335,0.00009851468,0.00014605575],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007401924,0.0001555034,0.0041626533,0.000013214506,0.000055631972,0.000041013664,0.0018290624,0.0001677357,0.037545882,0.17699577,0.60323256,0.17579354],"study_design_scores_gemma":[0.00021829121,0.00009994993,0.06902393,0.00006365542,0.00005082445,0.000012466074,0.0007002301,0.26270416,0.0032574972,0.52527076,0.13786203,0.00073616207],"about_ca_topic_score_codex":0.00020267874,"about_ca_topic_score_gemma":0.009899545,"teacher_disagreement_score":0.7829722,"about_ca_system_score_codex":0.000017378894,"about_ca_system_score_gemma":0.00004476262,"threshold_uncertainty_score":0.9990779},"labels":[],"label_agreement":null},{"id":"W4323315086","doi":"10.1002/jcpy.1346","title":"Style, content, and the success of ideas","year":2023,"lang":"en","type":"article","venue":"Journal of Consumer Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Style (visual arts); Function (biology); Perspective (graphical); Context (archaeology); Psychology; Content (measure theory); Class (philosophy); Value (mathematics); Variance (accounting); Natural (archaeology); Writing style; Social psychology; Cognitive psychology; Linguistics; Computer science; Artificial intelligence","score_opus":0.04070871232479893,"score_gpt":0.3619696436976745,"score_spread":0.32126093137287554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323315086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40001428,0.0050229374,0.5788813,0.013427072,0.0006826607,0.0001672994,0.0000017226783,0.000092942,0.0017097751],"genre_scores_gemma":[0.9902252,0.0014787768,0.007527016,0.00064113695,0.000025565807,0.0000023344512,1.2285442e-7,0.000005048512,0.000094819414],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988672,0.00018202153,0.0004969028,0.00012474747,0.00018867417,0.00014044959],"domain_scores_gemma":[0.99834824,0.0004061441,0.00059056963,0.00035244625,0.00025417408,0.000048450114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104112,0.00007785404,0.00034453644,0.0002760902,0.00003885812,0.000023251523,0.00078010926,0.000047582947,0.000008780778],"category_scores_gemma":[0.00015768736,0.000047246864,0.000113054324,0.0005015659,0.00038358496,0.00024340367,0.00011992315,0.000191854,0.0000071925847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008145617,0.0002908822,0.103124954,0.000053947162,0.001474962,0.0003956663,0.0027918404,0.000030534397,0.021660326,0.40460342,0.050434634,0.41432425],"study_design_scores_gemma":[0.016087068,0.0009787,0.3944449,0.00019535415,0.00038360915,0.0028616483,0.00034186244,0.0037487408,0.0076820957,0.50189584,0.07071438,0.000665781],"about_ca_topic_score_codex":0.0000070195247,"about_ca_topic_score_gemma":0.000004509073,"teacher_disagreement_score":0.5902109,"about_ca_system_score_codex":0.0000056037643,"about_ca_system_score_gemma":0.000023783872,"threshold_uncertainty_score":0.19266711},"labels":[],"label_agreement":null},{"id":"W4360764647","doi":"10.1109/icmla55696.2022.00027","title":"Towards Emotion Cause Generation in Natural Language Processing using Deep Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Computer science; Generative grammar; Artificial intelligence; Natural language processing; Emotion recognition; Task analysis; Emotion classification; Deep learning; Cognitive psychology; Speech recognition; Psychology; Engineering","score_opus":0.02281344021177964,"score_gpt":0.312059707008795,"score_spread":0.28924626679701537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360764647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27385426,0.00032511808,0.7252526,0.00006577583,0.000037213646,0.000056420293,5.104839e-8,0.00022937663,0.00017914668],"genre_scores_gemma":[0.8132199,0.000002021702,0.18650436,0.00009270174,0.000029523157,0.000009455829,0.000006537233,0.000005928702,0.00012953914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990697,0.000111406785,0.00015693471,0.00025764882,0.0002478995,0.00015641331],"domain_scores_gemma":[0.9997071,0.000006900118,0.00007926595,0.00015419682,0.000033932938,0.000018592493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027317955,0.00007696902,0.00009189278,0.00022565803,0.0002443984,0.000098382014,0.00027043815,0.000017770057,0.000026692693],"category_scores_gemma":[0.00002965538,0.00007815046,0.000029232546,0.0007486666,0.000008509807,0.0007416989,0.0002804779,0.00025033794,0.0000010422816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020302002,0.000042970212,0.0010122327,0.0000074317995,0.00000634122,0.000048851063,0.005382609,0.12665716,0.07969331,0.0018634511,0.000013404927,0.7852702],"study_design_scores_gemma":[0.00006838969,0.000016031498,0.0003173819,0.0000026055684,0.0000028668585,0.000016225142,0.00037742598,0.99141747,0.0074663907,0.00016025592,0.00005186409,0.00010308571],"about_ca_topic_score_codex":0.00012113883,"about_ca_topic_score_gemma":0.000090396104,"teacher_disagreement_score":0.86476034,"about_ca_system_score_codex":0.00025982223,"about_ca_system_score_gemma":0.00003423918,"threshold_uncertainty_score":0.3186883},"labels":[],"label_agreement":null},{"id":"W4360789531","doi":"10.7202/1097460ar","title":"Approche computationnelle de l’analyse conceptuelle","year":2023,"lang":"fr","type":"article","venue":"Philosophiques","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy; Physics","score_opus":0.28500287423019793,"score_gpt":0.39873394825107233,"score_spread":0.1137310740208744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360789531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015630543,0.010958227,0.8858358,0.08399051,0.00044936614,0.00035149956,0.000017411734,0.002994976,0.0138391275],"genre_scores_gemma":[0.6998726,0.0027482186,0.28186166,0.005600676,0.002384894,0.00012296744,0.00007146791,0.00009490864,0.007242599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99665165,0.00045586657,0.00061614404,0.0008832193,0.0005120213,0.000881074],"domain_scores_gemma":[0.9975509,0.000492269,0.0002904244,0.00093364465,0.00041964403,0.00031311504],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010462782,0.00041904344,0.0005443549,0.00050218374,0.00034156878,0.0002703813,0.0012724894,0.0002675876,0.00013529712],"category_scores_gemma":[0.0003139112,0.00047374368,0.0003500071,0.0022035749,0.0004845848,0.0011448576,0.0006903091,0.00045370564,0.0014738919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010357505,0.00022656063,0.0005083293,0.0001507273,0.00026432847,0.00027867497,0.005140568,0.007058866,0.0014470654,0.83126366,0.12104843,0.032602407],"study_design_scores_gemma":[0.00017844891,0.000088388646,0.00015526266,0.0000972556,0.0000769872,0.000022459053,0.0001363822,0.2719728,0.0056478214,0.67866886,0.04253786,0.000417449],"about_ca_topic_score_codex":0.00012378416,"about_ca_topic_score_gemma":0.000014438553,"teacher_disagreement_score":0.69830954,"about_ca_system_score_codex":0.00033359113,"about_ca_system_score_gemma":0.00023006846,"threshold_uncertainty_score":0.9997714},"labels":[],"label_agreement":null},{"id":"W4361295185","doi":"10.22329/il.v43i1.7639","title":"The Broad Reach of Multivariable Thinking","year":2023,"lang":"en","type":"article","venue":"Informal Logic","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Multivariable calculus; Causal reasoning; Simple (philosophy); Sample (material); Psychology; Cognitive psychology; Social psychology; Cognition; Epistemology; Psychiatry","score_opus":0.020350997013837597,"score_gpt":0.2876073364846006,"score_spread":0.267256339470763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361295185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068300697,0.00009770402,0.9240442,0.000597406,0.00017286117,0.00019117375,0.0000011862245,0.0014495077,0.06661589],"genre_scores_gemma":[0.861982,0.000101368,0.13600095,0.0003200069,0.000032600114,0.00002504915,0.0000042268243,0.0000064021183,0.0015274117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991108,0.000019046636,0.0002537936,0.000111426416,0.00025938262,0.00024553275],"domain_scores_gemma":[0.9990628,0.00019241874,0.00013733399,0.0005064851,0.000075501055,0.000025500436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006472512,0.00007462219,0.00010816648,0.00009187758,0.00021059325,0.00007361427,0.0011651642,0.00004281241,0.0000032979028],"category_scores_gemma":[0.00013923146,0.000046348636,0.000062438834,0.00082712504,0.000055872148,0.00064374035,0.0005370602,0.00011488367,0.00007477961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043786476,0.000010607021,0.00060385786,0.000008559973,0.000020545984,0.0000059774034,0.00085720693,0.0014818851,0.0011834918,0.8764013,0.0013222424,0.11809993],"study_design_scores_gemma":[0.00037801152,0.00021572312,0.011036577,0.000052058716,0.00001453301,0.00001872347,0.00028519306,0.31027764,0.033436008,0.5432174,0.10061545,0.0004526432],"about_ca_topic_score_codex":0.000031272168,"about_ca_topic_score_gemma":0.0000045217603,"teacher_disagreement_score":0.85515195,"about_ca_system_score_codex":0.000014483496,"about_ca_system_score_gemma":0.000025548363,"threshold_uncertainty_score":0.21651845},"labels":[],"label_agreement":null},{"id":"W4365451534","doi":"10.1145/3592604","title":"Semi-Supervised Lexicon-Aware Embedding for News Article Time Estimation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Lexicon; Classifier (UML); Natural language processing; Stop words; WordNet; Machine learning","score_opus":0.008482545231234899,"score_gpt":0.2775019277698858,"score_spread":0.26901938253865093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365451534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012372353,0.000019039928,0.9840189,0.0015538157,0.00001975694,0.00029451816,0.000011121425,0.0011964391,0.00051404274],"genre_scores_gemma":[0.85067046,0.0000062153977,0.14782217,0.0009248933,0.0000272145,0.000113722774,0.00008242947,0.000019548123,0.00033333036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889225,0.000025966216,0.00036106963,0.00021452784,0.00023033425,0.00027582573],"domain_scores_gemma":[0.99918085,0.00009581804,0.0001463092,0.00040453862,0.000076823184,0.00009564367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022335512,0.00016629524,0.00016587501,0.00044389945,0.0004679468,0.0004649879,0.0003744334,0.00008801717,0.000025154115],"category_scores_gemma":[0.000084537336,0.00016277564,0.00007606127,0.00087936467,0.000034387504,0.003021609,0.000020927157,0.00014626261,0.00009685163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011032067,0.000016613816,0.0000035491416,0.000093403985,0.00001050167,0.0000011393082,0.0103537915,0.01153301,0.0009565408,0.00008067015,0.00012051938,0.9768192],"study_design_scores_gemma":[0.00040530963,0.000040675146,0.00003755261,0.000114794166,0.000017392911,0.000009030949,0.0035575877,0.98223925,0.01155669,0.0009964327,0.0008198371,0.00020546658],"about_ca_topic_score_codex":0.0000051354828,"about_ca_topic_score_gemma":0.000003936893,"teacher_disagreement_score":0.97661376,"about_ca_system_score_codex":0.00004983311,"about_ca_system_score_gemma":0.000044021122,"threshold_uncertainty_score":0.6637798},"labels":[],"label_agreement":null},{"id":"W4366136173","doi":"10.2139/ssrn.4421954","title":"A First Look at Information Highlighting in Stack Overflow Answers","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Stack (abstract data type); Computer science; Data science; World Wide Web; Programming language","score_opus":0.010915847275495192,"score_gpt":0.2544394522229137,"score_spread":0.2435236049474185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366136173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019878646,0.0007873014,0.97509116,0.0025027979,0.0004438657,0.00031760728,0.0000039550728,0.0005803582,0.0003943301],"genre_scores_gemma":[0.94042546,0.01997244,0.03656896,0.000294945,0.00039279883,0.00009560705,0.00006148972,0.00008503559,0.002103291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99532026,0.000107934524,0.00090955076,0.00048335516,0.0007088437,0.0024700747],"domain_scores_gemma":[0.9979302,0.00010734457,0.00085814827,0.0008313165,0.00017009262,0.00010284116],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024725015,0.00038052085,0.00047183203,0.0010130956,0.0002701955,0.00040351198,0.00202122,0.00029798647,0.000007679214],"category_scores_gemma":[0.00016280742,0.0003776949,0.00028485904,0.00075817556,0.000037895254,0.0017392465,0.0018315294,0.0044035846,0.00014535483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001457927,0.00024661655,0.016920518,0.00041695908,0.0012888736,0.0001819675,0.007364921,0.1718629,0.00020084086,0.6712032,0.0041465857,0.12602079],"study_design_scores_gemma":[0.0006450776,0.0001811963,0.0013200268,0.0004144849,0.000043264063,0.00019136906,0.00032113038,0.094410926,0.00035950326,0.8948192,0.00641314,0.0008806862],"about_ca_topic_score_codex":0.0001966628,"about_ca_topic_score_gemma":0.0059913923,"teacher_disagreement_score":0.93852216,"about_ca_system_score_codex":0.006990409,"about_ca_system_score_gemma":0.0021369248,"threshold_uncertainty_score":0.9998675},"labels":[],"label_agreement":null},{"id":"W4366431549","doi":"10.23977/jaip.2023.060110","title":"AI Application to Generate an Expected Picture Using Keywords with Stable Diffusion","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Noise (video); Image (mathematics); Artificial intelligence; Generator (circuit theory); Field (mathematics); Painting; Creativity; Diffusion; Process (computing); Computer vision; Visual arts; Law; Mathematics; Art; Power (physics); Programming language","score_opus":0.045394645205839315,"score_gpt":0.3835652351684803,"score_spread":0.338170589962641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366431549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08890315,0.000027493348,0.90800244,0.0025765686,0.00013412777,0.00016391308,6.12583e-7,0.00015276362,0.000038957656],"genre_scores_gemma":[0.55313575,0.000046893532,0.44567445,0.00083865324,0.00025555273,0.0000072912226,0.0000014029773,0.00001790661,0.000022063927],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978641,0.00019406373,0.0006389887,0.00033927424,0.0006647329,0.0002988232],"domain_scores_gemma":[0.99707437,0.00021205624,0.00073891465,0.0005401793,0.0012288246,0.00020567664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001084331,0.00017096155,0.00025535646,0.00051277236,0.00022795323,0.00036598544,0.00083951687,0.00007322101,0.000010667787],"category_scores_gemma":[0.00046824623,0.00013674714,0.00006327155,0.0027055424,0.000034974288,0.003566454,0.00015934311,0.00038497747,0.000041166528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003623505,0.00041917944,0.00009319669,0.00000871648,0.0000747587,0.00017714304,0.0048554563,0.2786302,0.4168127,0.015532489,0.00024115462,0.28279266],"study_design_scores_gemma":[0.000033705408,0.0006037976,0.00004764417,0.000047203797,0.000070753784,0.00019126009,0.0019974315,0.7279571,0.24838099,0.014945974,0.00542383,0.00030028468],"about_ca_topic_score_codex":0.000050369745,"about_ca_topic_score_gemma":0.00003104513,"teacher_disagreement_score":0.46423262,"about_ca_system_score_codex":0.0001342427,"about_ca_system_score_gemma":0.00015158071,"threshold_uncertainty_score":0.55763865},"labels":[],"label_agreement":null},{"id":"W4367293423","doi":"10.5220/0011826700003467","title":"Novel Topic Models for Content Based Recommender Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Recommender system; Computer science; Content (measure theory); Information retrieval; Mathematics","score_opus":0.2072451708935658,"score_gpt":0.32651371135770835,"score_spread":0.11926854046414254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367293423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011301462,0.000016357666,0.9947619,0.0018122453,0.00015775449,0.00031150837,0.0000027732676,0.0012233523,0.0016011316],"genre_scores_gemma":[0.278103,0.000006691491,0.71378154,0.0010681526,0.000044948596,0.00035399947,0.000011142021,0.000014334921,0.006616194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999137,0.000013435515,0.00019674019,0.00028939816,0.00014273557,0.00022070046],"domain_scores_gemma":[0.9991513,0.00015032769,0.000053234067,0.000482777,0.00011389804,0.00004844926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025289322,0.00009151785,0.00015596038,0.00014201262,0.00006437628,0.00008364187,0.00050861493,0.00003961415,0.000003498122],"category_scores_gemma":[0.000022069298,0.00007561752,0.00009016405,0.00037591156,0.000009231535,0.00034851403,0.00010560892,0.00003976878,0.000015809042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033716872,0.00006480419,0.00003847059,0.000038211387,0.000039535826,0.0000015691763,0.0000716384,0.021448346,0.006548328,0.940809,0.013880869,0.017055862],"study_design_scores_gemma":[0.00022340246,0.000028793522,0.000018508763,0.000009591641,0.0000039062597,5.7838713e-7,0.00003100147,0.9815894,0.00401685,0.009383904,0.0045848885,0.00010919347],"about_ca_topic_score_codex":0.000048244896,"about_ca_topic_score_gemma":0.000009539651,"teacher_disagreement_score":0.96014106,"about_ca_system_score_codex":0.000045276127,"about_ca_system_score_gemma":0.000022242239,"threshold_uncertainty_score":0.3083593},"labels":[],"label_agreement":null},{"id":"W4378364165","doi":"10.1145/3589462.3589463","title":"ConfSys - An Intelligent Conference Management System","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Process (computing); Automation; Relevance (law); Metadata; Salient; Matching (statistics); Quality (philosophy); Software engineering; Information retrieval; World Wide Web; Data science; Artificial intelligence; Engineering; Programming language","score_opus":0.04069419251764079,"score_gpt":0.30958856042868116,"score_spread":0.2688943679110404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378364165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010082847,0.000007768824,0.9610738,0.00017680839,0.00008997779,0.00016652582,4.318221e-7,0.0038050357,0.033671338],"genre_scores_gemma":[0.8351405,0.0000426583,0.16100149,0.0001085273,0.0000151195645,0.000048169917,0.000004677596,0.000007510543,0.0036313378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882114,0.000044003882,0.00021314259,0.0004097126,0.00026515842,0.00024684885],"domain_scores_gemma":[0.99889404,0.000021340471,0.00005298858,0.00086375396,0.00007469266,0.00009316295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000289303,0.00011461255,0.00014459992,0.00023213585,0.000075648946,0.00015810532,0.0011149095,0.000030493891,0.000029000796],"category_scores_gemma":[0.0000034792736,0.000098612734,0.00004780085,0.0007802231,0.00002539268,0.00043947957,0.00044176826,0.000055513232,0.0007527539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.8603397e-7,0.000011971678,0.000026094713,0.00001790979,0.000015935599,0.000042225605,0.00013273617,0.00006606106,0.00018856948,0.9302587,0.00075012073,0.06848922],"study_design_scores_gemma":[0.00018769066,0.00014421952,0.0008494457,0.000116421375,0.000026518135,0.000017941818,0.0024653014,0.893971,0.02954284,0.047892917,0.024152339,0.0006333578],"about_ca_topic_score_codex":0.000019574834,"about_ca_topic_score_gemma":0.000011491095,"teacher_disagreement_score":0.8939049,"about_ca_system_score_codex":0.00006049454,"about_ca_system_score_gemma":0.000011555646,"threshold_uncertainty_score":0.967538},"labels":[],"label_agreement":null},{"id":"W4379184890","doi":"10.1155/2023/2570824","title":"A Function Area Division Approach for Autonomous Transportation System Based on Text Similarity","year":2023,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Shenzhen Science and Technology Innovation Program; National Key Research and Development Program of China","keywords":"Similarity (geometry); Function (biology); Cluster analysis; Computer science; Context (archaeology); Hierarchical clustering; Data mining; Artificial intelligence; Geography; Image (mathematics)","score_opus":0.017789884034501297,"score_gpt":0.2629471552590599,"score_spread":0.24515727122455858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379184890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03691436,0.000027976357,0.9615759,0.00017319905,0.00029062052,0.0004706279,0.000029028144,0.00045877692,0.000059475533],"genre_scores_gemma":[0.7621598,0.000012137556,0.23741233,0.000066285094,0.00004807227,0.000056322966,0.00020666889,0.000022430577,0.000015952482],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769723,0.000050177056,0.00091979065,0.00040313386,0.0006512676,0.00027839656],"domain_scores_gemma":[0.9979416,0.00019584123,0.0008803974,0.00035090744,0.0005158472,0.00011541596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066092465,0.00024126185,0.0004232288,0.00067285495,0.00017943008,0.000054907996,0.00041247002,0.00012405693,0.0000019910574],"category_scores_gemma":[0.00003548241,0.00021943342,0.0003793143,0.0011377146,0.00002471522,0.0012913044,0.0000019117003,0.0002369534,0.000002281198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030514615,0.00015317068,0.00047367078,0.00016666314,0.000040084942,0.000019715388,0.00046880383,0.9548883,0.0043058926,0.005923275,0.00009714244,0.033158123],"study_design_scores_gemma":[0.0034328997,0.0020421213,0.13917345,0.00036901544,0.00025918646,0.0000043524674,0.0006581464,0.83703816,0.009684229,0.005522314,0.0012299729,0.00058616826],"about_ca_topic_score_codex":0.0000024456403,"about_ca_topic_score_gemma":0.000011458402,"teacher_disagreement_score":0.7252454,"about_ca_system_score_codex":0.00018463492,"about_ca_system_score_gemma":0.00009564542,"threshold_uncertainty_score":0.89482355},"labels":[],"label_agreement":null},{"id":"W4379984080","doi":"10.1109/aeis59450.2022.00030","title":"Behavioral Mapping, Using NLP to Predict Individual Behavior : Focusing on Towards/Away Behavior","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Mitacs","keywords":"Artificial intelligence; Computer science; Natural language processing","score_opus":0.08143062791456686,"score_gpt":0.3463467068363596,"score_spread":0.26491607892179275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379984080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.588196,0.000017793873,0.40900937,0.00017485023,0.00030874545,0.0007995094,0.000037572812,0.0010165691,0.00043963484],"genre_scores_gemma":[0.71541965,7.192452e-7,0.28294966,0.0005333085,0.00007107147,0.00059039285,0.000021644686,0.000040044033,0.00037347872],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99601865,0.0001625443,0.0005771786,0.0010659477,0.00144346,0.0007322459],"domain_scores_gemma":[0.99807626,0.000031867334,0.00021338972,0.0012759208,0.00011424835,0.00028828572],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057010044,0.00038980265,0.00041172223,0.0009192989,0.00080800586,0.00031239618,0.0022449747,0.00008742739,0.00033647657],"category_scores_gemma":[0.000019322193,0.00041119417,0.0002470318,0.0016050924,0.00005556275,0.0007178123,0.002742882,0.0005436277,0.000030565694],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041569372,0.005225096,0.04967141,0.000015083803,0.0001061445,0.0013655504,0.006019157,0.0035443248,0.06058709,0.011302127,0.004164124,0.8579583],"study_design_scores_gemma":[0.006809125,0.016959507,0.33835417,0.00036539912,0.0035649505,0.00247652,0.0067561036,0.06542596,0.40349504,0.0053336984,0.13507381,0.015385709],"about_ca_topic_score_codex":0.00031791424,"about_ca_topic_score_gemma":0.00003123788,"teacher_disagreement_score":0.8425726,"about_ca_system_score_codex":0.0005912974,"about_ca_system_score_gemma":0.00017052852,"threshold_uncertainty_score":0.999834},"labels":[],"label_agreement":null},{"id":"W4380446958","doi":"10.1177/07356331231178873","title":"Predicting the Persuasiveness of Influence Strategies From Student Online Learning Behaviour Using Machine Learning Methods","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Computing Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Adaptation (eye); Artificial intelligence; Machine learning; Psychology","score_opus":0.11991158000098773,"score_gpt":0.5442643351950351,"score_spread":0.4243527551940474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380446958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8770576,0.00053778203,0.12131798,0.0007991653,0.00013760658,0.0000880988,0.0000013584539,0.000038205835,0.000022170992],"genre_scores_gemma":[0.8250351,0.000053409745,0.17457883,0.000008583549,0.00026225718,0.0000014206913,0.000005286139,0.00001313688,0.000041983298],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99539435,0.0017451497,0.00078479666,0.00027827363,0.0014287035,0.0003686981],"domain_scores_gemma":[0.9897267,0.0069469246,0.00083779555,0.00029435215,0.0021005266,0.00009368111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077380375,0.00013755453,0.00031576856,0.0007474232,0.0007209768,0.0002871783,0.00174936,0.000055740755,0.000013044759],"category_scores_gemma":[0.0030892726,0.00010607821,0.00014653125,0.002130585,0.00017766908,0.0006334513,0.0008952485,0.0016677881,0.0000019522029],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001227387,0.00017441506,0.5328297,0.000022401784,0.00011351897,0.0000096263975,0.007546728,0.4244098,0.025194434,0.0021459062,0.000011763628,0.007529419],"study_design_scores_gemma":[0.00019183508,0.00023187976,0.4443265,0.00038017475,0.000033068896,0.000045203946,0.0123268105,0.53054154,0.0025866975,0.009123214,0.00006574383,0.00014729946],"about_ca_topic_score_codex":0.0005036816,"about_ca_topic_score_gemma":0.000015278012,"teacher_disagreement_score":0.10613176,"about_ca_system_score_codex":0.0002042599,"about_ca_system_score_gemma":0.00084576185,"threshold_uncertainty_score":0.7245802},"labels":[],"label_agreement":null},{"id":"W4380761095","doi":"10.2139/ssrn.4477833","title":"Demand Forecasting of New Products Using Language Models on the Product Descriptions","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Product (mathematics); Demand forecasting; Econometrics; Computer science; Economics; Mathematics; Operations management","score_opus":0.10737581900762051,"score_gpt":0.31181763415626995,"score_spread":0.20444181514864945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380761095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04856532,0.003112152,0.94545025,0.0019548452,0.00023497116,0.00040369353,0.0000018665522,0.00019623844,0.000080687554],"genre_scores_gemma":[0.9204604,0.0011907009,0.07671383,0.00004126132,0.000596411,0.000014375276,0.0000035478774,0.00005483742,0.00092465227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965615,0.00018464343,0.000550631,0.00062892574,0.0005614515,0.0015128166],"domain_scores_gemma":[0.9976057,0.000088803594,0.0007821158,0.0011844209,0.00027304055,0.00006592104],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029298514,0.00030699893,0.00039448022,0.00038741602,0.00028699933,0.0001817066,0.0018993018,0.000100448655,0.0000014890101],"category_scores_gemma":[0.0004178907,0.00022279129,0.0002319145,0.0007375834,0.000053580105,0.00040025974,0.0008464378,0.0033868956,0.0000035214844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024150057,0.00013331861,0.000066345805,0.000092558024,0.00082600716,0.000024500692,0.0033983355,0.45494235,0.007271369,0.44975084,0.00048028052,0.08298994],"study_design_scores_gemma":[0.00007258609,0.00006846279,0.000006598886,0.00023798781,0.00007089795,0.00015725693,0.00018744411,0.20210221,0.005730702,0.7911364,0.000017457745,0.00021201004],"about_ca_topic_score_codex":0.0002209403,"about_ca_topic_score_gemma":0.00029823658,"teacher_disagreement_score":0.8718951,"about_ca_system_score_codex":0.00087343226,"about_ca_system_score_gemma":0.0040021213,"threshold_uncertainty_score":0.99891233},"labels":[],"label_agreement":null},{"id":"W4383818705","doi":"10.33423/jabe.v25i3.6208","title":"Conceptual Meta-Models: An Example Correlating Anthony’s Triangle, Simon’s Structure, and Stevens’ Scale of Measurement","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Business and Economics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Acknowledgement; Simple (philosophy); Brainstorming; Scale (ratio); Computer science; Craft; Epistemology; Mathematical economics; Core (optical fiber); Econometrics; Artificial intelligence; Data science; Psychology; Mathematics; Philosophy; Visual arts; Art","score_opus":0.11024792538248765,"score_gpt":0.253274796042182,"score_spread":0.14302687065969436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383818705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81269425,0.000422766,0.18643075,0.00007472764,0.00010119346,0.00011638155,0.000006424822,0.000036663132,0.00011681288],"genre_scores_gemma":[0.94166756,0.000443053,0.05776338,0.000044341075,0.00006130992,0.0000028378747,0.0000018421673,0.000012610741,0.0000030546641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987373,0.00002252147,0.00065802503,0.00024820014,0.00016538604,0.00016857867],"domain_scores_gemma":[0.998521,0.00007815216,0.000784034,0.00025030726,0.0002719901,0.00009451894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008702603,0.0001593072,0.00068233703,0.00023786158,0.00008726071,0.000093425646,0.00030898818,0.000069095804,0.0000043452806],"category_scores_gemma":[0.00001640416,0.00013178191,0.00008046461,0.00030286622,0.00010315077,0.0008495628,0.00016237478,0.0001245408,2.7569047e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042686216,0.0002867373,0.0021601743,0.00019955236,0.0026088047,0.000028593022,0.009343768,0.35044834,0.017213905,0.23466328,0.00048423556,0.38213575],"study_design_scores_gemma":[0.0048817615,0.0005366017,0.013325577,0.00012260032,0.0017152656,0.000117630334,0.005225175,0.53793,0.019710772,0.4122007,0.0028541938,0.0013797411],"about_ca_topic_score_codex":0.00003777347,"about_ca_topic_score_gemma":0.0000685284,"teacher_disagreement_score":0.38075602,"about_ca_system_score_codex":0.00004353555,"about_ca_system_score_gemma":0.00007263558,"threshold_uncertainty_score":0.537391},"labels":[],"label_agreement":null},{"id":"W4385567143","doi":"10.18653/v1/2022.finnlp-1.10","title":"A Taxonomical NLP Blueprint to Support Financial Decision Making through Information-Centred Interactions","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Blueprint; Usability; Taxonomy (biology); Visualization; Artificial intelligence; Data science; Software; Natural language processing; Human–computer interaction","score_opus":0.026220031128080044,"score_gpt":0.3076132401009309,"score_spread":0.28139320897285086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385567143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0085886875,0.0000020298269,0.9845437,0.00078395195,0.00025225774,0.00022489269,0.000004209942,0.00037281655,0.0052274726],"genre_scores_gemma":[0.5470648,7.3367204e-7,0.45085755,0.0018873555,0.000016975071,0.00009464241,0.0000037044674,0.0000028218521,0.00007141424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987724,0.000030999774,0.00039765777,0.00026285037,0.00030828576,0.00022780684],"domain_scores_gemma":[0.9991111,0.00010099106,0.000114451395,0.00054693426,0.00006862701,0.000057870817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013134023,0.00011067331,0.00014765435,0.00021780183,0.00030687355,0.00014771856,0.00091034,0.000019404217,0.00081410125],"category_scores_gemma":[0.00014285064,0.00011263174,0.00010375202,0.00064123236,0.000012207871,0.0018238089,0.0017626131,0.00020357227,0.00027293598],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005203935,0.00017959767,0.0004139132,0.0000030632223,0.000018979892,0.000014070844,0.003201499,0.010918538,0.00023888041,0.26270238,0.053688675,0.6685684],"study_design_scores_gemma":[0.00030133562,0.00020590732,0.0013091115,0.000013993863,0.000009615773,0.000054476943,0.0004157637,0.057330232,0.0019369705,0.04139081,0.8966064,0.0004254053],"about_ca_topic_score_codex":0.00002471046,"about_ca_topic_score_gemma":0.000043074822,"teacher_disagreement_score":0.8429177,"about_ca_system_score_codex":0.0003056858,"about_ca_system_score_gemma":0.00010273405,"threshold_uncertainty_score":0.89138377},"labels":[],"label_agreement":null},{"id":"W4385834249","doi":"10.1109/access.2023.3305260","title":"Summarizing Students’ Free Responses for an Introductory Algebra-Based Physics Course Survey Using Cluster and Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Sentiment analysis; Likert scale; Computer science; Valence (chemistry); Set (abstract data type); Cluster grouping; Mathematics education; Macro; Natural language processing; Text messaging; Artificial intelligence; Information retrieval; Psychology; Statistics; World Wide Web; Mathematics","score_opus":0.10250271593371403,"score_gpt":0.42651022883468137,"score_spread":0.32400751290096735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385834249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4713058,0.000020423859,0.5280438,0.000074859156,0.00009759415,0.000196788,0.000022268778,0.00023710319,0.0000013492036],"genre_scores_gemma":[0.9593405,0.000007099624,0.040049523,0.0002735624,0.00014074236,0.000049345046,0.000050016228,0.00002812168,0.00006106122],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976015,0.0003774753,0.00033540258,0.0007762514,0.0005271512,0.00038219115],"domain_scores_gemma":[0.9974292,0.00060197915,0.00022286447,0.0013620167,0.00027210708,0.00011182748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017712074,0.00022424031,0.00040223252,0.0004991983,0.00026485766,0.00074394245,0.0020748933,0.00006383018,0.0000020052655],"category_scores_gemma":[0.00013509145,0.00022486506,0.00014313728,0.0025743076,0.00008361554,0.0015370981,0.00067306607,0.000105944135,0.0000019046627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014680678,0.00038194607,0.9391546,0.00005143945,0.001195869,0.000014359139,0.0004310055,0.03766421,0.0078385705,0.00027048885,0.0022536865,0.010597014],"study_design_scores_gemma":[0.00067333336,0.00008035827,0.2721266,0.000017981252,0.00051437697,3.8160596e-7,0.000019349884,0.695314,0.027379304,0.0033501065,0.000073180214,0.00045102672],"about_ca_topic_score_codex":0.00029689007,"about_ca_topic_score_gemma":0.00086443045,"teacher_disagreement_score":0.667028,"about_ca_system_score_codex":0.00008053661,"about_ca_system_score_gemma":0.000079039506,"threshold_uncertainty_score":0.9169731},"labels":[],"label_agreement":null},{"id":"W4386454333","doi":"10.2139/ssrn.4559513","title":"An Exploration of the Effects of Message Framing on Plant-based Meat Alternatives","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of the Fraser Valley","funders":"","keywords":"Framing (construction); Business; Advertising; Engineering; Civil engineering","score_opus":0.013047608597176692,"score_gpt":0.28604436140732004,"score_spread":0.27299675281014335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386454333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18641107,0.00014244772,0.8128441,0.0002697213,0.0001035225,0.00010051778,7.0907794e-7,0.000083373925,0.000044527515],"genre_scores_gemma":[0.99804413,0.0003238193,0.0014763402,0.000052425174,0.00004022667,0.000005199843,0.0000013973267,0.000009321772,0.000047144884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984223,0.00020528896,0.00022627029,0.00016304033,0.00041210908,0.00057096913],"domain_scores_gemma":[0.9990055,0.00019582146,0.00031723405,0.00038194915,0.00007074809,0.000028742154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007399714,0.00010162435,0.00016386624,0.00023217137,0.00010721627,0.000025520942,0.00090763415,0.000036003144,6.5758655e-7],"category_scores_gemma":[0.000108920496,0.00007000282,0.00010768956,0.0006044505,0.00004140695,0.0007658321,0.00005283679,0.00054755853,0.0000014054025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048793,0.00024798073,0.0016614178,0.000058897593,0.00022545423,0.00001151106,0.0015687867,0.008109289,0.1796655,0.7320299,0.00007365798,0.07629876],"study_design_scores_gemma":[0.0003702839,0.000839988,0.00080336415,0.0001519012,0.000023178196,0.0000074007667,0.00020736495,0.029211164,0.6168156,0.3513978,0.000045688153,0.00012622212],"about_ca_topic_score_codex":0.000012508479,"about_ca_topic_score_gemma":0.00009182071,"teacher_disagreement_score":0.81163305,"about_ca_system_score_codex":0.00014990135,"about_ca_system_score_gemma":0.00033877694,"threshold_uncertainty_score":0.2854632},"labels":[],"label_agreement":null},{"id":"W4386565867","doi":"10.1016/j.infsof.2023.107321","title":"A large-scale exploratory study of android sports apps in the google play store","year":2023,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; World Wide Web; Android (operating system); Empirical research; Sentiment analysis; App store; Set (abstract data type); Data science; Internet privacy; Artificial intelligence","score_opus":0.008951972813567967,"score_gpt":0.25349437146295273,"score_spread":0.24454239864938476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386565867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7675709,0.00003950123,0.23071976,0.00026125295,0.000026465179,0.0002934672,0.0000024011597,0.001011559,0.00007467483],"genre_scores_gemma":[0.9941708,0.00004011971,0.005557369,0.00012206705,0.0000026675643,0.00009119497,0.0000065073327,0.0000027897297,0.0000064815545],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9991386,0.00002588406,0.00033423444,0.00012041584,0.00021914837,0.000161735],"domain_scores_gemma":[0.9992405,0.000047268382,0.0001530672,0.0004786651,0.00006471942,0.000015785577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004648831,0.00008511933,0.00016186808,0.0007952178,0.000077409364,0.000026224663,0.0005290721,0.00009553372,0.0000022101356],"category_scores_gemma":[0.00008288944,0.00006529886,0.000019467516,0.0017440813,0.000051622195,0.00092937116,0.00025746363,0.00015751216,0.0000099894305],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017832124,0.0005437483,0.24311912,0.000073217976,0.000037386548,0.00006260822,0.18656348,0.0004033291,0.00005207652,0.029405503,0.0026462104,0.5370755],"study_design_scores_gemma":[0.007518258,0.0027726411,0.24871108,0.00023533299,0.00007067375,0.00020324209,0.4084802,0.050431322,0.0034844247,0.16572775,0.11047684,0.0018882324],"about_ca_topic_score_codex":0.0000035012038,"about_ca_topic_score_gemma":0.000104055565,"teacher_disagreement_score":0.53518724,"about_ca_system_score_codex":0.000016084556,"about_ca_system_score_gemma":0.000019741956,"threshold_uncertainty_score":0.26628104},"labels":[],"label_agreement":null},{"id":"W4386645575","doi":"10.1007/978-3-031-41456-5_16","title":"An Abstractive Automatic Summarization Approach Based on a Text Comprehension Model of Cognitive Psychology","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université du Québec à Trois-Rivières","funders":"","keywords":"Automatic summarization; Computer science; Natural language processing; Comprehension; Cognition; Artificial intelligence; Cognitive model; Cognitive science; Information retrieval; Programming language; Psychology","score_opus":0.035853468901795464,"score_gpt":0.31732284320819737,"score_spread":0.2814693743064019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386645575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013876714,0.0000147278815,0.99573374,0.00013155903,0.00019532461,0.0005820815,0.000018392604,0.00051948125,0.0026659458],"genre_scores_gemma":[0.41163486,0.000008500431,0.58727014,0.0009156891,0.000042165164,0.000019914882,0.000038096252,0.0000391777,0.00003146838],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958509,0.00008025989,0.00068993453,0.0018017482,0.0011086935,0.00046842828],"domain_scores_gemma":[0.9961227,0.0009134409,0.00065761723,0.0015385009,0.0006370311,0.00013066431],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072941626,0.00053519435,0.0007384297,0.0018635951,0.0001650651,0.00014373162,0.0023763222,0.00041196047,0.0000048423626],"category_scores_gemma":[0.00017408501,0.0005031169,0.00015717116,0.001136178,0.00073537516,0.0006637916,0.00043288118,0.0007538704,0.000016225213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012829819,0.00015421721,0.0000104829305,0.000034001885,0.000012374334,0.000011762496,0.0003697708,0.641971,0.00069010054,0.0069423504,0.0000043051637,0.3497868],"study_design_scores_gemma":[0.00023655966,0.00034266643,0.00017335928,0.00043282812,0.000017102848,0.0000044062854,3.2935526e-7,0.870701,0.0015556215,0.12612925,0.0000019963554,0.00040485474],"about_ca_topic_score_codex":0.000007191013,"about_ca_topic_score_gemma":0.00001749794,"teacher_disagreement_score":0.41149607,"about_ca_system_score_codex":0.00018179278,"about_ca_system_score_gemma":0.0003665603,"threshold_uncertainty_score":0.99974203},"labels":[],"label_agreement":null},{"id":"W4388422667","doi":"10.18280/isi.280530","title":"Leveraging Latent Dirichlet Allocation for Feature Extraction in User Comments: Enhancements to User-Centered Design in Indonesian Financial Technology","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Indonesian; Computer science; Dirichlet distribution; Topic model; Data mining; Information retrieval; Mathematics","score_opus":0.02612105426512728,"score_gpt":0.29246254596887966,"score_spread":0.2663414917037524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388422667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13122457,0.0000110603005,0.8663075,0.00079700735,0.00015562079,0.0010741152,0.000003976723,0.00039442832,0.00003170805],"genre_scores_gemma":[0.8977408,0.000023605111,0.10095462,0.00035373232,0.000016813523,0.000750814,0.00011398953,0.000011146539,0.00003451476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836576,0.0000694713,0.00063539617,0.00026316976,0.00024254824,0.00042364813],"domain_scores_gemma":[0.99906117,0.00007165672,0.00028147295,0.00035165553,0.00018777892,0.00004625944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007082648,0.00019411101,0.00025524935,0.0019202806,0.00014325304,0.00017489292,0.00050656823,0.0001800729,0.0000014420935],"category_scores_gemma":[0.00031358137,0.00021384805,0.000044759927,0.002950838,0.0000248453,0.0046473364,0.00017317217,0.000180293,0.000032711167],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031710727,0.0003468409,0.07204185,0.00042392212,0.00007256794,0.000024636642,0.017565876,0.045681037,0.017918257,0.018779973,0.0069866013,0.8198413],"study_design_scores_gemma":[0.005903257,0.0009147956,0.377097,0.0018998317,0.00003935679,0.00003120909,0.0018119268,0.39124826,0.13314144,0.06212579,0.023665,0.0021221128],"about_ca_topic_score_codex":0.00005072318,"about_ca_topic_score_gemma":0.00007255331,"teacher_disagreement_score":0.8177192,"about_ca_system_score_codex":0.00080633187,"about_ca_system_score_gemma":0.000066847984,"threshold_uncertainty_score":0.872047},"labels":[],"label_agreement":null},{"id":"W4388481904","doi":"10.48550/arxiv.2311.02985","title":"Towards a Transformer-Based Reverse Dictionary Model for Quality Estimation of Definitions","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transformer; Computer science; Artificial intelligence; Engineering; Electrical engineering; Voltage","score_opus":0.28084115684796945,"score_gpt":0.2807720832417779,"score_spread":0.00006907360619157199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388481904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007928386,0.0000071748973,0.9900425,0.00025047,0.000082687286,0.0004659496,0.00023739263,0.00067201187,0.00031344517],"genre_scores_gemma":[0.7665694,0.00006276285,0.23294654,0.000043244265,0.000008262974,0.000012956631,0.00013515844,0.0000155471,0.00020617012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984519,0.000078199155,0.0003621495,0.00076178176,0.00013019348,0.00021579683],"domain_scores_gemma":[0.99809885,0.00019991798,0.00036119545,0.00095587637,0.00030234174,0.00008179146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038523186,0.0002305202,0.00038364652,0.00046792303,0.00014067629,0.00002526483,0.0009590079,0.00023265847,0.0000039732304],"category_scores_gemma":[0.000089601,0.0002849211,0.00048038605,0.0007146936,0.00010932161,0.0004227306,0.00023474572,0.00025226088,0.000007006553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020034095,0.00007243103,0.000028365446,0.00012276626,0.000043172255,0.0000038367016,0.00009563122,0.73041683,0.000039433235,0.268428,0.000098928824,0.0006305545],"study_design_scores_gemma":[0.00018508063,0.000022758899,0.00008008549,0.00005274127,0.000073353745,1.6319194e-7,0.000014106411,0.5964605,0.0003934712,0.40254906,0.000007980574,0.00016067883],"about_ca_topic_score_codex":0.00014248544,"about_ca_topic_score_gemma":0.0000682096,"teacher_disagreement_score":0.75864094,"about_ca_system_score_codex":0.00022906625,"about_ca_system_score_gemma":0.0004108044,"threshold_uncertainty_score":0.9999603},"labels":[],"label_agreement":null},{"id":"W4389289483","doi":"10.33423/jabe.v25i6.6570","title":"Big Data Measures of Environmental Concern","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Business and Economics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Snapshot (computer storage); Big data; Environmental data; Survey data collection; Environmental pollution; Environmental resource management; Scale (ratio); Data science; Environmental planning; Environmental science; Business; Computer science; Geography; Environmental protection; Data mining; Statistics; Political science; Database; Cartography; Mathematics","score_opus":0.07659842379509464,"score_gpt":0.24882667005392708,"score_spread":0.17222824625883243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389289483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74664026,0.00027662047,0.25161576,0.00044545016,0.0002667596,0.00008046823,0.000024901932,0.00004160084,0.0006081985],"genre_scores_gemma":[0.98480225,0.0023535653,0.012660615,0.000047367317,0.00011577523,6.481191e-7,0.000004036072,0.0000067722585,0.000008983196],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993235,0.000004188,0.0003504341,0.00014902803,0.000076366545,0.00009646666],"domain_scores_gemma":[0.99910975,0.000035539113,0.0004127772,0.00037705037,0.000024627203,0.000040274193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033502656,0.00007571916,0.00024778882,0.00014934895,0.000034537126,0.000043048898,0.00072272663,0.000033030272,0.0000025291838],"category_scores_gemma":[0.000008201816,0.00006674438,0.000027843947,0.00016734666,0.0000644215,0.0003822405,0.00044822524,0.00006420692,0.000003491354],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004335671,0.00006322914,0.0011822088,0.000024838017,0.00013136325,0.0000103073435,0.00023550479,0.0030043845,0.0124476,0.00939281,0.0007087848,0.9727556],"study_design_scores_gemma":[0.0062026996,0.0003841035,0.20906167,0.0002169185,0.00047051298,0.0004063256,0.0017487608,0.17499019,0.07216322,0.27403817,0.2579797,0.0023377384],"about_ca_topic_score_codex":0.0000027630222,"about_ca_topic_score_gemma":0.0000037603857,"teacher_disagreement_score":0.97041786,"about_ca_system_score_codex":0.000022301112,"about_ca_system_score_gemma":0.000037210593,"threshold_uncertainty_score":0.27217567},"labels":[],"label_agreement":null},{"id":"W4389519544","doi":"10.18653/v1/2023.newsum-1.12","title":"Analyzing Multi-Sentence Aggregation in Abstractive Summarization via the Shapley Value","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Nvidia","keywords":"Automatic summarization; Shapley value; Computer science; Sentence; Value (mathematics); Natural language processing; Artificial intelligence; Mathematics; Game theory; Machine learning; Mathematical economics","score_opus":0.02542860140765619,"score_gpt":0.3057754320863267,"score_spread":0.2803468306786705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010599694,0.00001910551,0.9874541,0.0008017593,0.000038865277,0.00016824926,3.5367756e-7,0.0004181825,0.00049965695],"genre_scores_gemma":[0.90986884,0.00006474785,0.08950881,0.00011500753,0.000015527909,0.000030448831,0.00000874015,0.000007045155,0.00038081344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989725,0.000073328265,0.00023328148,0.00032304536,0.00019832801,0.00019951921],"domain_scores_gemma":[0.99919343,0.00017278503,0.000116274685,0.00040827072,0.00008242139,0.0000268191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004496317,0.000097447926,0.00010490083,0.0002867911,0.0001128967,0.00009252543,0.0005966779,0.00004193478,0.000008366227],"category_scores_gemma":[0.000118382624,0.00007202004,0.000049791175,0.0022571324,0.00003346022,0.00091401587,0.00019454639,0.00012826879,0.000085706844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011187865,0.00023283478,0.08283867,0.000021454354,0.000086125925,0.000055183504,0.003862323,0.07403051,0.045657672,0.16258469,0.00056779286,0.63005155],"study_design_scores_gemma":[0.00008208282,0.000008137018,0.049033366,0.000014486838,0.0000035890846,0.0000011827299,0.0000636818,0.9284431,0.0125076575,0.009669714,0.000072674644,0.000100370904],"about_ca_topic_score_codex":0.00032915256,"about_ca_topic_score_gemma":0.0004786024,"teacher_disagreement_score":0.89926916,"about_ca_system_score_codex":0.00007831848,"about_ca_system_score_gemma":0.00002014245,"threshold_uncertainty_score":0.2936892},"labels":[],"label_agreement":null},{"id":"W4389519868","doi":"10.18653/v1/2023.findings-emnlp.199","title":"SimCKP: Simple Contrastive Learning of Keyphrase Representations","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Artificial intelligence; Natural language processing; Phrase; Generator (circuit theory); Context (archaeology); Benchmark (surveying); Margin (machine learning); Simple (philosophy); Set (abstract data type); Machine learning; Power (physics)","score_opus":0.01824043602855783,"score_gpt":0.32997400725410264,"score_spread":0.3117335712255448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012989736,0.0000079031115,0.97854304,0.0002613721,0.000015768068,0.00007885278,9.712313e-7,0.00095678854,0.0071455897],"genre_scores_gemma":[0.9505441,0.00001440571,0.047667805,0.00004563653,0.0000104228675,0.000014407095,0.000007934034,0.000005347851,0.0016899509],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991913,0.000048079164,0.00019345715,0.00023122338,0.00017860442,0.00015734664],"domain_scores_gemma":[0.99911207,0.00031673146,0.00009101437,0.00032512035,0.00011325045,0.000041843334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017738243,0.00006520786,0.00013393843,0.00018835565,0.00007604565,0.000025557592,0.00035340298,0.00002350293,0.000043024567],"category_scores_gemma":[0.0002851778,0.00006031818,0.00006552558,0.0012076794,0.00004105765,0.00034196072,0.00020787708,0.000080583995,0.000067432185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009597939,0.00012499391,0.026161037,0.000022036975,0.00015399588,0.00006826868,0.0025117346,0.027988471,0.06524552,0.74107903,0.014992833,0.12164249],"study_design_scores_gemma":[0.00035910148,0.00012427942,0.015346716,0.000013672876,0.000021069185,0.0000032431901,0.0007979785,0.70368886,0.17137758,0.102955826,0.005007839,0.00030382004],"about_ca_topic_score_codex":0.00006299463,"about_ca_topic_score_gemma":0.000013813957,"teacher_disagreement_score":0.93755436,"about_ca_system_score_codex":0.0000133131025,"about_ca_system_score_gemma":0.000020876263,"threshold_uncertainty_score":0.2459704},"labels":[],"label_agreement":null},{"id":"W4390475903","doi":"10.31436/iiumej.v25i1.1832","title":"Editorial","year":2024,"lang":"en","type":"editorial","venue":"IIUM Engineering Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Islam; Engineering; Malay; Library science; Management; Theology; Philosophy","score_opus":0.0028569979317511077,"score_gpt":0.24022953900490582,"score_spread":0.2373725410731547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390475903","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.17765616e-7,0.000682648,0.44578668,0.0000526227,0.55271596,0.000030066554,0.0000050267467,0.00063191704,0.0000949596],"genre_scores_gemma":[0.00000860405,0.00030822674,0.08009702,0.0000051458487,0.9188029,0.000011135972,0.000009143907,0.00008020712,0.000677589],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968058,0.000026306416,0.0005324419,0.00050149113,0.0016242462,0.0005097425],"domain_scores_gemma":[0.9981662,0.0003329384,0.00019958545,0.0006699392,0.00040553458,0.00022577045],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00070786517,0.00044150074,0.00049230293,0.0006719984,0.0000923673,0.0012499745,0.0022230824,0.0008139368,0.000010589467],"category_scores_gemma":[0.0007641581,0.00040862156,0.00038615614,0.0005438189,0.000016407932,0.0006734038,0.00047453959,0.003964861,0.00014442306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001254518,0.00000818355,5.3254496e-8,0.000041698393,0.00009184495,0.000104468854,0.000034139677,0.0011638078,0.00012264565,0.000506042,0.99673265,0.0011932289],"study_design_scores_gemma":[0.000099851095,0.00005192506,1.1108354e-7,0.0002470351,0.000052310505,0.000042413543,6.16387e-7,0.009483022,0.00009994948,0.001845922,0.98766243,0.00041439515],"about_ca_topic_score_codex":0.0000028596446,"about_ca_topic_score_gemma":5.943134e-7,"teacher_disagreement_score":0.36608696,"about_ca_system_score_codex":0.00041313758,"about_ca_system_score_gemma":0.0004216617,"threshold_uncertainty_score":0.99983656},"labels":[],"label_agreement":null},{"id":"W4390781999","doi":"10.1002/asi.24865","title":"<scp>Phenomenon‐based</scp> classification: An Annual Review of Information Science and Technology (ARIST) paper","year":2024,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Phenomenon; Identification (biology); Computer science; Discipline; Epistemology; Information system; Data science; Sociology; Social science; Engineering; Philosophy","score_opus":0.009216745243985884,"score_gpt":0.28738744698619406,"score_spread":0.2781707017422082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390781999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039750975,0.008543022,0.7753453,0.15814318,0.0021240474,0.0030018527,0.00011630355,0.0012953844,0.011679935],"genre_scores_gemma":[0.9497894,0.0022615336,0.04613283,0.00168364,0.000031176696,0.0000445354,0.0000034815093,0.0000055408377,0.000047847705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997376,0.000024288829,0.0009023381,0.00016121102,0.0012721546,0.00026398725],"domain_scores_gemma":[0.9908994,0.00016739382,0.001594087,0.00042971934,0.0068418807,0.00006756313],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0065345867,0.000116366115,0.00025406634,0.0028910886,0.00045441507,0.00036835854,0.0016536021,0.00013317908,7.365423e-7],"category_scores_gemma":[0.0076017743,0.000083925566,0.000048045364,0.009416401,0.0008416761,0.02098752,0.00031717116,0.0002795896,0.0000031180805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020927394,0.000028889952,0.0014051055,0.00047669976,0.000028779988,2.5916043e-7,0.0011131412,0.000017429264,0.0039599654,0.75545204,0.0037534025,0.23376219],"study_design_scores_gemma":[0.0007860092,0.00092583726,0.0048391735,0.0015300296,0.00014458889,0.000194707,0.0033938037,0.06209077,0.030430408,0.11077607,0.78460133,0.00028729098],"about_ca_topic_score_codex":0.0000011828384,"about_ca_topic_score_gemma":9.09989e-7,"teacher_disagreement_score":0.9100384,"about_ca_system_score_codex":0.0005246239,"about_ca_system_score_gemma":0.0012701732,"threshold_uncertainty_score":0.9927054},"labels":[],"label_agreement":null},{"id":"W4391621552","doi":"10.2139/ssrn.4719403","title":"Comprehensive Analysis of Transformer Networks in Identifying Informative Sentences Containing Customer Needs","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transformer; Computer science; Customer needs; Natural language processing; Business; Engineering; Marketing; Electrical engineering","score_opus":0.0169723683184902,"score_gpt":0.30422782540503407,"score_spread":0.2872554570865439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391621552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050514903,0.009853718,0.9380514,0.00019995788,0.00027783358,0.00024569372,0.0000042006463,0.0001337203,0.0007185598],"genre_scores_gemma":[0.9854811,0.010492796,0.0037300014,0.000073376716,0.00006898914,0.000025010117,0.000017871516,0.000023522174,0.0000873574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951696,0.00020999585,0.0014271047,0.00047038432,0.00069654925,0.0020263998],"domain_scores_gemma":[0.99783385,0.00018352181,0.0009430654,0.0005342926,0.00041143427,0.000093842085],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020032683,0.00046754032,0.0012854018,0.004766002,0.00011784673,0.0003219034,0.0017857832,0.00030358633,0.0000084172925],"category_scores_gemma":[0.00002349946,0.00042033065,0.00097368116,0.0050367503,0.00012204995,0.0007727925,0.0007007076,0.0069986666,0.0000058515807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009256655,0.00012816796,0.0047036237,0.0002384107,0.020485936,0.00006118877,0.020524658,0.43879077,0.00023405578,0.37378427,0.000033555283,0.14092281],"study_design_scores_gemma":[0.00040114898,0.00019404945,0.0008877222,0.00066116883,0.002190141,0.00010037031,0.013445649,0.5684808,0.00026742648,0.41239777,0.00015498037,0.0008187878],"about_ca_topic_score_codex":0.00030962715,"about_ca_topic_score_gemma":0.0016185018,"teacher_disagreement_score":0.93496615,"about_ca_system_score_codex":0.0014303793,"about_ca_system_score_gemma":0.00167725,"threshold_uncertainty_score":0.9998249},"labels":[],"label_agreement":null},{"id":"W4391756409","doi":"10.1016/j.mehy.2024.111295","title":"Comment on: Hypothesis testing of the adoption of pseudoscientific methods","year":2024,"lang":"en","type":"article","venue":"Medical Hypotheses","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; Royal Ottawa Mental Health Centre; University of Ottawa","funders":"","keywords":"Pseudoscience; Psychology; Medicine; Alternative medicine; Pathology","score_opus":0.07637725113718358,"score_gpt":0.35444273570711243,"score_spread":0.27806548456992886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391756409","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066659795,0.0003548901,0.9829153,0.007509264,0.00032950554,0.00014798158,0.0000032513478,0.00025196598,0.0018218829],"genre_scores_gemma":[0.5147885,0.0000146362245,0.48439983,0.0006671946,0.000028536953,0.00001350565,1.344522e-7,0.000008824648,0.000078793826],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979947,0.00030703083,0.00038173347,0.00030698534,0.00084294594,0.00016657013],"domain_scores_gemma":[0.9948508,0.0041764993,0.00012552139,0.00069952087,0.00007869819,0.0000689219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017488468,0.00011201158,0.00022993612,0.0001621352,0.00006589843,0.000040018436,0.0012333879,0.00006622095,0.000046347664],"category_scores_gemma":[0.0045926166,0.00006695279,0.00015220784,0.0012621813,0.00029843338,0.00012458155,0.00032552294,0.00018417776,0.000009639417],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022310126,0.00014049292,0.00023096785,0.00010269164,0.00003267156,0.000006059542,0.0002062034,0.00002815545,0.009947671,0.05279151,0.0016605189,0.9348508],"study_design_scores_gemma":[0.00015156293,0.0002666088,0.0024008248,0.0015746753,0.00008273231,0.000025838252,0.00006852657,0.13765939,0.6527621,0.16207148,0.042621274,0.00031498817],"about_ca_topic_score_codex":0.000015775262,"about_ca_topic_score_gemma":0.0000018717119,"teacher_disagreement_score":0.93453586,"about_ca_system_score_codex":0.00003704932,"about_ca_system_score_gemma":0.00009535448,"threshold_uncertainty_score":0.5498123},"labels":[],"label_agreement":null},{"id":"W4391793582","doi":"10.1145/3632971.3632980","title":"Open-ended questions automated evaluation: proposal of a new generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","score_opus":0.08351453324136883,"score_gpt":0.40420583955243855,"score_spread":0.32069130631106973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391793582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00439071,0.00001590333,0.985097,0.0022259424,0.0000748732,0.00048800677,6.4543775e-7,0.002891616,0.004815291],"genre_scores_gemma":[0.38388142,0.0000070584383,0.6134317,0.00007281691,0.00003848714,0.00006600203,0.000027430273,0.0000058141195,0.0024692805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892646,0.00008882183,0.00024131575,0.00026612278,0.00036096334,0.00011632836],"domain_scores_gemma":[0.9990461,0.000021455631,0.0000987109,0.0005072557,0.0002772804,0.000049191553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059164176,0.00007289408,0.00012292936,0.0001903595,0.00007493196,0.00012989237,0.0008402991,0.00003662524,0.000061804596],"category_scores_gemma":[0.00011794992,0.000064003914,0.000034273464,0.0015212345,0.000017349714,0.0008765668,0.0004078532,0.00003904858,0.00007854354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002339368,0.00008786749,0.00009726345,0.00000594378,0.000047346413,0.0000034388174,0.00048058302,0.006820112,0.1055245,0.6073777,0.16483326,0.11471965],"study_design_scores_gemma":[0.0001589632,0.000036950256,0.000745888,0.0000063489624,0.000011330348,0.0000017087866,0.0000066685916,0.9129229,0.04756166,0.038020864,0.00044947278,0.00007720249],"about_ca_topic_score_codex":0.00012566823,"about_ca_topic_score_gemma":0.00014525554,"teacher_disagreement_score":0.90610284,"about_ca_system_score_codex":0.000048391103,"about_ca_system_score_gemma":0.0004366625,"threshold_uncertainty_score":0.26100037},"labels":[],"label_agreement":null},{"id":"W4391971213","doi":"10.32942/x2vg87","title":"The changing landscape of text mining - a review of approaches for ecology and evolution","year":2024,"lang":"en","type":"review","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Medical Research Council","keywords":"Ecology; Geography; Landscape ecology; Environmental resource management; Biology; Environmental science","score_opus":0.06786742054177088,"score_gpt":0.3466628727282187,"score_spread":0.27879545218644786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391971213","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.100054e-8,0.7558112,0.24319735,0.00005932052,0.00003105159,0.00052072294,0.0000023585574,0.000045748344,0.0003321533],"genre_scores_gemma":[0.000010958588,0.9457309,0.05370477,0.00001164411,0.000022472335,0.00024120059,0.0000053413933,0.000011355929,0.00026130717],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876386,0.00008121622,0.00055848353,0.00031994094,0.00010538798,0.0001710936],"domain_scores_gemma":[0.9985008,0.00051289075,0.0004567959,0.00044754578,0.000063282474,0.000018650588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010245304,0.00017430866,0.0010800005,0.00026265558,0.000053512624,0.000019826728,0.0005708842,0.00009156839,0.0000011846533],"category_scores_gemma":[0.00013757002,0.00009473237,0.00033294177,0.0007475095,0.000058697493,0.00008368422,0.00039232816,0.00008682224,8.682879e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4052358e-7,0.0000040648033,6.102465e-7,0.07130804,0.00007041041,1.5320317e-7,0.000025596037,7.0212366e-8,4.2952035e-8,0.05243598,0.00045687187,0.87569803],"study_design_scores_gemma":[0.000037936938,0.00009762793,8.635321e-7,0.08735098,0.001421926,0.00002911404,0.000042268235,0.006790997,0.0000032383143,0.0045735985,0.8994078,0.00024366892],"about_ca_topic_score_codex":7.020253e-7,"about_ca_topic_score_gemma":0.0000048450943,"teacher_disagreement_score":0.89895093,"about_ca_system_score_codex":0.00002898817,"about_ca_system_score_gemma":0.0000930897,"threshold_uncertainty_score":0.38630742},"labels":[],"label_agreement":null},{"id":"W4392384312","doi":"10.1145/3616855.3635691","title":"Vector Search with OpenAI Embeddings: Lucene Is All You Need","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Ranking (information retrieval); Encoder; Information retrieval; Architecture; Artificial intelligence; Data mining; Geography; Operating system","score_opus":0.018889090855615288,"score_gpt":0.3146775010715027,"score_spread":0.2957884102158874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392384312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037590142,0.00027259838,0.97704285,0.0041184667,0.00005776676,0.00016714822,0.0000013236473,0.0016104217,0.012970434],"genre_scores_gemma":[0.6311846,0.000037355232,0.35925174,0.0013020246,0.000052874475,0.000023740055,0.0000019284332,0.000023729415,0.008122029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998491,0.000025931844,0.00016328607,0.0005783495,0.00040439586,0.0003370768],"domain_scores_gemma":[0.99904835,0.000055738543,0.000020189163,0.00067469396,0.00009113762,0.0001099025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022696187,0.00016204559,0.0001768718,0.00021753463,0.000058214275,0.00052652083,0.0010047501,0.00004714572,0.0002160753],"category_scores_gemma":[0.000008382429,0.0001133407,0.00007255951,0.0010510043,0.000044160002,0.00095336296,0.0003962157,0.00018751607,0.00029210566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033989967,0.00021359982,0.0005163676,0.00015728282,0.00078697875,0.0006079225,0.0072886357,0.00033862484,0.038083337,0.61795604,0.09653762,0.23747961],"study_design_scores_gemma":[0.00035645274,0.0005057637,0.00037594105,0.00020490089,0.000084015104,0.00010215918,0.00021810154,0.48913777,0.34506214,0.011510392,0.15141015,0.0010322256],"about_ca_topic_score_codex":0.00009262301,"about_ca_topic_score_gemma":0.000013857173,"teacher_disagreement_score":0.62742555,"about_ca_system_score_codex":0.000067318324,"about_ca_system_score_gemma":0.00007357819,"threshold_uncertainty_score":0.50772524},"labels":[],"label_agreement":null},{"id":"W4392612056","doi":"10.1145/3627508.3638307","title":"Visual Keyword/Result Linking: Using Interaction to Dynamically Reveal Relationships","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Information retrieval; Search engine; Space (punctuation); Visualization; Digital library; Interface (matter); User satisfaction; Value (mathematics); Information visualization; Feature (linguistics); World Wide Web; Human–computer interaction; Data mining; Machine learning","score_opus":0.04515645247046382,"score_gpt":0.3678306697881741,"score_spread":0.3226742173177103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392612056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020458955,0.000029550107,0.9736135,0.0011376705,0.0002560271,0.00011831106,4.4675372e-7,0.0012949724,0.0030905397],"genre_scores_gemma":[0.577107,0.0000018532496,0.4218505,0.0001470859,0.00006471846,0.0000058965206,0.0000029227238,0.000009234778,0.00081080914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870545,0.000077115445,0.00030970757,0.00046899114,0.00023962808,0.00019908528],"domain_scores_gemma":[0.99922794,0.00019760164,0.000042842144,0.000347448,0.00009458165,0.00008957889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037359886,0.00012487697,0.00012629182,0.0003807775,0.00013334924,0.00038786733,0.0004061114,0.00007222199,0.0000139431895],"category_scores_gemma":[0.0001168799,0.00011433475,0.00008337653,0.0011996105,0.0000150278465,0.0010847246,0.00026583025,0.00033745388,0.00015270905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019336803,0.0001488386,0.0015776227,0.000063103245,0.00013226568,0.00010566829,0.0019739962,0.0127050495,0.0666135,0.59802234,0.0029681695,0.31567007],"study_design_scores_gemma":[0.000029694054,0.000045647048,0.00031605462,0.00012466562,0.000012613262,0.000020493428,0.00002287638,0.97275877,0.0036097923,0.018251609,0.004617056,0.00019072286],"about_ca_topic_score_codex":0.000025426501,"about_ca_topic_score_gemma":0.000043794476,"teacher_disagreement_score":0.96005374,"about_ca_system_score_codex":0.00023498955,"about_ca_system_score_gemma":0.000049496266,"threshold_uncertainty_score":0.46624357},"labels":[],"label_agreement":null},{"id":"W4392811535","doi":"10.1111/cogs.13416","title":"Probing the Representational Structure of Regular Polysemy via Sense Analogy Questions: Insights from Contextual Word Vectors","year":2024,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Polysemy; Analogy; Computer science; Natural language processing; Linguistics; Artificial intelligence; Mathematics; Cognitive psychology; Psychology","score_opus":0.014178112154821837,"score_gpt":0.30500564028455596,"score_spread":0.2908275281297341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392811535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23901162,0.0009088957,0.75897175,0.0002534804,0.00020233433,0.00021277792,0.000019914502,0.000179783,0.00023947432],"genre_scores_gemma":[0.98157054,0.000011494965,0.018126138,0.00015317537,0.00006784641,0.000012768771,0.000009090046,0.0000071846684,0.00004175456],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99792993,0.00015410992,0.00029656693,0.0007484376,0.0006359804,0.00023495137],"domain_scores_gemma":[0.9980817,0.000715394,0.00013434657,0.00045880667,0.00053473137,0.000075026896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000251983,0.0001539166,0.00018386723,0.0003839706,0.00031962135,0.00023021108,0.0008289775,0.00004774314,0.000022571598],"category_scores_gemma":[0.000526916,0.000107417494,0.000081195554,0.0027458468,0.0014632074,0.0012754742,0.0003723782,0.00022993806,0.000012339253],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016188595,0.00004842358,0.00045745747,0.000014442385,0.00011403575,0.00009698179,0.0069356174,0.00024200746,0.66738,0.19023213,0.00012330877,0.1343394],"study_design_scores_gemma":[0.00018323968,0.00008820384,0.017655538,0.0003577085,0.00007501406,0.000062153245,0.000589502,0.117358044,0.48556277,0.37748545,0.0002134523,0.0003688892],"about_ca_topic_score_codex":0.00011707028,"about_ca_topic_score_gemma":0.00006248034,"teacher_disagreement_score":0.74255896,"about_ca_system_score_codex":0.00007315879,"about_ca_system_score_gemma":0.00026277822,"threshold_uncertainty_score":0.53912485},"labels":[],"label_agreement":null},{"id":"W4392910034","doi":"10.1109/icassp48485.2024.10447992","title":"VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Adversarial system; Covariance; Distillation; Variance (accounting); Computer science; Spotting; Artificial intelligence; Mathematics; Statistics; Chemistry; Chromatography","score_opus":0.02042862100012554,"score_gpt":0.30573294457778605,"score_spread":0.2853043235776605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392910034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051055104,0.0004172109,0.9645331,0.002744438,0.0014194351,0.0005319629,0.000011037506,0.002847459,0.026984831],"genre_scores_gemma":[0.35567555,0.00005443959,0.63812387,0.00071960234,0.00086288806,0.00009756957,0.000024283125,0.000063708336,0.0043780813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614483,0.000120981036,0.00076680456,0.0016050015,0.0005774269,0.00078494777],"domain_scores_gemma":[0.99753976,0.00032256998,0.0001541255,0.0014052691,0.00028422958,0.00029402133],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077221025,0.0005168401,0.0005289533,0.0005068093,0.00032387147,0.0007962614,0.0015933699,0.00022220993,0.00008262919],"category_scores_gemma":[0.00025840825,0.0004919075,0.00032180457,0.003168842,0.000076702185,0.0014463165,0.0008222019,0.00044396459,0.0005589159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053159514,0.00018060021,0.00027775683,0.00021825983,0.00032298567,0.00029564157,0.0035585908,0.060439907,0.005005901,0.455086,0.013906163,0.46065503],"study_design_scores_gemma":[0.00040947058,0.0000841298,0.00084212975,0.0004949337,0.00007456205,0.000024452678,0.00006952921,0.82436305,0.0028606607,0.008090473,0.16157408,0.001112548],"about_ca_topic_score_codex":0.000041328913,"about_ca_topic_score_gemma":0.00010686272,"teacher_disagreement_score":0.7639231,"about_ca_system_score_codex":0.00045207652,"about_ca_system_score_gemma":0.000259505,"threshold_uncertainty_score":0.99975324},"labels":[],"label_agreement":null},{"id":"W4393012052","doi":"10.3389/frai.2024.1200949","title":"Key point generation as an instrument for generating core statements of a political debate on Twitter","year":2024,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Key (lock); Process (computing); Artificial intelligence; Point (geometry); Ranking (information retrieval); Complement (music); Hyperparameter; Natural language processing; Information retrieval; GRASP; Probabilistic logic; Word embedding; Word (group theory); Data mining; Machine learning; Embedding","score_opus":0.1039080750419846,"score_gpt":0.3956751987625539,"score_spread":0.29176712372056934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393012052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10219525,0.00005086719,0.89608306,0.00039833214,0.0007163595,0.00033969013,0.00000572685,0.00011314024,0.00009760122],"genre_scores_gemma":[0.618623,0.000009056336,0.38091302,0.0002506229,0.00009021191,0.00006136561,0.000011741798,0.000011092536,0.000029860947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980547,0.00006336002,0.00064468035,0.00056198775,0.00029626043,0.00037901013],"domain_scores_gemma":[0.99926525,0.000051332365,0.0000870005,0.00040081746,0.00010099177,0.00009459315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047168933,0.00017193849,0.00022897498,0.00037484692,0.00007488373,0.00017533642,0.00046928079,0.00007026095,0.000009733016],"category_scores_gemma":[0.00009483635,0.0001639811,0.000085527485,0.00043469534,0.000077393815,0.0006785011,0.000088573935,0.00014216213,0.000010764051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024954714,0.00013409363,0.00010648001,0.000027605023,0.000028343651,0.000015252915,0.001451306,0.0041828775,0.01553839,0.73438835,0.0005689026,0.24353345],"study_design_scores_gemma":[0.000012454651,0.0002232574,0.0000038363205,0.000042128933,0.000005313017,0.0000011117871,0.00016568543,0.552494,0.2333113,0.21349789,0.00013698406,0.00010604988],"about_ca_topic_score_codex":0.000076576296,"about_ca_topic_score_gemma":0.00004666549,"teacher_disagreement_score":0.5483111,"about_ca_system_score_codex":0.00023927337,"about_ca_system_score_gemma":0.00008074021,"threshold_uncertainty_score":0.6686955},"labels":[],"label_agreement":null},{"id":"W4393347796","doi":"10.1007/s41019-023-00239-2","title":"Uncovering Flat and Hierarchical Topics by Community Discovery on Word Co-occurrence Network","year":2024,"lang":"en","type":"article","venue":"Data Science and Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Alberta","funders":"Centre National de la Recherche Scientifique; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Hierarchy; Identification (biology); Topic model; Word (group theory); Exploit; Data science; Tree (set theory); Information retrieval; Linguistics","score_opus":0.023266520834801834,"score_gpt":0.2920903359651108,"score_spread":0.26882381513030895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393347796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09116597,0.0007877307,0.906614,0.00034389165,0.00026296993,0.000079058555,0.00010814203,0.0004068856,0.00023133557],"genre_scores_gemma":[0.96695906,0.00048218627,0.032205988,0.0001618109,0.000086566986,0.0000053959957,0.00007028532,0.000006762157,0.000021953778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988489,0.000017137407,0.00012256656,0.0004304187,0.00029083193,0.00029010302],"domain_scores_gemma":[0.9988428,0.00018335058,0.000014959029,0.00084326265,0.000014615913,0.00010100969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089460803,0.00012021584,0.000118248136,0.00011315023,0.00027602864,0.00087858684,0.001337061,0.000027281874,4.6885268e-7],"category_scores_gemma":[0.00013575098,0.00010624648,0.000009205484,0.00079091295,0.00017276745,0.0035136363,0.0013045548,0.0003867598,0.0000014264516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008052615,0.00005701877,0.0012849937,0.0003392472,0.000053774536,0.000067184585,0.0014093069,0.011822677,0.030816726,0.15516326,0.018224528,0.78075325],"study_design_scores_gemma":[0.000065195025,0.00008232503,0.0009316095,0.00028713339,0.000009595586,0.000023944682,0.00002221946,0.87507284,0.0023981547,0.0023476558,0.11834038,0.00041893177],"about_ca_topic_score_codex":0.000016146882,"about_ca_topic_score_gemma":0.0000033844703,"teacher_disagreement_score":0.8757931,"about_ca_system_score_codex":0.000030934243,"about_ca_system_score_gemma":0.00004256487,"threshold_uncertainty_score":0.8472233},"labels":[],"label_agreement":null},{"id":"W4393676817","doi":"10.5281/zenodo.10069275","title":"The Effect of Typing Efficiency and Suggestion Accuracy on Usage of Word Suggestions and Entry Speed","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Word (group theory); Typing; Computer science; Natural language processing; Arithmetic; Psychology; Speech recognition; Linguistics; Mathematics; Philosophy","score_opus":0.01859516809902201,"score_gpt":0.280757001738307,"score_spread":0.26216183363928497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393676817","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024681536,0.0021459167,0.10572884,0.0027353338,0.00083909323,0.0063417265,0.84705627,0.0048757745,0.0055955043],"genre_scores_gemma":[0.117637575,0.012960905,0.0019353413,0.00009058995,0.00027485675,6.666826e-7,0.864216,0.0020870352,0.00079699047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998174,0.00050066644,0.00031763225,0.0004249641,0.00035442898,0.00022830375],"domain_scores_gemma":[0.9979589,0.00060771377,0.00033070077,0.00078547053,0.00023852583,0.000078688165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001212512,0.00017193025,0.0002491437,0.00037796792,0.0010575806,0.00038667308,0.0013882255,0.00008818494,0.00005110095],"category_scores_gemma":[0.0031428307,0.00013771698,0.00004807373,0.0009011926,0.00029417098,0.00019381219,0.0019207309,0.00033680839,0.0002978482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005048493,0.000047077447,0.0000032131834,0.00022056972,0.00005108424,0.0000063805446,0.00010280281,0.00007839385,0.0006068499,0.0014026077,0.86918163,0.12824892],"study_design_scores_gemma":[0.00034089002,0.0008625152,0.000622188,0.0003158047,0.00005567354,0.000031088817,0.000020599155,0.0018189608,0.0012070813,0.00029231512,0.99421173,0.00022116708],"about_ca_topic_score_codex":0.000029514384,"about_ca_topic_score_gemma":0.0000010018168,"teacher_disagreement_score":0.12802775,"about_ca_system_score_codex":0.000052582913,"about_ca_system_score_gemma":0.0000042089173,"threshold_uncertainty_score":0.8134162},"labels":[],"label_agreement":null},{"id":"W4393719360","doi":"10.5281/zenodo.10069276","title":"The Effect of Typing Efficiency and Suggestion Accuracy on Usage of Word Suggestions and Entry Speed","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Word (group theory); Computer science; Natural language processing; Typing; Speech recognition; Artificial intelligence; Linguistics; Philosophy","score_opus":0.01859516809902201,"score_gpt":0.280757001738307,"score_spread":0.26216183363928497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393719360","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024681536,0.0021459167,0.10572884,0.0027353338,0.00083909323,0.0063417265,0.84705627,0.0048757745,0.0055955043],"genre_scores_gemma":[0.117637575,0.012960905,0.0019353413,0.00009058995,0.00027485675,6.666826e-7,0.864216,0.0020870352,0.00079699047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998174,0.00050066644,0.00031763225,0.0004249641,0.00035442898,0.00022830375],"domain_scores_gemma":[0.9979589,0.00060771377,0.00033070077,0.00078547053,0.00023852583,0.000078688165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001212512,0.00017193025,0.0002491437,0.00037796792,0.0010575806,0.00038667308,0.0013882255,0.00008818494,0.00005110095],"category_scores_gemma":[0.0031428307,0.00013771698,0.00004807373,0.0009011926,0.00029417098,0.00019381219,0.0019207309,0.00033680839,0.0002978482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005048493,0.000047077447,0.0000032131834,0.00022056972,0.00005108424,0.0000063805446,0.00010280281,0.00007839385,0.0006068499,0.0014026077,0.86918163,0.12824892],"study_design_scores_gemma":[0.00034089002,0.0008625152,0.000622188,0.0003158047,0.00005567354,0.000031088817,0.000020599155,0.0018189608,0.0012070813,0.00029231512,0.99421173,0.00022116708],"about_ca_topic_score_codex":0.000029514384,"about_ca_topic_score_gemma":0.0000010018168,"teacher_disagreement_score":0.12802775,"about_ca_system_score_codex":0.000052582913,"about_ca_system_score_gemma":0.0000042089173,"threshold_uncertainty_score":0.8134162},"labels":[],"label_agreement":null},{"id":"W4393748815","doi":"10.5281/zenodo.5720363","title":"Replication Package for the Paper: Transfer Learning with Time Series Data: A Systematic Mapping Study","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Replication (statistics); Computer science; Series (stratigraphy); R package; Time series; Machine learning; Programming language; Biology; Statistics; Mathematics","score_opus":0.042432545873847614,"score_gpt":0.27273189811639115,"score_spread":0.23029935224254353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393748815","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014635753,0.00029665913,0.73634523,0.0006860566,0.000043935688,0.0036396245,0.25725245,0.0014224658,0.0002989537],"genre_scores_gemma":[0.0006712001,0.0002607932,0.0032546893,0.000107945205,0.00012169725,0.0000032361156,0.9940092,0.00085560884,0.0007156052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99625134,0.00093967665,0.0005124425,0.0012645974,0.0006707599,0.00036120263],"domain_scores_gemma":[0.9931694,0.00018872198,0.00026613925,0.0054809605,0.00080639485,0.00008834538],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023963843,0.0002964954,0.00047559183,0.0002482188,0.0028108985,0.002348247,0.006189741,0.00009101617,0.0005535736],"category_scores_gemma":[0.0016089528,0.00022309736,0.00007606815,0.0011569302,0.0001110921,0.0011072392,0.00308324,0.00053445983,0.00073788286],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021979888,0.00016815144,1.5846324e-7,0.0017222855,0.00033823043,0.000023242057,0.000676713,0.00004831107,0.0003807221,0.0002475662,0.9918001,0.0045725154],"study_design_scores_gemma":[0.00024445413,0.00035890724,0.000006493294,0.0005132506,0.0001812033,0.000104079896,0.00062208826,0.0013742517,0.000059546124,0.000029734192,0.9962261,0.00027989212],"about_ca_topic_score_codex":0.000014082426,"about_ca_topic_score_gemma":0.0000035847395,"teacher_disagreement_score":0.7367568,"about_ca_system_score_codex":0.00013186174,"about_ca_system_score_gemma":0.000014071352,"threshold_uncertainty_score":0.99918723},"labels":[],"label_agreement":null},{"id":"W4393753614","doi":"10.5281/zenodo.3635095","title":"Testing ritual knot tracing for cognitive priming effects rules out analytic analogy: Core Data Sets","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Analogy; Knot (papermaking); Tracing; Priming (agriculture); Core (optical fiber); Cognition; Computer science; Cognitive science; Psychology; Epistemology; Philosophy; Programming language; Engineering; Neuroscience; Biology","score_opus":0.23788761834435018,"score_gpt":0.4032536182026153,"score_spread":0.1653659998582651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393753614","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003993887,0.000386156,0.0143747255,0.00001181747,0.000099090954,0.0013149605,0.9834088,0.0003558852,0.000044549604],"genre_scores_gemma":[0.00019303102,0.000003876507,0.031988975,0.00024858754,0.00023317618,0.00033956062,0.96690416,0.000050018087,0.00003863659],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961709,0.00010127089,0.0005884139,0.0018615447,0.0005400071,0.0007378561],"domain_scores_gemma":[0.9901413,0.00540064,0.00089969917,0.0028674344,0.0005305446,0.00016039783],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028431613,0.0006660586,0.0010145544,0.0005258763,0.00027494656,0.00040445392,0.004693025,0.0004450387,0.00077213574],"category_scores_gemma":[0.0158532,0.0006732033,0.00021953494,0.0005721317,0.000023386667,0.00114291,0.003069676,0.0007278038,0.0011147854],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044445196,0.000044150027,0.000004536362,0.0015070727,0.00015185396,0.00007551569,0.00003466059,0.000012385277,0.00001121612,0.0000022980505,0.98114574,0.017006125],"study_design_scores_gemma":[0.0011562806,0.00051777245,0.0003450227,0.034531366,0.001097534,0.000072363175,0.000032552354,0.1220843,0.0006339784,0.000783319,0.8360367,0.0027088402],"about_ca_topic_score_codex":0.000016349319,"about_ca_topic_score_gemma":0.00009333013,"teacher_disagreement_score":0.14510907,"about_ca_system_score_codex":0.00013681305,"about_ca_system_score_gemma":0.00034099,"threshold_uncertainty_score":0.99966294},"labels":[],"label_agreement":null},{"id":"W4393792028","doi":"10.5281/zenodo.3635094","title":"Testing ritual knot tracing for cognitive priming effects rules out analytic analogy: Core Data Sets","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Analogy; Knot (papermaking); Priming (agriculture); Cognition; Tracing; Core (optical fiber); Cognitive psychology; Computer science; Psychology; Epistemology; Neuroscience; Philosophy; Engineering; Programming language; Biology","score_opus":0.1521145632011919,"score_gpt":0.3529259361354704,"score_spread":0.2008113729342785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393792028","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000094197305,0.000116836985,0.37393832,0.000067623274,0.0001168225,0.0012452892,0.6226101,0.000982971,0.00082785584],"genre_scores_gemma":[0.0027970595,0.000047702873,0.019275831,0.00016422721,0.00019216334,3.3834544e-7,0.97650427,0.00090065657,0.00011774616],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99597925,0.00040528367,0.0005667406,0.0016391987,0.00067987153,0.00072965195],"domain_scores_gemma":[0.99484146,0.00074348407,0.0005936361,0.0024294946,0.0011773471,0.0002145812],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014649829,0.00044884393,0.00062490127,0.00078607467,0.0018724565,0.0015215684,0.006418695,0.00022851197,0.00025082097],"category_scores_gemma":[0.007943031,0.0004828469,0.0001225705,0.00094916805,0.000193959,0.0010722447,0.0074238116,0.00073822844,0.002762382],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021179283,0.000110412984,0.0000011075402,0.00047977385,0.00017203992,0.00003897627,0.0001788886,0.000023856648,0.00027784053,0.00015051269,0.88906604,0.10947937],"study_design_scores_gemma":[0.00064228603,0.00047032227,0.000069716356,0.00063036074,0.00029261838,0.000090947426,0.000056131008,0.026338426,0.00020434182,0.00046944965,0.9700695,0.00066585006],"about_ca_topic_score_codex":0.000021329526,"about_ca_topic_score_gemma":0.000003004473,"teacher_disagreement_score":0.3546625,"about_ca_system_score_codex":0.00024199107,"about_ca_system_score_gemma":0.00002818256,"threshold_uncertainty_score":0.9997623},"labels":[],"label_agreement":null},{"id":"W4393981161","doi":"10.25144/16085","title":"THE CONTRIBUTION OF AUTOMATIC SPEECH RECOGNITION FOR KEYWORDS TO ASSIST IN THE INTEGRATED ORGANISATION OF DIGITAL MESSAGES","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kwantlen Polytechnic University","funders":"","keywords":"Computer science; Speech recognition; Natural language processing","score_opus":0.022005704841387256,"score_gpt":0.3041059391850769,"score_spread":0.28210023434368964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393981161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16369049,0.000004842982,0.8335819,0.0017936431,0.000025916626,0.00046623938,0.000008175058,0.00017869155,0.00025005586],"genre_scores_gemma":[0.9765752,0.000005237153,0.023224875,0.000036208316,0.0000056807985,0.000060186354,0.000039760707,0.0000035634905,0.00004930779],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991802,0.000058341175,0.00030554304,0.00012534937,0.00021649398,0.00011410272],"domain_scores_gemma":[0.99867827,0.0006732166,0.00013782094,0.00026247505,0.00023657968,0.000011664704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000898233,0.000062757426,0.00012364393,0.00013626278,0.00008473519,0.00007317785,0.0004732496,0.000030137157,0.0000029335881],"category_scores_gemma":[0.0007633788,0.000034857858,0.000048199112,0.0013306747,0.00003277792,0.00034331533,0.000117275114,0.00004256363,0.000006557002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000147217,0.00008395646,0.0013236958,0.000018066297,0.00003244483,0.0000010147368,0.0011244528,0.000026578657,0.010800862,0.028752398,0.0015889494,0.95623285],"study_design_scores_gemma":[0.00048228263,0.00034436004,0.018583719,0.00011348864,0.00003200147,0.0000036376766,0.0017921831,0.16091192,0.45418084,0.3624805,0.000855237,0.00021985146],"about_ca_topic_score_codex":0.000015799762,"about_ca_topic_score_gemma":0.000113833245,"teacher_disagreement_score":0.956013,"about_ca_system_score_codex":0.000034972792,"about_ca_system_score_gemma":0.000030264739,"threshold_uncertainty_score":0.14214621},"labels":[],"label_agreement":null},{"id":"W4394842830","doi":"10.1515/cllt-2023-0028","title":"The distributional properties of long nominal compounds in scientific articles: an investigation based on the uniform information density hypothesis","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Constant (computer programming); Scientific literature; Information transmission; Econometrics; Data science; Information retrieval; Mathematics; Biology","score_opus":0.021486894088511916,"score_gpt":0.23154092932942288,"score_spread":0.21005403524091096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394842830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48873302,0.00043243347,0.5076927,0.0003275823,0.0011365707,0.00041405193,0.00002729543,0.00023556364,0.0010007999],"genre_scores_gemma":[0.9964358,0.00000678408,0.003307343,0.000079806116,0.00011338922,0.000014947865,0.000011655321,0.000006215166,0.00002405128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987395,0.00015087082,0.0003918876,0.00022333224,0.00030863256,0.00018577767],"domain_scores_gemma":[0.99747676,0.0013843717,0.00013530884,0.00047671338,0.00046703356,0.000059808197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021588833,0.00013372072,0.00013222093,0.0001701995,0.0004678295,0.00062748365,0.0004570065,0.000043611966,0.0000011914287],"category_scores_gemma":[0.008099127,0.0000808144,0.00004421234,0.00047563235,0.0006852428,0.000087896355,0.00010135602,0.00019088075,0.0000038470357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030082323,0.000026604794,0.00077652436,0.000048937167,0.000008640644,0.0000055624814,0.0010005693,0.00021957199,0.00029434092,0.9877283,0.000015830832,0.009845027],"study_design_scores_gemma":[0.00008966772,0.000076813296,0.0030941688,0.0002685451,0.000027561491,0.0000033870003,0.00011085457,0.56250453,0.010444951,0.4221849,0.0010459118,0.00014869515],"about_ca_topic_score_codex":0.000032182994,"about_ca_topic_score_gemma":0.000058731304,"teacher_disagreement_score":0.56554335,"about_ca_system_score_codex":0.000086801876,"about_ca_system_score_gemma":0.00022827921,"threshold_uncertainty_score":0.9695996},"labels":[],"label_agreement":null},{"id":"W4394938781","doi":"10.5267/j.ijdns.2024.1.014","title":"Multi-objective of wind-driven optimization as feature selection and clustering to enhance text clustering","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Feature selection; Computer science; Selection (genetic algorithm); Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Correlation clustering; Data mining; Machine learning","score_opus":0.015719585447118743,"score_gpt":0.34774977221899417,"score_spread":0.3320301867718754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394938781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010261236,0.00041120194,0.9881146,0.00069407624,0.0003794878,0.00006156567,0.000004485053,0.00002600526,0.000047361413],"genre_scores_gemma":[0.5290968,0.00026267942,0.47042197,0.00006657952,0.00012578988,4.786289e-7,0.0000012037535,0.0000032334015,0.000021281116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987716,0.000025410052,0.00025490657,0.00034589574,0.000465522,0.00013664461],"domain_scores_gemma":[0.9990737,0.00008452514,0.00018536407,0.00018594327,0.00038797283,0.00008248585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069162005,0.00008839235,0.00013628116,0.00034075518,0.000092111026,0.00036275332,0.0013316507,0.000029389741,0.000002605538],"category_scores_gemma":[0.00012024078,0.000076534336,0.00002211421,0.0007849133,0.00009156751,0.003151539,0.0011021472,0.00015425806,6.112279e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005422021,0.000037852435,0.00096364896,0.000020901962,0.0001112813,0.00004131876,0.0013357212,0.6772806,0.030472491,0.0007822828,0.00044091654,0.28845876],"study_design_scores_gemma":[0.00006457497,0.000095816176,0.00070630334,0.00030389792,0.000010135096,0.00025139743,0.000025310565,0.9949723,0.0026599453,0.00024513935,0.00058382796,0.000081345665],"about_ca_topic_score_codex":0.000010268226,"about_ca_topic_score_gemma":0.00003878459,"teacher_disagreement_score":0.51883554,"about_ca_system_score_codex":0.00007675052,"about_ca_system_score_gemma":0.00011333165,"threshold_uncertainty_score":0.34980386},"labels":[],"label_agreement":null},{"id":"W4394973187","doi":"10.48550/arxiv.2404.11793","title":"Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Automatic summarization; Argument (complex analysis); Key (lock); Metric (unit); Point (geometry); Computer science; Process management; Business; Mathematics; Operations management; Information retrieval; Engineering; Computer security; Medicine","score_opus":0.054917207792881305,"score_gpt":0.24167628664611276,"score_spread":0.18675907885323145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394973187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42141563,0.00015883276,0.57749635,0.000037471025,0.00018576728,0.00039817765,0.0000015947275,0.00022765239,0.00007853249],"genre_scores_gemma":[0.97328687,0.00021594089,0.026214954,0.000028438262,0.00011355245,0.000009202225,0.00005660761,0.000021746255,0.000052700037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719274,0.00039134367,0.0004095439,0.0014930296,0.0002444319,0.00026891398],"domain_scores_gemma":[0.998355,0.00009593967,0.00029350937,0.00088258425,0.00027564025,0.00009734297],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016160143,0.00031617697,0.0003926312,0.0013760844,0.00014400814,0.00039013414,0.0005742472,0.00020280872,0.000011168055],"category_scores_gemma":[0.00015717793,0.00038661362,0.00008342266,0.0018662398,0.000037852107,0.0011000918,0.0015504869,0.0005019035,0.000006982663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073926008,0.00013051122,0.0021832807,0.00039734197,0.00011478524,0.00019135907,0.001844617,0.8737238,0.005950432,0.08238405,0.000010422845,0.033062007],"study_design_scores_gemma":[0.00022396998,0.00003818669,0.0013340357,0.00026373588,0.00013846195,0.0000037136099,0.00005928797,0.9127424,0.0031959577,0.08164502,0.0000050849535,0.00035018733],"about_ca_topic_score_codex":0.00014249278,"about_ca_topic_score_gemma":0.00032909247,"teacher_disagreement_score":0.55187124,"about_ca_system_score_codex":0.0013256192,"about_ca_system_score_gemma":0.00026950103,"threshold_uncertainty_score":0.99985856},"labels":[],"label_agreement":null},{"id":"W4396531244","doi":"10.22215/etd/2024-15938","title":"The Fusion of Multilingual Semantic Search and Large Language Models: A New Paradigm for Enhanced Topic Exploration and Contextual Search","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Semantic search; Linguistics; Semantic Web","score_opus":0.035890965213824906,"score_gpt":0.3618835984187028,"score_spread":0.3259926332048779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396531244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14181684,0.0032496033,0.8534564,0.00021915778,0.00008017543,0.0007084999,0.0000054148995,0.00013559512,0.0003283293],"genre_scores_gemma":[0.9656189,0.0012577965,0.020954002,0.000022750424,0.00006224812,0.00006995095,0.000105848194,0.000024582116,0.011883914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852973,0.000058322337,0.00033015705,0.0005031061,0.00032293913,0.00025571507],"domain_scores_gemma":[0.99903685,0.0002968364,0.00007466743,0.0003778755,0.00014493009,0.00006882579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004545841,0.00019460508,0.00029497084,0.00018296632,0.00016905184,0.00020524372,0.00035366046,0.0001418443,0.000003238576],"category_scores_gemma":[0.000053811313,0.00013882892,0.00007803309,0.00023087878,0.000036038713,0.00044488788,0.0001522428,0.00021524154,0.0000017185749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012863327,0.00006162569,0.0000035901214,0.0007111515,0.0001351006,0.00000658956,0.07651023,0.00011160005,0.030104138,0.20113853,0.00019168394,0.69089717],"study_design_scores_gemma":[0.00059035205,0.00024563092,0.000025227413,0.0002834654,0.00006847663,0.000002402567,0.01171252,0.7202378,0.20309827,0.063206844,0.00020464134,0.0003244065],"about_ca_topic_score_codex":0.00022352209,"about_ca_topic_score_gemma":0.0028435036,"teacher_disagreement_score":0.83250237,"about_ca_system_score_codex":0.00002458784,"about_ca_system_score_gemma":0.00014032857,"threshold_uncertainty_score":0.5661279},"labels":[],"label_agreement":null},{"id":"W4396993769","doi":"10.2139/ssrn.4830848","title":"Optimal Text-Based Time-Series Indices","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Center for Interuniversity Research and Analysis on Organizations; HEC Montréal","funders":"","keywords":"Series (stratigraphy); Time series; Computer science; Econometrics; Mathematics; Statistics; Geology","score_opus":0.004212325084687087,"score_gpt":0.24914385377778328,"score_spread":0.2449315286930962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396993769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049355933,0.00585179,0.98525476,0.0021586402,0.000115031464,0.00006482778,7.6357026e-7,0.00068755646,0.000931039],"genre_scores_gemma":[0.8692111,0.0013299197,0.123274446,0.00021695552,0.00036472915,0.000015912541,0.0000037856198,0.00004602082,0.0055371565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99727684,0.00007298412,0.00027814633,0.00035067444,0.00038408497,0.001637262],"domain_scores_gemma":[0.99934846,0.00007210927,0.00009886688,0.00032958938,0.00006636199,0.00008463823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001193811,0.00019132216,0.00019531054,0.00038692995,0.00020905994,0.00052321365,0.0010985654,0.00007246125,0.000045852234],"category_scores_gemma":[0.000033476048,0.00015963164,0.00019026975,0.0007429888,0.00006504718,0.001440336,0.00010967803,0.0014892769,0.00022882121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018646308,0.000059156424,0.00010496582,0.00001393344,0.00026749936,0.00008927083,0.00018140273,0.0011749613,0.0029627075,0.79267126,0.0009073578,0.20154886],"study_design_scores_gemma":[0.00035618086,0.001076606,0.00007202344,0.00013263668,0.00009539812,0.0015007423,0.00016685987,0.10289746,0.014189754,0.8288516,0.04988213,0.00077866274],"about_ca_topic_score_codex":0.0000065542813,"about_ca_topic_score_gemma":0.00003907489,"teacher_disagreement_score":0.86427546,"about_ca_system_score_codex":0.0006198696,"about_ca_system_score_gemma":0.0020341896,"threshold_uncertainty_score":0.65095896},"labels":[],"label_agreement":null},{"id":"W4398946215","doi":"10.7910/dvn/wndofl","title":"Replication data for Identifying science in the news","year":2022,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Replication (statistics); Computer science; Computational biology; Data science; Information retrieval; Biology; Virology","score_opus":0.08390283603802001,"score_gpt":0.36997543838186797,"score_spread":0.28607260234384796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398946215","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.6361783e-7,0.0000019862803,0.19146685,0.000056807698,0.00022792161,0.0006200071,0.8075169,0.00008265217,0.000026160124],"genre_scores_gemma":[0.000005433988,0.00019447325,0.043314826,0.0007953631,0.00007038143,0.00029987644,0.955283,0.00000929535,0.000027365688],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961837,0.00014293214,0.0004515161,0.0018953915,0.0009275354,0.00039894367],"domain_scores_gemma":[0.9780872,0.00027559165,0.00041838706,0.021082131,0.00008428886,0.0000524279],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.004298416,0.00022645887,0.00027046484,0.00058701326,0.0005163302,0.0006775508,0.025952876,0.00007152939,0.0019639155],"category_scores_gemma":[0.0017792835,0.00019168042,0.00006670383,0.001933184,0.0001747713,0.0032001736,0.008608898,0.0004442435,0.0007245177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027457577,0.000043392698,0.0000014458916,0.000023316648,0.0000053502886,0.000012036771,0.000032000346,0.0000070078204,0.000036578956,0.00092858734,0.99528104,0.0036265245],"study_design_scores_gemma":[0.00010803918,0.000020884994,0.000013077561,0.000016591175,0.000035096156,0.000013038092,0.0000728691,0.0027556252,0.00002551486,0.0012177097,0.99550277,0.00021876894],"about_ca_topic_score_codex":0.00045224893,"about_ca_topic_score_gemma":0.0004757919,"teacher_disagreement_score":0.14815202,"about_ca_system_score_codex":0.00021555647,"about_ca_system_score_gemma":0.00033829265,"threshold_uncertainty_score":0.99940926},"labels":[],"label_agreement":null},{"id":"W4399665456","doi":"10.18438/eblip30521","title":"Machine-learning Recommender Systems Can Inform Collection Development Decisions","year":2024,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Recommender system; Information retrieval; Collaborative filtering; Cosine similarity; World Wide Web; Naive Bayes classifier; Artificial intelligence; Support vector machine; Cluster analysis","score_opus":0.021566165454653587,"score_gpt":0.28118580625305634,"score_spread":0.2596196407984028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399665456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009824569,0.0015789333,0.9688515,0.022680905,0.0002525361,0.00024922183,0.0000016314502,0.0010977031,0.0051893014],"genre_scores_gemma":[0.35085976,0.008757782,0.6092137,0.029000225,0.000089329995,0.00025311514,0.00013325238,0.000026654252,0.0016661971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986091,0.00015841512,0.0005184057,0.00019587735,0.00034609062,0.00017205712],"domain_scores_gemma":[0.9971633,0.0021703898,0.00022666465,0.0002537207,0.00007812371,0.00010780973],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007343705,0.00014703674,0.00012585771,0.00053978455,0.0003865317,0.0019919658,0.00033300425,0.00007096603,0.00003224059],"category_scores_gemma":[0.0011032899,0.00012934627,0.00003520728,0.0013217267,0.00001864991,0.23841038,0.0002159019,0.00034099893,0.00005786754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060758382,0.000028274873,0.0002677453,0.00018498882,0.00006855848,0.000011345118,0.0018488779,0.0037253245,0.000022870543,0.6014673,0.007428494,0.38488543],"study_design_scores_gemma":[0.000052003663,0.000047812333,0.00012799185,0.00032514732,0.000009563923,0.000029316496,0.00017713466,0.3299591,0.00068022555,0.00016532201,0.668295,0.00013136746],"about_ca_topic_score_codex":0.000011601651,"about_ca_topic_score_gemma":1.61935e-7,"teacher_disagreement_score":0.66086656,"about_ca_system_score_codex":0.00005808015,"about_ca_system_score_gemma":0.0003957205,"threshold_uncertainty_score":0.99904406},"labels":[],"label_agreement":null},{"id":"W4399828186","doi":"10.1007/978-3-031-54071-4_7","title":"Comparison of Information Structures and Their Blackwell Ordering","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","score_opus":0.011326714725242151,"score_gpt":0.2618874376106657,"score_spread":0.2505607228854235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026973972,0.0085720755,0.90095836,0.00004437328,0.00035048986,0.00057099917,0.00003258425,0.00035921924,0.08908491],"genre_scores_gemma":[0.9880456,0.00007061927,0.0017608755,0.00003010281,0.00010179143,0.00002062718,0.000011474622,0.000024480365,0.009934448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986199,0.000017591232,0.00070046587,0.00026322072,0.00024755456,0.00015123656],"domain_scores_gemma":[0.9985697,0.00009529089,0.00056418544,0.0005556144,0.00016471188,0.000050494134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018757043,0.00029700337,0.00078328454,0.00033983146,0.0000431015,0.00020889955,0.00047835655,0.0002077705,0.000004680619],"category_scores_gemma":[0.000011969277,0.00022961607,0.00012436874,0.000056405843,0.00005922209,0.00045924028,0.00016460971,0.0002679365,0.000021224323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004241515,0.0000020799348,0.000019581947,0.00037803283,0.00019644284,0.0000014406539,0.00063476583,0.00043811576,0.00020051438,0.9802515,0.0004147427,0.017458562],"study_design_scores_gemma":[0.00059019536,0.00020345255,0.000028497512,0.0011822811,0.00019556796,0.00003371182,0.00016570075,0.36560282,0.00083919655,0.23035784,0.3999241,0.0008766314],"about_ca_topic_score_codex":0.000032819527,"about_ca_topic_score_gemma":0.000010524605,"teacher_disagreement_score":0.98801863,"about_ca_system_score_codex":0.000052903455,"about_ca_system_score_gemma":0.000035325655,"threshold_uncertainty_score":0.9363472},"labels":[],"label_agreement":null},{"id":"W4399855255","doi":"10.18280/isi.290327","title":"LAMBDA: Lexicon and Aspect-Based Multimodal Data Analysis of Tweet","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lexicon; Natural language processing; Computer science; Lambda; Artificial intelligence; Physics; Optics","score_opus":0.03530651952822245,"score_gpt":0.3006870633019621,"score_spread":0.26538054377373965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399855255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014129151,0.006188737,0.97541404,0.0005476394,0.00039385798,0.00026594024,0.00040673162,0.0004239656,0.0022299571],"genre_scores_gemma":[0.88497436,0.0002039803,0.11377468,0.00012191866,0.00005761823,0.000016543185,0.00067472,0.000013990128,0.0001621671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748546,0.00013387346,0.0010790902,0.0004565039,0.00047744345,0.00036763403],"domain_scores_gemma":[0.9974366,0.00030646377,0.00043090977,0.0013647386,0.00034604582,0.000115242125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001094425,0.00030188088,0.000601984,0.0016020909,0.00015494319,0.0009121617,0.0009583438,0.00020616056,0.00007068231],"category_scores_gemma":[0.000331436,0.00031111395,0.00018948257,0.004003884,0.00046652104,0.011485509,0.0005928426,0.0002398221,0.00004141307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023169256,0.00007263667,0.0032022435,0.0018766421,0.002041026,0.00002258836,0.007155423,0.00682596,0.00034473068,0.1552723,0.001344417,0.8218189],"study_design_scores_gemma":[0.00014972175,0.00009534639,0.0059193564,0.00047194658,0.0011560033,0.000011048326,0.00016039381,0.9724937,0.0019620971,0.0067457967,0.010527484,0.00030707804],"about_ca_topic_score_codex":0.0009178599,"about_ca_topic_score_gemma":0.0002473143,"teacher_disagreement_score":0.9656678,"about_ca_system_score_codex":0.00028654397,"about_ca_system_score_gemma":0.00033491844,"threshold_uncertainty_score":0.9999341},"labels":[],"label_agreement":null},{"id":"W4399885315","doi":"10.21203/rs.3.rs-4587452/v1","title":"Topic Composition in AEA Journals","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Composition (language); Literature; Art","score_opus":0.10093493111736679,"score_gpt":0.4908727773061603,"score_spread":0.3899378461887935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399885315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103286475,0.02592718,0.81609243,0.022925118,0.0009938562,0.002898695,0.00003778389,0.0020697017,0.025768775],"genre_scores_gemma":[0.9685041,0.0009209457,0.02948042,0.00004399417,0.0002238968,0.0001973642,0.000017628478,0.00002438157,0.00058728736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962403,0.0005671237,0.00043491603,0.00081421115,0.001373514,0.0005698898],"domain_scores_gemma":[0.9978581,0.00023434115,0.00007901208,0.0012491607,0.00044631836,0.00013308912],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023917777,0.00020093207,0.00035683694,0.0018913416,0.00010571406,0.0008575683,0.0019380943,0.00027554718,0.000052336432],"category_scores_gemma":[0.00011927308,0.00018879911,0.00019563142,0.0015409217,0.000075910524,0.00023212394,0.005958311,0.0033560677,0.00020032188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034766872,0.00085043436,0.007770404,0.00462226,0.0002883797,0.003951319,0.004964943,0.0050208275,0.010654177,0.3458678,0.022388253,0.59358644],"study_design_scores_gemma":[0.000119341494,0.00009186381,0.0049221152,0.0033546328,0.0000071573536,0.000016807384,0.000047898713,0.046802804,0.0059466967,0.9355439,0.0027758705,0.0003709198],"about_ca_topic_score_codex":0.00012247023,"about_ca_topic_score_gemma":0.00006989968,"teacher_disagreement_score":0.8652176,"about_ca_system_score_codex":0.00063725165,"about_ca_system_score_gemma":0.000301382,"threshold_uncertainty_score":0.9989432},"labels":[],"label_agreement":null},{"id":"W4399900193","doi":"10.18280/ria.380311","title":"Summarizing Business News: Evaluating BART, T5, and PEGASUS for Effective Information Extraction","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information extraction; Computer science; Information retrieval","score_opus":0.03529687329299615,"score_gpt":0.3489899099083913,"score_spread":0.31369303661539516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399900193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005526122,0.0006622197,0.9909677,0.000701026,0.00033857586,0.00064198,0.000002393753,0.0004657849,0.00069418876],"genre_scores_gemma":[0.84444755,0.00019012099,0.15452869,0.00010495764,0.00013775266,0.00025145643,0.000016072521,0.00001774875,0.00030563545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987129,0.000050889746,0.00041466125,0.000391829,0.00017606073,0.0002536887],"domain_scores_gemma":[0.99853504,0.00063200004,0.00011483614,0.0003570628,0.00030465188,0.00005641205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075707736,0.00016108896,0.00017743462,0.00028515613,0.00022225776,0.0005455548,0.0002820518,0.00007312988,0.000008818616],"category_scores_gemma":[0.0005013948,0.00015739571,0.00007959765,0.0009271237,0.000044303324,0.0027909335,0.00012444783,0.00015395888,0.0000670046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000083632385,0.0000146570255,0.000030079535,0.00017822033,0.000016482762,0.0000025199863,0.0011183408,0.008939306,0.0075428956,0.029461218,0.00018921467,0.9524987],"study_design_scores_gemma":[0.000022670394,0.00009841667,0.00006325021,0.00019742711,0.000023812423,0.000025679212,0.0002567096,0.92642003,0.044707622,0.015239501,0.012761829,0.0001830682],"about_ca_topic_score_codex":0.00003953667,"about_ca_topic_score_gemma":0.000016763774,"teacher_disagreement_score":0.9523156,"about_ca_system_score_codex":0.00010343702,"about_ca_system_score_gemma":0.000057908892,"threshold_uncertainty_score":0.64184105},"labels":[],"label_agreement":null},{"id":"W4401043913","doi":"10.18653/v1/2024.naacl-long.454","title":"Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Automatic summarization; Argument (complex analysis); Key (lock); Metric (unit); Computer science; Point (geometry); Engineering; Artificial intelligence; Computer security; Mathematics; Operations management","score_opus":0.02062459436336553,"score_gpt":0.3120638485940622,"score_spread":0.29143925423069666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401043913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16474417,0.0003882621,0.83374333,0.00018286584,0.00012724093,0.00030619773,2.2573927e-7,0.00036655448,0.00014112967],"genre_scores_gemma":[0.8071696,0.000051575193,0.19254422,0.000051008406,0.00008422307,0.000050538772,0.0000142197105,0.000009007162,0.000025575593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824077,0.00018409984,0.00038322667,0.0005969995,0.00041905977,0.00017584067],"domain_scores_gemma":[0.9993197,0.00010298956,0.00006420529,0.0003373454,0.00012712588,0.00004868659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019536468,0.00013700605,0.00017345125,0.00075472373,0.00009591955,0.0005509399,0.0001763519,0.00004843914,0.000022739223],"category_scores_gemma":[0.00017464615,0.00013231138,0.000025886777,0.0015821664,0.000012381948,0.0024082146,0.00013248682,0.00010823552,0.0000042114116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013827057,0.00006969274,0.0009735634,0.0001279805,0.000031371274,0.000021502887,0.0027297954,0.015659919,0.13077699,0.04800265,0.000022966946,0.8015822],"study_design_scores_gemma":[0.00010910379,0.000041658146,0.0020416626,0.00008828846,0.000020894237,0.000007497063,0.000037482034,0.9463562,0.045335114,0.005782547,0.00002547412,0.00015408422],"about_ca_topic_score_codex":0.00005206406,"about_ca_topic_score_gemma":0.0001819533,"teacher_disagreement_score":0.93069625,"about_ca_system_score_codex":0.00044513843,"about_ca_system_score_gemma":0.00009858124,"threshold_uncertainty_score":0.5395502},"labels":[],"label_agreement":null},{"id":"W4401784090","doi":"10.1007/978-3-031-66694-0_17","title":"Citation Polarity Identification in Scientific Research Articles Using Deep Learning Methods","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Identification (biology); Polarity (international relations); Citation; Computer science; Information retrieval; Data science; Library science; Chemistry; Botany; Biology; Biochemistry","score_opus":0.1929742432770527,"score_gpt":0.4777759264100746,"score_spread":0.2848016831330219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401784090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004179615,0.00097598677,0.9821496,0.0004039466,0.00019542938,0.00035792758,0.0000015299837,0.0001542763,0.015343343],"genre_scores_gemma":[0.19762936,0.0007312869,0.8005236,0.000053533025,0.000016775704,0.00003214596,0.000030821062,0.000011573336,0.00097090384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709237,0.00024022936,0.0009774191,0.00053132,0.0008258338,0.00033284805],"domain_scores_gemma":[0.9961043,0.00051644765,0.000313244,0.0020024127,0.0009820524,0.0000815326],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011648099,0.00018340388,0.00023710709,0.005754588,0.0009531417,0.00278921,0.0030663048,0.00014408138,0.000003318331],"category_scores_gemma":[0.00031445367,0.00019886765,0.000049476726,0.0035447942,0.0014919254,0.010863685,0.0031317188,0.001149344,0.000050876664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.301662e-7,0.00001039289,0.00005243911,0.000024076035,0.0000025841396,3.5648006e-7,0.0031619626,0.0010007323,0.00034338073,0.60838646,0.0000039352026,0.38701308],"study_design_scores_gemma":[0.0000525084,0.000013887526,0.00053038937,0.00017389705,0.0000038528283,0.0000063967855,0.00006812186,0.8091373,0.00018746722,0.18114965,0.008507537,0.0001690111],"about_ca_topic_score_codex":0.000039485803,"about_ca_topic_score_gemma":0.00005561398,"teacher_disagreement_score":0.8081365,"about_ca_system_score_codex":0.0005608727,"about_ca_system_score_gemma":0.00026508697,"threshold_uncertainty_score":0.998246},"labels":[],"label_agreement":null},{"id":"W4401943123","doi":"10.1109/tkde.2024.3443928","title":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Rectification; Key (lock); Artificial intelligence; Information extraction; Information retrieval; Pattern recognition (psychology)","score_opus":0.02764258680815602,"score_gpt":0.2946802442361714,"score_spread":0.2670376574280154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401943123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014307059,0.0005329027,0.9958149,0.00012147774,0.0006520353,0.00017553312,0.000020132393,0.0011372541,0.000115065646],"genre_scores_gemma":[0.8792195,0.0007122389,0.11972429,0.000023657756,0.00007130396,0.00007351507,0.000064242275,0.000020265972,0.00009099041],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988718,0.000024502333,0.00033649462,0.00041156294,0.00016696414,0.00018868769],"domain_scores_gemma":[0.998861,0.00015143515,0.00003896094,0.0007999416,0.000068312125,0.00008031613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037443754,0.00018556317,0.00014221438,0.000518357,0.00014380844,0.00037815978,0.00043114144,0.000084730455,0.000010462047],"category_scores_gemma":[0.0000124886965,0.0001869891,0.00004757847,0.0007633236,0.000011489036,0.0051786243,0.000014393299,0.00029007057,0.00009696974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006916057,0.00006700731,0.0000014287224,0.00022525908,0.00009383534,0.0000037154955,0.0013754164,0.0242292,0.032894284,0.001153876,0.0003465964,0.9396025],"study_design_scores_gemma":[0.00009834542,0.00003315205,0.000009359777,0.00013557402,0.000041759828,0.000026439915,0.000018366005,0.9497723,0.035216752,0.00013639651,0.014302749,0.00020878405],"about_ca_topic_score_codex":0.000019007442,"about_ca_topic_score_gemma":0.000014148469,"teacher_disagreement_score":0.9393937,"about_ca_system_score_codex":0.00012212439,"about_ca_system_score_gemma":0.00003582349,"threshold_uncertainty_score":0.76251936},"labels":[],"label_agreement":null},{"id":"W4402422143","doi":"10.1515/lingvan-2023-0102","title":"Bibliographic bias and information-density sampling","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Marcus och Amalia Wallenbergs minnesfond","keywords":"Sampling bias; Sampling (signal processing); Statistics; Information retrieval; Computer science; Geography; Mathematics; Sample size determination; Telecommunications","score_opus":0.025144856216042854,"score_gpt":0.29749520760234294,"score_spread":0.2723503513863001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402422143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003108893,0.0007748639,0.9896422,0.00012300727,0.00061276584,0.000077845005,0.000004662995,0.0011170815,0.004538704],"genre_scores_gemma":[0.70375216,0.0003451489,0.2953639,0.0002694214,0.00021931785,0.0000049302525,0.000006486187,0.00000769359,0.000030932566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990843,0.000018873945,0.0002474861,0.00023508239,0.00022405964,0.00019021814],"domain_scores_gemma":[0.9989987,0.00022755758,0.00005338088,0.00039341018,0.00024874782,0.00007820459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029587667,0.0001277588,0.00014180731,0.0016832018,0.00010680229,0.0006350323,0.00032194055,0.000060183535,0.0000038442345],"category_scores_gemma":[0.0011316742,0.00012013071,0.00007298486,0.002736359,0.000049879138,0.00047016793,0.00023398895,0.00017894877,0.00004269451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014158076,0.000009976211,0.0020879149,0.00008953161,0.000049730126,0.00003598423,0.0006902107,0.000049041737,0.000074796226,0.9393233,0.0016369332,0.05595113],"study_design_scores_gemma":[0.00012113676,0.00007187185,0.0035702435,0.00017808635,0.00007043198,0.000031933792,0.000044542303,0.09879767,0.0015598014,0.28517216,0.60980713,0.0005749663],"about_ca_topic_score_codex":0.000030919495,"about_ca_topic_score_gemma":0.000008130378,"teacher_disagreement_score":0.7006433,"about_ca_system_score_codex":0.000016796426,"about_ca_system_score_gemma":0.000033011213,"threshold_uncertainty_score":0.61236316},"labels":[],"label_agreement":null},{"id":"W4402683031","doi":"10.18653/v1/2024.sighan-1.1","title":"Automatic Quote Attribution in Chinese Literary Works","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Attribution; Computer science; Authorship attribution; Natural language processing; Psychology; Social psychology","score_opus":0.006278342811272761,"score_gpt":0.2905591747985497,"score_spread":0.28428083198727694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402683031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037717637,0.0012151398,0.9572699,0.0008468749,0.00008715004,0.00008005587,2.7520136e-7,0.0017079334,0.0010750153],"genre_scores_gemma":[0.847939,0.000029129973,0.15149486,0.00013978795,0.000024884805,0.000016946196,0.0000033228407,0.000005283583,0.0003467622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915427,0.00003522942,0.00020786822,0.0002913699,0.00014459727,0.00016666065],"domain_scores_gemma":[0.9994744,0.00007769302,0.00001868123,0.0003763089,0.00001798029,0.00003494615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021894235,0.00010073416,0.00012649896,0.00028920054,0.000023054305,0.0002785669,0.00040524916,0.000049051945,0.00006590289],"category_scores_gemma":[0.000019620393,0.00007576746,0.000063401356,0.0015970143,0.000013695548,0.0013936346,0.00016976673,0.00014970174,0.00010520319],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7118274e-7,0.000028193115,0.0016412068,0.000025856549,0.000009903959,0.00007644678,0.00038991345,0.00004392993,0.00034699007,0.07320064,0.00048253674,0.9237539],"study_design_scores_gemma":[0.000039316135,0.000012198541,0.005940661,0.00014115381,0.000001963556,0.000008728888,0.0000015152357,0.86304283,0.00035901507,0.12927835,0.0010616111,0.000112693284],"about_ca_topic_score_codex":0.000011001036,"about_ca_topic_score_gemma":0.000019087356,"teacher_disagreement_score":0.9236412,"about_ca_system_score_codex":0.000078971774,"about_ca_system_score_gemma":0.00002473876,"threshold_uncertainty_score":0.30897072},"labels":[],"label_agreement":null},{"id":"W4402703397","doi":"10.1007/978-3-031-67317-7_9","title":"Machine Learning Based Extractive Text Summarization Using Document Aware and Document Unaware Features","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in systems, decision and control","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Natural language processing; Artificial intelligence; World Wide Web","score_opus":0.02520959795395034,"score_gpt":0.3316281685645455,"score_spread":0.3064185706105952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402703397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000363357,0.18255785,0.8091364,0.0002591627,0.0009074786,0.0013855234,0.000023102088,0.0003155115,0.0053786417],"genre_scores_gemma":[0.9016917,0.016588636,0.011379611,0.00030732623,0.00029080609,0.000227781,0.000035693927,0.00013878707,0.0693397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971598,0.00012193855,0.0007778732,0.0010094874,0.0006548326,0.00027607716],"domain_scores_gemma":[0.9977903,0.0009192095,0.0004567963,0.00045867456,0.0002874037,0.00008763428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075174024,0.00054304086,0.0010762948,0.00062770856,0.00028215547,0.00040436056,0.00031574318,0.00024419415,0.0000074365134],"category_scores_gemma":[0.00013510321,0.00043185923,0.00012386867,0.00015315104,0.00013527008,0.00034469616,0.0005184625,0.00057566783,0.00000555283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045563866,0.00006372336,0.0009993966,0.0018217772,0.0028748186,0.0013056685,0.0035607037,0.016594894,0.000112544076,0.42972517,0.0017996519,0.540686],"study_design_scores_gemma":[0.0057218624,0.0008237204,0.00021692675,0.019649416,0.0011635673,0.00022991933,0.0022311104,0.43605754,0.00004504035,0.29892522,0.23168308,0.0032525777],"about_ca_topic_score_codex":0.000073687064,"about_ca_topic_score_gemma":0.00009915673,"teacher_disagreement_score":0.9016553,"about_ca_system_score_codex":0.00042685342,"about_ca_system_score_gemma":0.000052041163,"threshold_uncertainty_score":0.9998133},"labels":[],"label_agreement":null},{"id":"W4402721984","doi":"10.1145/3670947.3670971","title":"TextVista: NLP-Enriched Time-Series Text Data Visualizations","year":2024,"lang":"en","type":"article","venue":"Graphics Interface","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Bruyère","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya; Ontario Centre of Innovation","keywords":"Computer science; Natural language processing; Series (stratigraphy); Artificial intelligence; Time series; Visualization; Information retrieval; Machine learning","score_opus":0.03054556567332933,"score_gpt":0.3480504868164028,"score_spread":0.3175049211430735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402721984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022814023,0.0021789118,0.9911837,0.0015138127,0.0002422203,0.00013973122,0.000030677176,0.0019326546,0.0025501663],"genre_scores_gemma":[0.80989385,0.0007212372,0.17775801,0.00042381696,0.00013518875,0.000040538802,0.0001379168,0.00007734008,0.010812083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980627,0.00007875008,0.00035159866,0.00086341996,0.00033877423,0.0003047839],"domain_scores_gemma":[0.99734545,0.00016477726,0.00007261261,0.0021971846,0.00013199306,0.000088008666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042363425,0.00023301416,0.00022919055,0.00043622474,0.00016642168,0.0007057574,0.002878105,0.00009761297,0.00008696389],"category_scores_gemma":[0.00014872118,0.00021724426,0.000092935385,0.002187085,0.00016671218,0.002291604,0.0016039929,0.00030812446,0.00042234172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003769669,0.00007213686,0.000056167606,0.000047798632,0.00015426712,0.000031091244,0.0006230078,0.00008807589,0.0066279913,0.92766994,0.053262763,0.011362976],"study_design_scores_gemma":[0.00008944525,0.00012309603,0.00007950337,0.00014026131,0.00007186484,0.000049385955,0.000057514815,0.43917978,0.009011132,0.12980263,0.42075312,0.0006422785],"about_ca_topic_score_codex":0.000015297737,"about_ca_topic_score_gemma":0.000033590488,"teacher_disagreement_score":0.81342566,"about_ca_system_score_codex":0.00004526063,"about_ca_system_score_gemma":0.000078323756,"threshold_uncertainty_score":0.8858964},"labels":[],"label_agreement":null},{"id":"W4402727755","doi":"10.1109/cvpr52733.2024.01054","title":"Discovering and Mitigating Visual Biases Through Keyword Explanation","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Data science; Information retrieval; Natural language processing","score_opus":0.024809341216219888,"score_gpt":0.3365943777522731,"score_spread":0.31178503653605316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402727755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06890048,0.00036548977,0.9264904,0.00033784824,0.000051613806,0.000042377036,3.4885582e-7,0.00077437167,0.0030370269],"genre_scores_gemma":[0.7941264,0.000052748273,0.20547445,0.00009750393,0.000033137167,0.000007514041,0.0000017418173,0.0000051158313,0.00020142314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999351,0.000013945364,0.00012142355,0.00027039766,0.00013007148,0.00011314877],"domain_scores_gemma":[0.99966383,0.00014947017,0.00001972728,0.00012981678,0.000014520243,0.00002260703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008152752,0.00007643896,0.000076660544,0.0000722962,0.000063994536,0.0003351964,0.00014445718,0.00002020253,0.000009226719],"category_scores_gemma":[0.000040921892,0.00006317891,0.000028710105,0.00033146783,0.000022398946,0.0016942662,0.00016139892,0.000058454072,0.00000803278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.765416e-7,0.000022620887,0.0006741497,0.0000520364,0.000043522985,0.000049988186,0.0022249175,0.00021608117,0.015441489,0.64142656,0.0007832619,0.33906442],"study_design_scores_gemma":[0.00006853771,0.00006522361,0.00039655442,0.00023948439,0.000014264903,0.000027190688,0.0002628618,0.78191715,0.15626214,0.05642526,0.0039998195,0.00032150105],"about_ca_topic_score_codex":0.00004469326,"about_ca_topic_score_gemma":0.000022361963,"teacher_disagreement_score":0.7817011,"about_ca_system_score_codex":0.00002214898,"about_ca_system_score_gemma":0.00001138949,"threshold_uncertainty_score":0.32323068},"labels":[],"label_agreement":null},{"id":"W4402731657","doi":"10.23977/jaip.2024.070315","title":"Siamese Network-Based Text Similarity Algorithm Research","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Similarity (geometry); Computer science; Algorithm; Artificial intelligence","score_opus":0.1152017498653385,"score_gpt":0.4580224853169203,"score_spread":0.3428207354515818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402731657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009001866,0.002061047,0.9817089,0.013600132,0.0008412897,0.00014084249,0.0000010573353,0.00017011471,0.001386623],"genre_scores_gemma":[0.16317017,0.00040173242,0.83447474,0.00066737994,0.0011420818,0.0000071116883,5.5081125e-7,0.000025645053,0.000110559144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954332,0.0008846021,0.0010964278,0.00045032785,0.0015420261,0.00059340143],"domain_scores_gemma":[0.99184346,0.004737862,0.00045462963,0.000660498,0.002073685,0.00022985078],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01045457,0.00020230147,0.00034262374,0.00071982684,0.00029471374,0.0011702677,0.0017079846,0.00014522547,0.00007081413],"category_scores_gemma":[0.0039020088,0.00017367605,0.00027661028,0.0032222325,0.00021924957,0.003955394,0.00027934494,0.0019286873,0.0002149293],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049746108,0.00024279783,0.000004265883,0.000015611591,0.00008336032,0.00092216127,0.00041020874,0.008079293,0.00076578796,0.086889215,0.0047946176,0.8977429],"study_design_scores_gemma":[0.000016331438,0.0004784322,0.0000034605325,0.00017483684,0.000057602338,0.0002538169,0.00032162401,0.63560236,0.029881284,0.22175188,0.11123624,0.00022213138],"about_ca_topic_score_codex":0.000036568614,"about_ca_topic_score_gemma":0.000011993218,"teacher_disagreement_score":0.8975208,"about_ca_system_score_codex":0.00026364252,"about_ca_system_score_gemma":0.0006844997,"threshold_uncertainty_score":0.9998666},"labels":[],"label_agreement":null},{"id":"W4402747380","doi":"10.23977/acss.2024.080603","title":"Research on Graph-based Text Summarization Extraction Algorithm","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Graph; Text graph; Artificial intelligence; Natural language processing; Information retrieval; Algorithm; Theoretical computer science","score_opus":0.03971752346566083,"score_gpt":0.38430624482742454,"score_spread":0.3445887213617637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402747380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004091674,0.012592428,0.98493016,0.00016794218,0.0007900264,0.00030639634,0.0000025953154,0.00037427407,0.00042699202],"genre_scores_gemma":[0.85774994,0.0013527187,0.14017367,0.00010400842,0.00035909624,0.00013486847,0.000009909146,0.00002404106,0.00009175306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975526,0.00036966582,0.00040935847,0.00074896315,0.0005792754,0.0003401719],"domain_scores_gemma":[0.9984326,0.00083698175,0.000071238566,0.00043631374,0.00014732125,0.0000755771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013671932,0.00018443669,0.0002614366,0.0009993644,0.00014667487,0.00064415246,0.0004496682,0.000094027855,0.0000025559066],"category_scores_gemma":[0.000010473331,0.00015981556,0.000060820443,0.0017087229,0.0000749805,0.0014098883,0.000111813664,0.00035024385,0.000018379062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045359848,0.000064073036,0.00011218886,0.00012424678,0.000012692485,0.00008154937,0.000102983686,0.06327392,0.000280768,0.04853758,0.00032521546,0.88708025],"study_design_scores_gemma":[0.00011070033,0.00021756443,0.0000767972,0.0005492852,0.0000025633892,0.000011966726,0.000016973874,0.96761054,0.0007817481,0.013136564,0.01729934,0.00018593919],"about_ca_topic_score_codex":0.000037020407,"about_ca_topic_score_gemma":0.000012012424,"teacher_disagreement_score":0.90433663,"about_ca_system_score_codex":0.000096791744,"about_ca_system_score_gemma":0.00004365887,"threshold_uncertainty_score":0.65170896},"labels":[],"label_agreement":null},{"id":"W4402761492","doi":"10.3390/systems12090380","title":"Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering","year":2024,"lang":"en","type":"article","venue":"Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Social Science Fund of China; Fundo para o Desenvolvimento das Ciências e da Tecnologia; China Scholarship Council; Science and Technology Development Fund","keywords":"Cluster analysis; Coding (social sciences); Computer science; Psychology; Natural language processing; Artificial intelligence; Mathematics; Statistics","score_opus":0.015782493697655758,"score_gpt":0.29754658303594267,"score_spread":0.2817640893382869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402761492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015370261,0.0003060909,0.9793368,0.00011798305,0.0015395669,0.0008742446,0.0000052479672,0.0022106015,0.00023922237],"genre_scores_gemma":[0.9697623,0.0000017375544,0.029173167,0.000017934477,0.00011102064,0.00035146196,0.0000027412214,0.000035403675,0.0005441833],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979332,0.00029747814,0.00048096062,0.00065701635,0.00026649132,0.00036483054],"domain_scores_gemma":[0.9983774,0.0007001511,0.00013933417,0.00046434512,0.00019289467,0.00012591743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011603845,0.00021664223,0.00037771114,0.0005362662,0.00018792244,0.00072565454,0.0005843599,0.00007965223,0.0000011333896],"category_scores_gemma":[0.00024780183,0.00020405772,0.00013288583,0.0009075409,0.000025171319,0.000640398,0.00028823045,0.00021951502,0.00005677059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007886645,0.000036811653,0.00022271153,0.0033802881,0.0006660297,0.00045369143,0.019989435,0.01858346,0.8151386,0.03565552,0.0014249847,0.103659816],"study_design_scores_gemma":[0.00014793107,0.00022198858,0.000021987431,0.002099331,0.000020382677,0.0002634147,0.0014317823,0.9779459,0.008155003,0.0000896786,0.00928668,0.0003159243],"about_ca_topic_score_codex":0.000043263353,"about_ca_topic_score_gemma":0.0000070397573,"teacher_disagreement_score":0.95936245,"about_ca_system_score_codex":0.000543861,"about_ca_system_score_gemma":0.00006920009,"threshold_uncertainty_score":0.8321233},"labels":[],"label_agreement":null},{"id":"W4402978475","doi":"10.1109/tits.2024.3462951","title":"eMARLIN+: Addressing Partial Observability to Promote Traffic Signal Coordination by Leveraging Historical Information","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Observability; SIGNAL (programming language); Computer science; Transport engineering; Computer security; Engineering; Mathematics","score_opus":0.04013403747008683,"score_gpt":0.28761673632990536,"score_spread":0.24748269885981855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402978475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020510312,0.00015554171,0.9752092,0.00047427427,0.0014737771,0.0008164042,0.00006820312,0.0012694651,0.000022844783],"genre_scores_gemma":[0.99210525,0.000017410306,0.007038287,0.00007945359,0.00005137906,0.0003603522,0.00006342418,0.000023509598,0.000260942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712795,0.00011430522,0.0010810571,0.00059413037,0.00075491273,0.0003276206],"domain_scores_gemma":[0.99885845,0.0001228638,0.00014391367,0.00040773855,0.00027191112,0.00019509354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055899826,0.0003004282,0.00032740526,0.0005450732,0.00025899097,0.0004961976,0.00042149884,0.00015102881,0.0000358947],"category_scores_gemma":[0.000005925377,0.00030481082,0.00023627286,0.0012806377,0.000024421903,0.0024422093,8.588084e-7,0.00034926704,0.00010578532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053768297,0.00027219858,0.000021471611,0.0003556625,0.0001274272,0.000011957516,0.009016496,0.5899435,0.0052586817,0.0014101317,0.0014982128,0.39203045],"study_design_scores_gemma":[0.0002004623,0.00029376132,0.00004705215,0.00050149165,0.00010301349,0.000009460994,0.00025847278,0.8376333,0.08723959,0.00013848089,0.07291586,0.00065905537],"about_ca_topic_score_codex":0.00016992328,"about_ca_topic_score_gemma":0.000037576134,"teacher_disagreement_score":0.9715949,"about_ca_system_score_codex":0.0010708052,"about_ca_system_score_gemma":0.0000995351,"threshold_uncertainty_score":0.9999404},"labels":[],"label_agreement":null},{"id":"W4403134937","doi":"10.1080/08839514.2024.2403904","title":"Integration of Neural Embeddings and Probabilistic Models in Topic Modeling","year":2024,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Probabilistic logic; Artificial neural network; Statistical model; Artificial intelligence; Machine learning; Data mining; Data science; Theoretical computer science","score_opus":0.06095076820110108,"score_gpt":0.31866020918327603,"score_spread":0.25770944098217496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403134937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09330433,0.00015340169,0.9055214,0.00011956291,0.00004852145,0.0001756157,4.311204e-7,0.00016221026,0.00051451346],"genre_scores_gemma":[0.94055814,0.00002650842,0.05931877,0.000025112999,0.000019541449,0.000036789996,0.000001048182,0.000006939371,0.0000071780923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988509,0.000015769072,0.00041675958,0.00040000415,0.00015448769,0.00016212575],"domain_scores_gemma":[0.9995428,0.00009021293,0.000041211333,0.0002475104,0.000046406287,0.000031898297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478132,0.000116740055,0.00016946193,0.000225292,0.000031278934,0.000116487274,0.00031791508,0.00005163978,0.0000029773198],"category_scores_gemma":[0.000029693536,0.000107678956,0.000035000372,0.0006123945,0.00006106499,0.0004628247,0.00012968208,0.0001611644,0.000004246773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002162423,0.000012349057,8.2526634e-7,0.000016066144,0.0000020296955,0.0000017880747,0.0010620622,0.09900569,0.011753876,0.66049856,6.6041986e-7,0.22764394],"study_design_scores_gemma":[0.000002347001,0.000009549275,7.80935e-7,0.000024392792,0.0000024010171,8.6442844e-7,0.000051136747,0.5289627,0.018309213,0.45257998,0.0000019973425,0.000054696455],"about_ca_topic_score_codex":0.000058830647,"about_ca_topic_score_gemma":0.00007662445,"teacher_disagreement_score":0.8472538,"about_ca_system_score_codex":0.000038839917,"about_ca_system_score_gemma":0.000022995511,"threshold_uncertainty_score":0.43910202},"labels":[],"label_agreement":null},{"id":"W4403181741","doi":"10.1007/978-3-031-63821-3_6","title":"Natural Language Processing for Emotion Recognition and Analysis","year":2024,"lang":"en","type":"book-chapter","venue":"˜The œSpringer series in applied machine learning","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Natural language processing; Speech recognition; Psychology; Natural (archaeology); Communication; Biology; Paleontology","score_opus":0.01109883442005598,"score_gpt":0.2515212515609263,"score_spread":0.24042241714087031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403181741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032931313,0.009447808,0.91421074,0.00033004535,0.000160801,0.00092430966,0.000016579277,0.001325376,0.073255055],"genre_scores_gemma":[0.7500165,0.000405733,0.1283233,0.00018674444,0.0002869542,0.00026492326,0.00040713284,0.00017046135,0.11993824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982834,0.00001993366,0.00040347647,0.00076819526,0.00025294122,0.00027207978],"domain_scores_gemma":[0.99907947,0.00010696139,0.00031256687,0.00040803567,0.000055184788,0.00003781383],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050315633,0.0003791755,0.00050135783,0.0007139858,0.00023147292,0.0003446092,0.00047243404,0.00018726164,0.000013152673],"category_scores_gemma":[0.00001674579,0.0003164116,0.00018695602,0.0004150911,0.00009804719,0.0002558981,0.00047660575,0.0010741617,0.000013916213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035864192,0.000008516831,0.00003231551,0.000284539,0.0003537081,0.000016835293,0.0025167635,0.0005607758,0.00064532965,0.04810122,0.0000089123405,0.9474352],"study_design_scores_gemma":[0.0004792689,0.00012606822,0.00014423646,0.0005324058,0.001688056,0.000039280276,0.000302364,0.6589366,0.00061438244,0.2713988,0.06398088,0.0017575976],"about_ca_topic_score_codex":0.000021249472,"about_ca_topic_score_gemma":0.0003315855,"teacher_disagreement_score":0.94567764,"about_ca_system_score_codex":0.000108436914,"about_ca_system_score_gemma":0.000021365822,"threshold_uncertainty_score":0.9999288},"labels":[],"label_agreement":null},{"id":"W4403210328","doi":"10.1109/iri62200.2024.00029","title":"Accelerating Relational Keyword Queries With Embedded Predictive Neural Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Artificial neural network; Keyword search; Relational database; Information retrieval; Artificial intelligence; Data mining","score_opus":0.016837767891135235,"score_gpt":0.26378782246279087,"score_spread":0.24695005457165564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403210328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017455268,0.00019401405,0.985822,0.000511207,0.00008733797,0.00010899368,5.3714854e-7,0.0017143579,0.009816033],"genre_scores_gemma":[0.6747937,0.0000048594165,0.3240757,0.0001413303,0.00008858922,0.000028512364,0.000004505125,0.0000098552755,0.0008529285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989249,0.000034837958,0.0001829025,0.000402764,0.00025041273,0.00020418517],"domain_scores_gemma":[0.9993734,0.00015692927,0.000040892875,0.00029479552,0.00008316297,0.0000508567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012122484,0.00013744943,0.00012544489,0.00010663679,0.00012861523,0.0003222277,0.00032430878,0.000048673024,0.000045223765],"category_scores_gemma":[0.000017499777,0.00009909388,0.00005190741,0.00069604954,0.00005826013,0.0016286947,0.00016315177,0.00023112314,0.0000071259483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015274194,0.000022485203,0.0017119909,0.000010364615,0.000113907176,0.00007002207,0.00088688434,0.11009424,0.00011289048,0.82668805,0.0021277885,0.0581461],"study_design_scores_gemma":[0.000042001255,0.00008065085,0.0005623575,0.000026021924,0.000009676134,0.000019384843,0.000029026967,0.9921088,0.00035718232,0.006064954,0.0005642046,0.00013570733],"about_ca_topic_score_codex":0.0000072993435,"about_ca_topic_score_gemma":0.000022486007,"teacher_disagreement_score":0.8820146,"about_ca_system_score_codex":0.000046048783,"about_ca_system_score_gemma":0.00004267721,"threshold_uncertainty_score":0.40409312},"labels":[],"label_agreement":null},{"id":"W4403432858","doi":"10.1002/pra2.1017","title":"Exploratory Search in Digital Humanities: A Study of Visual Keyword/Result Linking","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Digital humanities; Information retrieval; Computer science; Humanities; World Wide Web; Art","score_opus":0.01574173510886453,"score_gpt":0.29249908303467237,"score_spread":0.27675734792580786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403432858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938787,0.000021889984,0.0035919622,0.00041456198,0.000059402886,0.00046047976,0.000003008126,0.00019054658,0.0013794022],"genre_scores_gemma":[0.998979,0.000008361272,0.00091061887,0.000017985763,0.0000049791283,0.0000480181,3.7691768e-7,0.000002112364,0.000028584409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871695,0.000001821048,0.00039491706,0.00014748386,0.0005742435,0.00016455821],"domain_scores_gemma":[0.99812436,0.00007261623,0.00030187235,0.000086762375,0.0014034187,0.000010998819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015028566,0.00006422008,0.00013397221,0.0013872526,0.00014003721,0.00031780102,0.00078501645,0.00006440084,1.1337561e-7],"category_scores_gemma":[0.0008835416,0.000050780483,0.00002438074,0.003967649,0.00015274447,0.0072042136,0.00043404466,0.00012900072,8.225254e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009168985,0.00017593562,0.08643063,0.00020863926,0.000040187017,9.388409e-8,0.03332985,0.000026382078,0.006224421,0.7868459,0.000112848364,0.086595945],"study_design_scores_gemma":[0.0028093485,0.0028248678,0.017898276,0.0009163793,0.00007403626,0.000011013926,0.11035552,0.21457687,0.32800466,0.31044137,0.0111000985,0.0009875497],"about_ca_topic_score_codex":0.0000030962851,"about_ca_topic_score_gemma":0.0000028710158,"teacher_disagreement_score":0.47640452,"about_ca_system_score_codex":0.00019500472,"about_ca_system_score_gemma":0.0001030287,"threshold_uncertainty_score":0.5222881},"labels":[],"label_agreement":null},{"id":"W4403494021","doi":"10.1561/116.20240044","title":"Automatic Medical Report Generation: Methods and Applications","year":2024,"lang":"en","type":"article","venue":"APSIPA Transactions on Signal and Information Processing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.015513525712463184,"score_gpt":0.3377518521077463,"score_spread":0.3222383263952831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403494021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001482919,0.0004630279,0.9963116,0.0011464794,0.00003918515,0.00014099137,0.0000010963327,0.00056239497,0.0011869372],"genre_scores_gemma":[0.45817685,0.00019872401,0.54033905,0.0008300607,0.00006146556,0.00025382134,0.000015003425,0.000007422477,0.00011763635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896455,0.000033431686,0.0004055225,0.00019876401,0.00028936093,0.00010835104],"domain_scores_gemma":[0.9995036,0.00007880331,0.00007577745,0.00015477122,0.000087977234,0.000099086385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005528878,0.000108854976,0.000119057455,0.0002795391,0.00033834486,0.00055075035,0.00013501316,0.000075178556,0.00006133478],"category_scores_gemma":[0.000013218127,0.00009214935,0.000033872653,0.0005782606,0.00006239593,0.004962514,0.000010061631,0.00018061105,0.000012482802],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6471505e-7,0.00000876007,8.2069107e-7,0.00007480056,0.000011073591,0.0000025704662,0.00031281123,0.0000725091,0.00010336781,0.01058684,0.000032650503,0.98879343],"study_design_scores_gemma":[0.00005777701,0.000025495983,0.000017840752,0.00007318206,0.00002223729,0.000346501,0.000041949348,0.9582738,0.0034875888,0.004649524,0.03287429,0.00012975748],"about_ca_topic_score_codex":0.000002823491,"about_ca_topic_score_gemma":7.7155215e-7,"teacher_disagreement_score":0.9886637,"about_ca_system_score_codex":0.000026006574,"about_ca_system_score_gemma":0.00011544803,"threshold_uncertainty_score":0.53108984},"labels":[],"label_agreement":null},{"id":"W4404401204","doi":"10.54195/irrj.19910","title":"Annotative Indexing","year":2025,"lang":"en","type":"preprint","venue":"Information Retrieval Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Tsinghua University; University of Glasgow","keywords":"Search engine indexing; Computer science; Information retrieval","score_opus":0.08469652661856103,"score_gpt":0.4552504328181435,"score_spread":0.37055390619958245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404401204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005260865,0.000103695376,0.9291891,0.0011651751,0.00021989801,0.0006821418,0.000028593406,0.0005410636,0.06754427],"genre_scores_gemma":[0.49999458,0.0010656529,0.4861001,0.001586719,0.00031180988,0.00042157172,0.00048024234,0.000032035965,0.010007269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99597454,0.0003386268,0.00069881295,0.00039535397,0.002059265,0.0005334219],"domain_scores_gemma":[0.9947589,0.0006633488,0.0002934341,0.001377565,0.0027850247,0.00012172086],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035546923,0.00022223598,0.0003216785,0.0023111259,0.0003065796,0.0010250395,0.0029476935,0.00039748225,0.000022405788],"category_scores_gemma":[0.0026647192,0.00022078896,0.0001466131,0.0029223599,0.00014579874,0.0027377422,0.006042666,0.002444451,0.00021398503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011613727,0.00007724597,0.00019137458,0.0007700101,0.00021311923,0.00001699317,0.010195987,0.0038050956,0.00011400067,0.5616689,0.020423902,0.40240723],"study_design_scores_gemma":[0.0004839082,0.00016717662,0.0007221558,0.00080851483,0.000015643842,0.000003983932,0.00043106155,0.35137397,0.031422187,0.4366107,0.17707989,0.0008808248],"about_ca_topic_score_codex":0.00005718113,"about_ca_topic_score_gemma":0.000002691161,"teacher_disagreement_score":0.4994685,"about_ca_system_score_codex":0.00059594476,"about_ca_system_score_gemma":0.0011588586,"threshold_uncertainty_score":0.99985695},"labels":[],"label_agreement":null},{"id":"W4404783428","doi":"10.18653/v1/2024.conll-1.1","title":"Words That Stick: Using Keyword Cohesion to Improve Text Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cohesion (chemistry); Segmentation; Natural language processing; Artificial intelligence; Information retrieval; Keyword search","score_opus":0.0256191780195542,"score_gpt":0.3269138498247393,"score_spread":0.3012946718051851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404783428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0132081695,0.000080458456,0.98356706,0.0004386541,0.00024443245,0.00020579602,7.785321e-7,0.00096832094,0.0012863149],"genre_scores_gemma":[0.4897544,0.000006840869,0.5089337,0.00027072744,0.000037773432,0.000011287139,0.0000011455534,0.000009464621,0.000974607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988434,0.000026375083,0.00016862586,0.00046112863,0.0002883541,0.00021212186],"domain_scores_gemma":[0.9993585,0.000075215,0.000031982327,0.00040889447,0.000042220916,0.000083230465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016343042,0.00012993143,0.00012245597,0.00025740758,0.00007508176,0.00036607235,0.00040654387,0.000040907948,0.000049785376],"category_scores_gemma":[0.000019057983,0.00010871953,0.000064135085,0.0008063009,0.000014493043,0.000914527,0.00027902878,0.00008744913,0.000119374476],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004348562,0.00003133943,0.00028308074,0.000030713854,0.000033839016,0.000029883742,0.00084845384,0.0010097035,0.32326582,0.029880263,0.001569548,0.643013],"study_design_scores_gemma":[0.00006306055,0.00008110516,0.00011888247,0.00007855751,0.000023999393,0.00000720926,0.00009596195,0.65033317,0.33861002,0.00796886,0.002337802,0.00028138075],"about_ca_topic_score_codex":0.000045256955,"about_ca_topic_score_gemma":0.00001938957,"teacher_disagreement_score":0.64932346,"about_ca_system_score_codex":0.00016479903,"about_ca_system_score_gemma":0.000044269447,"threshold_uncertainty_score":0.44334537},"labels":[],"label_agreement":null},{"id":"W4404851827","doi":"10.1080/01973533.2024.2433720","title":"A Bibliometric Review of Natural Language Processing Applications in Psychology from 1991 to 2023","year":2024,"lang":"en","type":"review","venue":"Basic and Applied Social Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Alberta; University of British Columbia","funders":"","keywords":"Psychology; Natural (archaeology); Social psychology; Cognitive psychology; Applied psychology","score_opus":0.049524424754623125,"score_gpt":0.46184174114458415,"score_spread":0.41231731638996105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404851827","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024011936,0.9590329,0.036780644,0.00038251598,0.000096473836,0.0010707524,0.00003493604,0.00014451344,0.0024548548],"genre_scores_gemma":[0.00013156021,0.9829823,0.013770695,0.0018186319,0.00018487507,0.0008987878,0.0001271272,0.000035879453,0.000050147406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997323,0.00012194329,0.0008812929,0.0011180339,0.00021470606,0.00034106083],"domain_scores_gemma":[0.9987118,0.00013179304,0.00042886296,0.00060488685,0.000047165013,0.00007546857],"candidate_categories":["metaepi_narrow","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0004250614,0.00039054983,0.0018881904,0.01084117,0.00006691728,0.000041436957,0.001140388,0.0003775145,0.000013558922],"category_scores_gemma":[0.000027316937,0.0003273361,0.0002617836,0.051308185,0.00013210461,0.00007523756,0.00034357875,0.00065490196,0.00007119077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011121882,0.00004717974,5.613059e-7,0.007197261,0.000037305814,0.0000042543165,0.00011341288,4.36232e-9,0.000007672692,0.0023052304,0.0041677784,0.9861182],"study_design_scores_gemma":[0.00012421238,0.00002300223,0.00006993616,0.007227592,0.0003366885,0.000008294201,0.000018619992,0.0000027802373,7.9655996e-7,0.005919559,0.9858562,0.0004123577],"about_ca_topic_score_codex":0.000018781313,"about_ca_topic_score_gemma":0.000014020448,"teacher_disagreement_score":0.98570585,"about_ca_system_score_codex":0.00004747947,"about_ca_system_score_gemma":0.00006655375,"threshold_uncertainty_score":0.99991786},"labels":[],"label_agreement":null},{"id":"W4404940533","doi":"10.1007/s42113-024-00214-8","title":"Lessons for Theory from Scientific Domains Where Evidence is Sparse or Indirect","year":2024,"lang":"en","type":"article","venue":"Computational Brain & Behavior","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; James S. McDonnell Foundation","keywords":"Epistemology; Computer science; Econometrics; Data science; Mathematics; Philosophy","score_opus":0.0854073085012884,"score_gpt":0.38960454482013085,"score_spread":0.30419723631884243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404940533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026650999,0.0017378049,0.9634704,0.0059673623,0.0005415803,0.0005695296,0.00017032842,0.0008593284,0.000032658605],"genre_scores_gemma":[0.52419287,0.000013697993,0.47132698,0.00071716175,0.00013901366,0.00042348512,0.0000892414,0.0000375684,0.0030599546],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973933,0.00013967797,0.00039510403,0.0011134141,0.0006084583,0.00035000697],"domain_scores_gemma":[0.9951259,0.003724735,0.000111749774,0.000647201,0.00026133363,0.0001290724],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009087107,0.00025376413,0.00027497477,0.00038172252,0.00041938486,0.0010986828,0.001228011,0.00009794147,0.00019651264],"category_scores_gemma":[0.00027829595,0.00022105026,0.0002431816,0.0011392662,0.00023606491,0.0012629397,0.00031703702,0.00019484865,0.00013447592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055193035,0.0003121263,0.00058824767,0.00006789139,0.00014696529,0.00022393689,0.0037677377,0.0013207619,0.0073367236,0.3228821,0.07165597,0.5916424],"study_design_scores_gemma":[0.000569212,0.00025746395,0.013951196,0.0010571943,0.00032184942,0.000057911853,0.00012761787,0.21817131,0.008810565,0.69664115,0.058807556,0.0012269838],"about_ca_topic_score_codex":0.000011820697,"about_ca_topic_score_gemma":0.000044728182,"teacher_disagreement_score":0.59041536,"about_ca_system_score_codex":0.00016804278,"about_ca_system_score_gemma":0.00045415867,"threshold_uncertainty_score":0.99993825},"labels":[],"label_agreement":null},{"id":"W4405034837","doi":"10.48550/arxiv.2412.01621","title":"NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Simple (philosophy); Task (project management); Computer science; Linguistics; Natural language processing; Psychology; Cognitive psychology; Epistemology; Philosophy; Economics; Management","score_opus":0.08503281301773807,"score_gpt":0.22324432976329897,"score_spread":0.1382115167455609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405034837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05431323,0.00023654418,0.937231,0.00022670228,0.0005103783,0.0006558057,0.000044272358,0.0029993684,0.003782719],"genre_scores_gemma":[0.9918929,0.00019065787,0.0064660027,0.00006962541,0.00009584194,0.000015167423,0.00005477258,0.000031292242,0.0011837733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967175,0.00024784033,0.00035094217,0.0020178133,0.00022051545,0.0004453603],"domain_scores_gemma":[0.9970357,0.0002208995,0.0004895394,0.0017835848,0.0002780498,0.00019227165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004039137,0.0005179163,0.0005326914,0.00068293937,0.00031052117,0.00037286876,0.0024325177,0.00044051104,0.000020859115],"category_scores_gemma":[0.000045934892,0.00052210526,0.00047792745,0.00159501,0.00013063737,0.0006425345,0.003012463,0.0010125816,0.00035547733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021651884,0.00012473715,0.0011122333,0.00030878233,0.0005073769,0.00032252175,0.0005631094,0.022793045,0.00058086566,0.9667823,0.002754268,0.0041291537],"study_design_scores_gemma":[0.0001998962,0.000059471215,0.00083723385,0.00034318818,0.00035264238,0.000015861264,0.0012448822,0.7261115,0.0005226756,0.26696658,0.0024812466,0.00086483697],"about_ca_topic_score_codex":0.00030006756,"about_ca_topic_score_gemma":0.00021251349,"teacher_disagreement_score":0.93757963,"about_ca_system_score_codex":0.0012845004,"about_ca_system_score_gemma":0.00024049866,"threshold_uncertainty_score":0.9997231},"labels":[],"label_agreement":null},{"id":"W4405918232","doi":"10.1002/asi.24977","title":"A study of drag‐and‐drop query refinement and query history visualization for mobile exploratory search","year":2024,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Visualization; Drag; Data mining; Physics; Mechanics","score_opus":0.018390033844011486,"score_gpt":0.31747201513829915,"score_spread":0.29908198129428765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405918232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6804803,0.0007792204,0.31489053,0.0021731663,0.0004361038,0.0010251644,0.0000044854078,0.000117120115,0.00009392117],"genre_scores_gemma":[0.9958459,0.000121951605,0.003852115,0.00007668479,0.00001188534,0.000051578267,3.619759e-7,0.0000025033435,0.000037033526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998843,0.000024827448,0.00045259972,0.000102266495,0.00046229534,0.000114991904],"domain_scores_gemma":[0.9979171,0.00014010038,0.0005575735,0.00014326959,0.0012165429,0.000025414178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002859567,0.000060852566,0.00015105556,0.0010106066,0.0001691341,0.000102410704,0.00034779255,0.00006301073,2.6409103e-7],"category_scores_gemma":[0.0006489516,0.00004406015,0.00003094044,0.00096780475,0.00012248276,0.0029006049,0.00018602819,0.000097886,1.7864205e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000466437,0.00029593465,0.019777749,0.00035377618,0.00023986888,0.0000010394718,0.03566125,0.0002639736,0.013063524,0.62621206,0.005975199,0.298109],"study_design_scores_gemma":[0.006502561,0.010866602,0.02025031,0.00073136145,0.0005485867,0.00017617519,0.043400437,0.29698464,0.07727381,0.10584575,0.436185,0.0012347584],"about_ca_topic_score_codex":0.0000032112512,"about_ca_topic_score_gemma":0.000005122952,"teacher_disagreement_score":0.5203663,"about_ca_system_score_codex":0.00043452193,"about_ca_system_score_gemma":0.00025503882,"threshold_uncertainty_score":0.21028684},"labels":[],"label_agreement":null},{"id":"W4406121435","doi":"10.1016/j.pharmr.2025.100037","title":"Anticoagulants: From chance discovery to structure-based design","year":2025,"lang":"en","type":"review","venue":"Pharmacological Reviews","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Thrombosis and Atherosclerosis Research Institute","funders":"","keywords":"Drug discovery; Computational biology; Chemistry; Biology; Biochemistry","score_opus":0.149436100269024,"score_gpt":0.4509059683486288,"score_spread":0.30146986807960474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406121435","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.0028086e-8,0.50650066,0.49085408,0.0000620746,0.00021834078,0.002048227,0.00004681097,0.00022575996,0.000043968957],"genre_scores_gemma":[0.000002009754,0.74494964,0.2512775,0.0024750603,0.00015567224,0.0008767693,0.000048187172,0.000020355135,0.0001947931],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99398136,0.0017285323,0.0014843962,0.0017321262,0.0004250612,0.0006485],"domain_scores_gemma":[0.9956807,0.0017778322,0.0008212773,0.0013665592,0.000076069184,0.0002775995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000772942,0.00096148654,0.0047023725,0.00037904232,0.00013442834,0.00030906897,0.00438631,0.00033266176,0.00016109021],"category_scores_gemma":[0.000863731,0.00061304885,0.0011469189,0.0022363018,0.000063030224,0.00047611928,0.0010182869,0.0007505508,0.00025315714],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031838035,0.00006590808,2.729929e-7,0.002208302,0.0000836268,0.000033453933,0.0000034616057,0.000014772931,0.00005724298,0.00038343173,0.005767143,0.9913792],"study_design_scores_gemma":[0.00009441706,0.00006261137,5.907702e-7,0.010205131,0.0009605896,0.0000016535496,9.577696e-8,0.0003653117,0.00035026178,0.0015137896,0.98578185,0.00066368683],"about_ca_topic_score_codex":0.00000571339,"about_ca_topic_score_gemma":0.0000016838794,"teacher_disagreement_score":0.9907155,"about_ca_system_score_codex":0.00028796456,"about_ca_system_score_gemma":0.00033657183,"threshold_uncertainty_score":0.99963206},"labels":[],"label_agreement":null},{"id":"W4406376912","doi":"10.1111/jedm.12424","title":"Using Multilabel Neural Network to Score High‐Dimensional Assessments for Different Use Foci: An Example with College Major Preference Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Preference; Artificial neural network; Artificial intelligence; Psychology; Machine learning; Computer science; Evaluation methods; Statistics; Mathematics; Reliability engineering","score_opus":0.23328784592740195,"score_gpt":0.3977295805474502,"score_spread":0.16444173462004827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406376912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3063923,0.00006488577,0.69063985,0.001643788,0.0005885716,0.00062577537,0.0000079579295,0.000018316772,0.000018555109],"genre_scores_gemma":[0.5438488,0.0000012776038,0.4554617,0.00042606774,0.0001272462,0.00006143313,0.000004529093,0.000009584684,0.00005937689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9968321,0.00017969278,0.00073479075,0.00045916392,0.0014182557,0.00037600627],"domain_scores_gemma":[0.995916,0.00027859834,0.00060073537,0.00050453376,0.0024441062,0.00025599462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009613713,0.00027675822,0.00043064612,0.00035036064,0.00031555645,0.00021240611,0.0008065459,0.000052916337,0.00001684954],"category_scores_gemma":[0.00010970584,0.00021361002,0.00012153168,0.0005743017,0.000031408686,0.0010613062,0.00015576705,0.00022296465,4.2076036e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001419331,0.010153891,0.20593435,0.00024695956,0.0027749133,0.000020329353,0.0005128519,0.2555192,0.07425781,0.39595458,0.025992468,0.027213331],"study_design_scores_gemma":[0.0037173436,0.002788671,0.785786,0.0015904852,0.0005863298,0.000060550985,0.00007309904,0.1324154,0.0065509067,0.064035095,0.0013984891,0.0009976801],"about_ca_topic_score_codex":0.00006126718,"about_ca_topic_score_gemma":0.00018105537,"teacher_disagreement_score":0.5798516,"about_ca_system_score_codex":0.0012345143,"about_ca_system_score_gemma":0.0015035053,"threshold_uncertainty_score":0.87107635},"labels":[],"label_agreement":null},{"id":"W4406526032","doi":"10.1007/978-3-031-83188-1","title":"Multimodal Learning toward Recommendation","year":2025,"lang":"en","type":"book","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National University of Singapore; Institute for Catastrophic Loss Reduction; Harbin Institute of Technology; Indian Council of Medical Research; Shandong University","keywords":"Computer science; Psychology","score_opus":0.016548706271586278,"score_gpt":0.29154211845566214,"score_spread":0.27499341218407586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406526032","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9803265e-8,0.000021039736,0.5275611,0.0004323337,0.00007309817,0.00007674138,5.2334326e-7,0.0007663665,0.47106874],"genre_scores_gemma":[0.00007713917,0.00006991153,0.28359336,0.00027761346,0.000051828807,0.000014556524,0.00008418329,0.0000102446775,0.7158212],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869365,0.00005137169,0.00030017883,0.00057264726,0.00018888341,0.00019329228],"domain_scores_gemma":[0.99900275,0.00014062038,0.00020065918,0.00048011454,0.00013126309,0.00004459864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020178205,0.00023750716,0.0003195901,0.00037266364,0.00008899503,0.00012545937,0.00092907634,0.00023554525,0.00023687084],"category_scores_gemma":[0.000067540386,0.00023315447,0.00016522137,0.00019420139,0.000020680633,0.00038894988,0.0006108443,0.0005544181,0.00012312901],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010607649,0.000012866919,0.000006954751,0.000028409611,0.000053451513,0.000003922989,0.00007047074,0.000058663572,0.000011955592,0.15576838,0.10541842,0.73856544],"study_design_scores_gemma":[0.00007187838,0.00003096178,0.0000038987296,0.000060871895,0.000019500929,0.0000012640966,0.0000029201046,0.039684024,0.00032476286,0.053707015,0.90579444,0.00029845774],"about_ca_topic_score_codex":0.000010961841,"about_ca_topic_score_gemma":0.0000070020806,"teacher_disagreement_score":0.800376,"about_ca_system_score_codex":0.00029206512,"about_ca_system_score_gemma":0.00024203621,"threshold_uncertainty_score":0.95077634},"labels":[],"label_agreement":null},{"id":"W4406800158","doi":"10.1007/978-3-031-78554-2_14","title":"A Real-Time Sentiment Feedback System: Binary Categorization and Context Understanding Based on Product Reviews","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Categorization; Context (archaeology); Product (mathematics); Binary number; Sentiment analysis; Artificial intelligence; Information retrieval; Mathematics; Arithmetic","score_opus":0.024243133494449783,"score_gpt":0.26564189855210996,"score_spread":0.24139876505766017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406800158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005802529,0.00070734735,0.9921564,0.0007369214,0.00043003383,0.0011030943,0.0000024554095,0.00038709203,0.0044708955],"genre_scores_gemma":[0.17310275,0.0008398704,0.82215834,0.0014582053,0.0003291526,0.00007213517,0.000034603934,0.000068643174,0.0019362909],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600136,0.00011202364,0.00069703604,0.0019408541,0.0007748602,0.00047385608],"domain_scores_gemma":[0.9971809,0.00037458647,0.0005087128,0.0016339722,0.00017656405,0.00012528831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012952429,0.0005937084,0.00085257465,0.0013563953,0.000334915,0.00046958437,0.0015901845,0.00019427988,0.0000069526996],"category_scores_gemma":[0.000091666036,0.0005213276,0.00013626054,0.0010863635,0.0003961855,0.0005058532,0.0007630178,0.00045674646,0.000022896109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030949013,0.00010027773,0.00005779276,0.0008683184,0.00004659588,0.0001450432,0.00063221174,0.028332647,0.0022363358,0.23145698,0.0006087042,0.7354841],"study_design_scores_gemma":[0.00023139527,0.00020229054,0.000011676108,0.0030461743,0.00003485083,0.0000150602455,4.873499e-7,0.9645567,0.0018388907,0.028539473,0.00087284105,0.00065013743],"about_ca_topic_score_codex":0.00002264296,"about_ca_topic_score_gemma":0.0000162054,"teacher_disagreement_score":0.9362241,"about_ca_system_score_codex":0.0015071996,"about_ca_system_score_gemma":0.0003863212,"threshold_uncertainty_score":0.99972385},"labels":[],"label_agreement":null},{"id":"W4407219662","doi":"10.1075/ml.24006.wes","title":"Orthographic uncertainty","year":2024,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence","score_opus":0.0113426503510872,"score_gpt":0.281487742315883,"score_spread":0.2701450919647958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407219662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07545666,0.0040253834,0.87855387,0.014353153,0.0010095955,0.0005426618,0.0000072505754,0.003942853,0.02210859],"genre_scores_gemma":[0.9926648,0.00005782445,0.0061337673,0.00038061762,0.00004566722,0.000020810763,0.0000031254604,0.0000075297858,0.00068582635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99924594,0.000042919593,0.00011490614,0.00024475137,0.00018920269,0.00016227938],"domain_scores_gemma":[0.99942756,0.000051030293,0.000020858773,0.00045826868,0.000010733945,0.000031549236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023869114,0.00009355916,0.000078798665,0.00009241763,0.00011097749,0.00017071204,0.00069217035,0.000022711783,0.000028850758],"category_scores_gemma":[0.000004292645,0.000057313948,0.000103703744,0.0006064374,0.00007519307,0.00031297567,0.00021120562,0.00012796499,0.000116534764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029402695,0.00002606099,0.0001187526,0.000010733438,0.000057047164,0.000023847657,0.0008000614,0.00005084392,0.011686333,0.8114117,0.0027990383,0.17301267],"study_design_scores_gemma":[0.0001885817,0.00019774938,0.0006451443,0.00013388199,0.000049724225,0.00009488895,0.00013566016,0.19255671,0.058331348,0.50700665,0.24009575,0.00056393445],"about_ca_topic_score_codex":0.000024171784,"about_ca_topic_score_gemma":0.000018671859,"teacher_disagreement_score":0.9172082,"about_ca_system_score_codex":0.000042487543,"about_ca_system_score_gemma":0.000020454365,"threshold_uncertainty_score":0.2337195},"labels":[],"label_agreement":null},{"id":"W4407505400","doi":"10.1037/xlm0001438","title":"Tracking the dynamic word-by-word incremental reading through multimeasures.","year":2025,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Psychology; Reading (process); Word recognition; Linguistics; Word length; Cognitive psychology; Word lists by frequency; Natural language processing; Computer science; Sentence","score_opus":0.02199783729644601,"score_gpt":0.36202037051378916,"score_spread":0.34002253321734316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407505400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4430206,0.005778215,0.54352903,0.0015361775,0.00046059614,0.00018740671,5.4894093e-7,0.00011215608,0.0053752405],"genre_scores_gemma":[0.98700076,0.00021840374,0.011462651,0.0011164921,0.000038235416,0.00000850961,0.0000026488422,0.000008283812,0.00014399012],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862784,0.00030856676,0.00041334052,0.00025722312,0.00020568386,0.00018732816],"domain_scores_gemma":[0.9991756,0.00013758328,0.00038811722,0.00016672221,0.00009497817,0.000037012378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000647693,0.00015018381,0.00022598346,0.00015505939,0.00037382095,0.000099043675,0.00038810552,0.000086670836,0.00001950913],"category_scores_gemma":[0.00007277748,0.00011908558,0.00010447529,0.00029617062,0.00016072746,0.0007937834,0.000098783436,0.00059164537,0.0000032925157],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015159878,0.00025492205,0.00040456408,0.0000065188506,0.0001731234,0.000031288724,0.0018160316,0.00003739129,0.8324054,0.0004717589,0.0011642829,0.16308315],"study_design_scores_gemma":[0.0050699846,0.0011821082,0.0067699733,0.0007338551,0.0002497041,0.0010734998,0.007912942,0.0051160334,0.9424955,0.022486195,0.0061523016,0.0007579002],"about_ca_topic_score_codex":0.0000030202912,"about_ca_topic_score_gemma":8.745843e-7,"teacher_disagreement_score":0.5439802,"about_ca_system_score_codex":0.000066913424,"about_ca_system_score_gemma":0.000017534494,"threshold_uncertainty_score":0.48561686},"labels":[],"label_agreement":null},{"id":"W4407733387","doi":"10.1007/s10508-025-03105-6","title":"A Content Analysis of Lay Definitions of Romantic Chemistry","year":2025,"lang":"en","type":"article","venue":"Archives of Sexual Behavior","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"York University","keywords":"Content analysis; Romance; Psychology; Public health; Content (measure theory); Sexual behavior; Chemistry; Social psychology; Psychoanalysis; Social science; Sociology; Medicine","score_opus":0.05534291665120807,"score_gpt":0.31381662861688153,"score_spread":0.2584737119656735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407733387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7016251,0.00010050909,0.29635462,0.000034585304,0.000010339597,0.00008527402,0.000034466946,0.00004320132,0.0017118559],"genre_scores_gemma":[0.92957515,0.000023773153,0.070155755,0.000008903403,0.0000015718616,0.000024054823,0.000017323388,0.0000031090026,0.00019036667],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894726,0.000028769124,0.00048754862,0.00024632865,0.00016803417,0.00012202919],"domain_scores_gemma":[0.9987138,0.00022019005,0.0002711099,0.0006839761,0.000078595316,0.000032360414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000695758,0.00009940324,0.00042718687,0.0004474744,0.000026760508,0.000006396958,0.00067494105,0.000030483341,0.000012430339],"category_scores_gemma":[0.00004893633,0.000096600976,0.00017455596,0.0011134375,0.0002310326,0.000096016505,0.00026388373,0.000073243245,3.1698286e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007713969,0.00052821235,0.04371297,0.00007420544,0.00049534807,0.0000034571738,0.00041161623,0.00009844893,0.9011595,0.03762369,0.0000053254917,0.015879463],"study_design_scores_gemma":[0.00023609599,0.000114732145,0.2606837,0.000064720814,0.0023538761,0.0000010235448,0.00022909774,0.003993172,0.72865987,0.0035050302,0.000013246344,0.00014546252],"about_ca_topic_score_codex":0.00009392178,"about_ca_topic_score_gemma":0.00002100563,"teacher_disagreement_score":0.22795,"about_ca_system_score_codex":0.0000072586554,"about_ca_system_score_gemma":0.000044952103,"threshold_uncertainty_score":0.39392737},"labels":[],"label_agreement":null},{"id":"W4408173301","doi":"10.26434/chemrxiv-2025-8z6h2","title":"MERMaid: Universal multimodal mining of chemical reactions from PDFs using vision-language models","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Canada First Research Excellence Fund; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence","score_opus":0.02439863093086714,"score_gpt":0.3166167865368164,"score_spread":0.29221815560594927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408173301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23138341,0.00022222534,0.76632214,0.0000594164,0.00015097111,0.00014251083,0.000016266877,0.00034083152,0.0013622349],"genre_scores_gemma":[0.53821695,0.000020429465,0.4615424,0.000022545893,0.00005304786,0.000007670607,0.000038258095,0.000012168739,0.000086503715],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978349,0.000055585017,0.0005466661,0.0009261899,0.00036111695,0.00027554444],"domain_scores_gemma":[0.997427,0.00023111641,0.0004726953,0.0015775375,0.00019136765,0.00010029775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001604733,0.00034049404,0.0006147451,0.00034724726,0.00006317088,0.00006814103,0.0016849128,0.00039983247,0.000021568858],"category_scores_gemma":[0.0000770283,0.00037858667,0.0003283803,0.00047099346,0.00012218341,0.0004901461,0.0026585313,0.0005964676,0.0000021403591],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002852959,0.00036599996,0.00010448796,0.00022048091,0.0005519179,0.000067983856,0.0050435048,0.05384408,0.91172886,0.005602242,0.0003906399,0.02205127],"study_design_scores_gemma":[0.00014108965,0.000004515026,0.00000784171,0.00032741408,0.00007790221,0.0000012454735,0.000093010385,0.69514525,0.2958415,0.008056062,0.000041011856,0.0002631648],"about_ca_topic_score_codex":0.0007214839,"about_ca_topic_score_gemma":0.0000049956975,"teacher_disagreement_score":0.64130116,"about_ca_system_score_codex":0.0002570295,"about_ca_system_score_gemma":0.00024691288,"threshold_uncertainty_score":0.9998666},"labels":[],"label_agreement":null},{"id":"W4409163690","doi":"10.1007/s00766-025-00436-7","title":"Tracing content requirements in financial documents using multi-granularity text analysis","year":2025,"lang":"en","type":"article","venue":"Requirements Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Tracing; Granularity; Computer science; Requirements analysis; Information retrieval; Software engineering; Programming language; Software","score_opus":0.05193979241721546,"score_gpt":0.3293895904679666,"score_spread":0.27744979805075115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409163690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15571386,0.00021658205,0.843126,0.000034993594,0.00020516009,0.0002978162,0.0000018479597,0.0002781544,0.00012561234],"genre_scores_gemma":[0.7972538,0.000017601684,0.20246226,0.00008774707,0.000015430041,0.00003520083,0.0000058104406,0.000013503065,0.000108672946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972449,0.00005821538,0.00082908105,0.0007447165,0.0004732499,0.0006498649],"domain_scores_gemma":[0.99877787,0.000041398584,0.00017466841,0.00080995215,0.00009972524,0.00009637356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006341533,0.00034574285,0.0005904234,0.0016823609,0.00012887808,0.0001685018,0.00094431045,0.00011939716,0.000008054153],"category_scores_gemma":[0.00018111363,0.0003858583,0.0002670355,0.003678163,0.00002402801,0.001326834,0.00045868597,0.00026468578,0.000003774754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047111604,0.0013723086,0.31898403,0.00040135885,0.0029933604,0.0002580489,0.0011117468,0.3481484,0.23594937,0.030748198,0.000046840265,0.05993923],"study_design_scores_gemma":[0.0011631302,0.000022936625,0.053395454,0.00030750415,0.00026650212,0.000001207907,0.000015801139,0.92403066,0.019619944,0.00046451628,0.00019822652,0.000514105],"about_ca_topic_score_codex":0.00028306854,"about_ca_topic_score_gemma":0.000109329274,"teacher_disagreement_score":0.64153993,"about_ca_system_score_codex":0.0007505054,"about_ca_system_score_gemma":0.000070173024,"threshold_uncertainty_score":0.99985933},"labels":[],"label_agreement":null},{"id":"W4409313533","doi":"10.3390/app15084134","title":"LLM-Enhanced Framework for Building Domain-Specific Lexicon for Urban Power Grid Design","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"State Grid Jiangsu Electric Power","keywords":"Computer science; Power grid; Lexicon; Architectural engineering; Power (physics); Artificial intelligence; Engineering; Physics","score_opus":0.028962359607354066,"score_gpt":0.3241110746509073,"score_spread":0.2951487150435533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409313533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010216318,0.00024794287,0.99293137,0.00095715927,0.00046344288,0.0012046143,0.0000028084748,0.00046928102,0.0027017784],"genre_scores_gemma":[0.27609602,0.00001197876,0.7225822,0.0005738988,0.00007794153,0.0005734119,8.8680844e-7,0.000008491745,0.0000751224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997533,0.00003153693,0.0003854477,0.0010621125,0.00035209564,0.0006357956],"domain_scores_gemma":[0.99758744,0.00134919,0.0002007971,0.00066635216,0.00011973817,0.000076479504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013586964,0.00024752,0.00034262106,0.0003661267,0.00087511307,0.0004446073,0.0022915762,0.00012796801,0.00000637614],"category_scores_gemma":[0.00007830962,0.00021857751,0.00015688204,0.0017806317,0.00036607115,0.0004885192,0.0002427965,0.0001398867,0.000006260019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016617912,0.000035944988,0.000005418471,0.000007636624,0.000012660871,2.1485371e-7,0.00020628284,0.00027676628,0.04522716,0.9384236,0.0032644689,0.012523255],"study_design_scores_gemma":[0.00017471604,0.00012075799,0.000012995687,0.000033382446,0.0000062731665,3.0849833e-7,0.00010148402,0.0014731096,0.25617084,0.71268433,0.028999612,0.00022220096],"about_ca_topic_score_codex":9.4610266e-7,"about_ca_topic_score_gemma":0.0000010988477,"teacher_disagreement_score":0.2750744,"about_ca_system_score_codex":0.00009246122,"about_ca_system_score_gemma":0.00016026874,"threshold_uncertainty_score":0.8913332},"labels":[],"label_agreement":null},{"id":"W4409603307","doi":"10.61091/jcmcc127b-142","title":"Research on the Optimization Method of Japanese Text Information Dissemination Path Based on Graph Theory","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"China Scholarship Council","keywords":"Computer science; Path (computing); Graph theory; Graph; Theoretical computer science; Information retrieval; Mathematics; Combinatorics; Computer network","score_opus":0.015817120619428676,"score_gpt":0.3401000032793355,"score_spread":0.3242828826599068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0085775945,0.00003396462,0.98487526,0.00054426066,0.0019676692,0.00034777846,8.9214166e-7,0.000042558,0.0036100317],"genre_scores_gemma":[0.9194429,0.000014206382,0.080342986,0.000066218774,0.00011069735,0.000005629891,0.0000012701139,0.0000099067265,0.0000061613537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965383,0.00075885525,0.001095925,0.00018447742,0.0011817146,0.00024072295],"domain_scores_gemma":[0.98972327,0.0069418745,0.0011704094,0.00053594564,0.0015603683,0.000068129506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009173294,0.00021101818,0.00049988134,0.00097174116,0.00038638915,0.0002918343,0.0010207318,0.00014221398,0.0000032317503],"category_scores_gemma":[0.0021936256,0.00014877196,0.00017479536,0.0016788866,0.00010762349,0.0005099019,0.00024759115,0.0006260824,8.1246446e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082893865,0.00033648236,0.000004384038,0.00008052127,0.00004264529,0.0000013762992,0.0010888195,0.00940945,0.00010964543,0.98183984,0.00019880214,0.0068051564],"study_design_scores_gemma":[0.00077925046,0.0005979532,0.000019302159,0.0006598098,0.00003148046,0.0000032834944,0.000639124,0.3867698,0.0028146284,0.6075146,0.000059137,0.00011163425],"about_ca_topic_score_codex":0.0000035054313,"about_ca_topic_score_gemma":4.6927457e-8,"teacher_disagreement_score":0.9108653,"about_ca_system_score_codex":0.00011825143,"about_ca_system_score_gemma":0.00014041142,"threshold_uncertainty_score":0.60667443},"labels":[],"label_agreement":null},{"id":"W4409603675","doi":"10.61091/jcmcc127b-196","title":"A Study on Improving Semantic Consistency of Translation Systems by Combining Dynamic Computing Methods in English Corpus","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Jilin Office of Philosophy and Social Science; Henan Office of Philosophy and Social Science","keywords":"Computer science; Consistency (knowledge bases); Natural language processing; Translation (biology); Artificial intelligence; Information retrieval; Chemistry","score_opus":0.016288306506166188,"score_gpt":0.32592750652418884,"score_spread":0.30963920001802264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35876167,0.0008327258,0.632887,0.000033375545,0.006309688,0.00064511853,8.6154984e-7,0.00009885096,0.00043068937],"genre_scores_gemma":[0.9378805,0.000016796059,0.06196474,0.000010511727,0.00009534779,0.0000034581628,7.501237e-7,0.00002488212,0.0000029897142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99510336,0.0006798999,0.0026103505,0.00044992202,0.00075221766,0.000404234],"domain_scores_gemma":[0.99321616,0.0029251464,0.0023574668,0.00053448015,0.00085628714,0.00011048832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0051331604,0.00040573644,0.0015902079,0.00088739966,0.0002377854,0.00031066829,0.0010294333,0.00019126757,2.7398042e-7],"category_scores_gemma":[0.0010462622,0.00039264833,0.00022143069,0.0013486764,0.000094222974,0.00040489246,0.00037566797,0.0006447367,1.593269e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012481428,0.0040670107,0.0018741017,0.00085186376,0.00046010164,0.00006447236,0.012479052,0.0010647372,0.009740279,0.9219618,0.00004589028,0.04726589],"study_design_scores_gemma":[0.0126420455,0.003407269,0.0005311368,0.003337367,0.00036619624,0.000048992657,0.0055155586,0.6493775,0.004448119,0.31939396,0.00006694139,0.0008648683],"about_ca_topic_score_codex":0.000032428397,"about_ca_topic_score_gemma":0.0000010121659,"teacher_disagreement_score":0.6483128,"about_ca_system_score_codex":0.00020972843,"about_ca_system_score_gemma":0.00019868699,"threshold_uncertainty_score":0.99985254},"labels":[],"label_agreement":null},{"id":"W4409603800","doi":"10.61091/jcmcc127b-230","title":"Value Assessment and Linguistic Feature Mining Based on Regression Analysis in Ancient Literary Texts","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Feature (linguistics); Linguistics; Regression; Natural language processing; Regression analysis; Artificial intelligence; History; Computer science; Statistics; Mathematics; Philosophy","score_opus":0.008985441968079889,"score_gpt":0.3100319215638725,"score_spread":0.3010464795957926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40419003,0.00097507646,0.586736,0.0006301221,0.0055469447,0.0003580719,0.0000011741043,0.000098688564,0.0014638603],"genre_scores_gemma":[0.8590773,0.000020434854,0.14060572,0.00010301286,0.00017346,0.000002121704,9.792144e-7,0.000011074917,0.0000059002355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973421,0.00022393023,0.0010015375,0.00040694518,0.00070922275,0.00031622502],"domain_scores_gemma":[0.99670154,0.0013315076,0.00095100945,0.0004644238,0.00040723346,0.00014429321],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021271093,0.00031988666,0.0009975176,0.0013893169,0.0002360027,0.00041428502,0.0006442923,0.00017041802,8.4267657e-7],"category_scores_gemma":[0.00058859016,0.00026582077,0.00021994322,0.0020030665,0.000059835562,0.00023142759,0.00039622287,0.00061441236,1.1983663e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055510514,0.00077812566,0.005731848,0.00017671227,0.00023506755,0.00010330511,0.0011594242,0.0011186827,0.00021969165,0.98014253,0.00013517347,0.010143938],"study_design_scores_gemma":[0.0021485973,0.00043451771,0.003495741,0.0012337954,0.00022944134,0.000008793307,0.000046921643,0.5463496,0.00029101098,0.4453213,0.0001877042,0.00025257963],"about_ca_topic_score_codex":0.00000311341,"about_ca_topic_score_gemma":4.9612333e-7,"teacher_disagreement_score":0.5452309,"about_ca_system_score_codex":0.0002170268,"about_ca_system_score_gemma":0.00023033506,"threshold_uncertainty_score":0.9999794},"labels":[],"label_agreement":null},{"id":"W4409813933","doi":"10.1016/j.procs.2025.03.116","title":"Harnessing Large Language Models for Precision Topic Extraction and Technology Patent Nomination: A GPT-centric Methodology","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep de Rimouski; Université du Québec à Rimouski","funders":"","keywords":"Computer science; Nomination; Patent analysis; Extraction (chemistry); Data science; Data mining","score_opus":0.04369533804685807,"score_gpt":0.3513519287723578,"score_spread":0.3076565907254998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409813933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009205055,0.0005810159,0.9877444,0.0012033348,0.00037514497,0.0004085095,7.820467e-7,0.00038325333,0.00009851494],"genre_scores_gemma":[0.37134415,0.000026077425,0.62829936,0.00015993849,0.00003244031,0.000070534625,7.1437904e-7,0.0000034348138,0.0000633471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819237,0.00004544543,0.00028370417,0.000836662,0.00023672407,0.0004050662],"domain_scores_gemma":[0.9986023,0.00028524458,0.00015319652,0.00047759138,0.0004211895,0.00006050917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012401605,0.00015117055,0.00023486928,0.0010948207,0.0003809396,0.00024814013,0.0010619668,0.000097482865,8.4676327e-7],"category_scores_gemma":[0.00026479395,0.00013916449,0.000040059054,0.0026447342,0.00016863122,0.0015062476,0.0008153834,0.00013675883,0.0000010735992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004674598,0.00006381311,0.00036481183,0.000040598105,0.0000066201533,0.0000033159072,0.0006071475,0.00025714593,0.007501202,0.1600098,0.00006334122,0.8310775],"study_design_scores_gemma":[0.00027280583,0.00005896132,0.00041736598,0.000042407824,0.000009918082,0.000019378409,0.000026619602,0.86339724,0.023624988,0.11154962,0.00044125688,0.00013945716],"about_ca_topic_score_codex":0.0000028159411,"about_ca_topic_score_gemma":0.000004361428,"teacher_disagreement_score":0.86314005,"about_ca_system_score_codex":0.00011675749,"about_ca_system_score_gemma":0.00019060289,"threshold_uncertainty_score":0.5674963},"labels":[],"label_agreement":null},{"id":"W4409973579","doi":"10.1145/3698204.3716444","title":"Integrating Eye Tracking, Feature Use, and Emotional Valence: A Multimodal Approach to Evaluating Search Interfaces","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Computer science; Eye tracking; Emotional valence; Feature (linguistics); Artificial intelligence; Valence (chemistry); Feature extraction; Computer vision; Human–computer interaction; Psychology; Cognition","score_opus":0.04454853921092032,"score_gpt":0.38224133973688423,"score_spread":0.3376928005259639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409973579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14065447,0.00006164481,0.8555639,0.0006198223,0.000035497316,0.00026242854,0.0000011705409,0.0003125089,0.0024885624],"genre_scores_gemma":[0.4587196,0.0000031686454,0.5395634,0.00021078423,0.000011888515,0.000020590931,0.000001969008,0.0000042868032,0.0014643018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828804,0.00013471134,0.00023384798,0.0006683012,0.00039163983,0.0002834741],"domain_scores_gemma":[0.9989227,0.0002189057,0.000051500345,0.0004054463,0.00032285583,0.00007856304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070733455,0.00018422335,0.00021346491,0.00033686464,0.00021461428,0.00056704285,0.0007081858,0.00008509198,0.000006595641],"category_scores_gemma":[0.00043974968,0.00015048201,0.000055721364,0.000943624,0.000057128367,0.0010295929,0.00067050447,0.0003512721,0.0000034628126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025024021,0.00033010368,0.06122781,0.00017032973,0.00016638366,0.0000047156036,0.007128566,0.006658359,0.045501523,0.22341177,0.0028398763,0.65253556],"study_design_scores_gemma":[0.00016873679,0.000077412624,0.022451786,0.00021568591,0.000011614549,0.000004963652,0.0004955877,0.9549291,0.018019715,0.0032548609,0.000128659,0.00024186111],"about_ca_topic_score_codex":0.00008463354,"about_ca_topic_score_gemma":0.000036012003,"teacher_disagreement_score":0.94827074,"about_ca_system_score_codex":0.00007858066,"about_ca_system_score_gemma":0.00006853955,"threshold_uncertainty_score":0.6136478},"labels":[],"label_agreement":null},{"id":"W4409973737","doi":"10.1145/3698204.3716481","title":"NeuroPhysIIR: International Workshop on NeuroPhysiological Approaches for Interactive Information Retrieval","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; RMIT University","keywords":"Computer science; Neurophysiology; Information retrieval; Neuroscience; Psychology","score_opus":0.03177285531587556,"score_gpt":0.30303675902391414,"score_spread":0.2712639037080386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409973737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025037667,0.0000019588178,0.9779621,0.00216487,0.00030004827,0.00024334033,0.0000018329799,0.00038031288,0.016441802],"genre_scores_gemma":[0.9089303,0.000008768679,0.08721363,0.0029329527,0.000051484432,0.000047919544,0.000020767658,0.0000041414414,0.000790059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991373,0.00003702937,0.00023473299,0.0002844712,0.00016344013,0.0001430427],"domain_scores_gemma":[0.999038,0.00033794326,0.00009983311,0.00036232566,0.00013505168,0.000026842115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008094425,0.0001263043,0.00013847798,0.0002463336,0.00007669912,0.00017580893,0.000870741,0.000049264996,0.000006504706],"category_scores_gemma":[0.00037262033,0.000100703604,0.00012058766,0.0004602624,0.000033065666,0.0013055011,0.0003156382,0.0001603519,0.000023692675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025829315,0.00014085398,0.000010428306,0.000007963956,0.000056859655,0.0000012110507,0.00010660896,0.0022493766,0.0020541202,0.7120595,0.0026945246,0.28036028],"study_design_scores_gemma":[0.0005680754,0.00029243444,0.0022059113,0.000040088282,0.000015260774,0.0000015110272,0.000082751634,0.84246725,0.025667008,0.095735386,0.032599576,0.00032476004],"about_ca_topic_score_codex":7.545435e-7,"about_ca_topic_score_gemma":1.8990967e-7,"teacher_disagreement_score":0.9064265,"about_ca_system_score_codex":0.00005855189,"about_ca_system_score_gemma":0.000020899266,"threshold_uncertainty_score":0.41065738},"labels":[],"label_agreement":null},{"id":"W4410016295","doi":"10.21917/ijsc.2025.0526","title":"A NATURAL LANGUAGE PROCESSING APPROACH TO COMPARATIVE SENTIMENT AND TOPIC ANALYSIS OF ENGLISH NATIONAL ANTHEMS","year":2025,"lang":"en","type":"article","venue":"ICTACT Journal on Soft Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural language processing; Computer science; Linguistics; Sentiment analysis; Natural (archaeology); Artificial intelligence; History; Archaeology","score_opus":0.01574438382345438,"score_gpt":0.3384823788672222,"score_spread":0.3227379950437678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410016295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17049675,0.0005696743,0.8251022,0.000080418424,0.000106123305,0.000096647585,9.539178e-7,0.00008738925,0.0034598305],"genre_scores_gemma":[0.89011484,0.0000024520332,0.10945035,0.00029735442,0.00007348508,0.0000014500407,0.0000019659185,0.0000033598474,0.000054770215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851596,0.000089878435,0.00042005035,0.0003065818,0.00046517816,0.00020233181],"domain_scores_gemma":[0.99858373,0.00021519407,0.00031023377,0.00017162692,0.00064687274,0.000072324794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005347466,0.00015189167,0.00042717173,0.0009971912,0.00021774747,0.00023494949,0.00046891053,0.00003529054,0.0000012511463],"category_scores_gemma":[0.00017751679,0.0001304138,0.00014312926,0.0019906724,0.00003208949,0.0002951615,0.00022588515,0.00029719394,3.855477e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011545829,0.0015160319,0.021071693,0.00019448154,0.005817832,0.00004001739,0.116424076,0.17514801,0.0078039244,0.043566845,0.0009984148,0.62730324],"study_design_scores_gemma":[0.00027882957,0.000058832953,0.01083278,0.00015504388,0.00015001142,0.000006763671,0.00067108683,0.9841042,0.00279731,0.0004000258,0.00034858414,0.00019652092],"about_ca_topic_score_codex":0.0000029495754,"about_ca_topic_score_gemma":0.0000012352511,"teacher_disagreement_score":0.8089562,"about_ca_system_score_codex":0.0001242667,"about_ca_system_score_gemma":0.00007285361,"threshold_uncertainty_score":0.531812},"labels":[],"label_agreement":null},{"id":"W4410087324","doi":"10.1109/wi-iat62293.2024.00083","title":"Using LLMs to Analyze Antecedent, Behavior and Consequence Narrative Recordings in Behavioral Health Science","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Antecedent (behavioral psychology); Narrative; Behavioural sciences; Psychology; Computer science; Cognitive psychology; Social psychology; Linguistics; Psychotherapist","score_opus":0.06715577909876917,"score_gpt":0.43577917777842723,"score_spread":0.36862339867965804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410087324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60739034,0.00014242454,0.39118814,0.0005379893,0.00009089562,0.00026178325,0.0000012367564,0.00030245623,0.00008473333],"genre_scores_gemma":[0.7268948,0.00001988809,0.27275267,0.00021848982,0.000007559174,0.000025083591,3.1706804e-7,0.0000072023217,0.00007400753],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978652,0.000033272285,0.00036393543,0.0009077238,0.00035890457,0.00047093505],"domain_scores_gemma":[0.9991477,0.00003067376,0.00006524631,0.00041496695,0.00010701615,0.00023435707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079264434,0.00017790515,0.00026991978,0.0010202522,0.00022365188,0.00054610474,0.00072792545,0.00003636072,0.000012707173],"category_scores_gemma":[0.000021424928,0.00016342688,0.000042801723,0.0036854388,0.00030978353,0.0017387928,0.00048964174,0.00019369312,0.000005655314],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014907634,0.00039721417,0.04271614,0.00007879298,0.000022362965,0.0013517078,0.036550675,0.00020109351,0.44332004,0.07962275,0.00041963847,0.39530468],"study_design_scores_gemma":[0.0010946278,0.0032966756,0.057657436,0.0028132766,0.00013706532,0.00313832,0.013388629,0.5914603,0.28537738,0.035399653,0.0013463674,0.0048902542],"about_ca_topic_score_codex":0.0021820907,"about_ca_topic_score_gemma":0.0008185997,"teacher_disagreement_score":0.59125924,"about_ca_system_score_codex":0.00051144516,"about_ca_system_score_gemma":0.00041801768,"threshold_uncertainty_score":0.6664355},"labels":[],"label_agreement":null},{"id":"W4410140237","doi":"10.1007/s41870-025-02541-w","title":"TextAI 3.0 (Multimodal): multimodal sentiment analysis using attention-enabled ensemble-based deep learning in hyperbolic space","year":2025,"lang":"en","type":"article","venue":"International Journal of Information Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Space (punctuation); Sentiment analysis; Ensemble learning; Deep learning; Hyperbolic space; Machine learning; Mathematics","score_opus":0.005213480878788831,"score_gpt":0.281656305663714,"score_spread":0.2764428247849252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410140237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11576604,0.00006603658,0.88088036,0.0025514243,0.00019931562,0.000105514766,9.419622e-7,0.00015082031,0.00027952326],"genre_scores_gemma":[0.7731316,0.000021808357,0.22657913,0.00020128246,0.000014520618,0.0000071316754,0.000007436188,0.000003830657,0.000033240136],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978038,0.00007170839,0.0011486398,0.0001726777,0.0005597332,0.00024342502],"domain_scores_gemma":[0.99725306,0.00010142096,0.0010954267,0.0002924307,0.0012147411,0.000042911837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005810457,0.00017872958,0.00039682802,0.008037407,0.00008850529,0.00018135074,0.0013883745,0.0001832881,0.000016621569],"category_scores_gemma":[0.00035454857,0.0001768132,0.00026884783,0.003159831,0.00006885008,0.0020810382,0.00027041626,0.0004998468,0.000011359153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009332471,0.00025761026,0.09054263,0.000019690346,0.001452817,0.000060759776,0.00040285417,0.6180366,0.013429727,0.04615105,0.000036533565,0.22951639],"study_design_scores_gemma":[0.0012766646,0.000050373055,0.004950429,0.000091815404,0.000107564134,0.000035491783,0.00025280204,0.96933496,0.01720644,0.005341292,0.0011759055,0.00017626691],"about_ca_topic_score_codex":0.000043534783,"about_ca_topic_score_gemma":0.000026989768,"teacher_disagreement_score":0.65736556,"about_ca_system_score_codex":0.00060393946,"about_ca_system_score_gemma":0.00017770557,"threshold_uncertainty_score":0.7210233},"labels":[],"label_agreement":null},{"id":"W4410355141","doi":"10.36315/2025inpact142","title":"AN ECOLOGICAL APPROACH TO THEORY-OF-MIND MEASUREMENT: CREATION OF THE EV-TOMI FROM OPEN-ENDED REPORTS","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Ecology; Biology","score_opus":0.04203306755129314,"score_gpt":0.3174950439469187,"score_spread":0.27546197639562553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410355141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020125587,0.000015509268,0.9043795,0.000168116,0.000040053215,0.00043248764,7.8030104e-7,0.000055045486,0.07478295],"genre_scores_gemma":[0.75895095,7.731639e-7,0.24062459,0.00015086471,0.000004587215,0.000031387022,0.000001557839,0.0000021331737,0.00023315716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99842805,0.00022791994,0.00042408158,0.00043925544,0.00036636216,0.00011432971],"domain_scores_gemma":[0.9981085,0.00007863634,0.00023417256,0.0012924762,0.0002486403,0.00003754002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013202847,0.00009958375,0.00024896194,0.00009563645,0.00007034225,0.00006626508,0.0015782835,0.00006321197,0.000041684216],"category_scores_gemma":[0.00029264897,0.00006155694,0.00007518036,0.00067800004,0.000055963617,0.0003161983,0.00053389766,0.00007225619,0.0000010737512],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003540198,0.001975465,0.0068548624,0.000010842096,0.0001574436,0.0000030566225,0.00082073675,0.00087594055,0.07368509,0.8343263,0.000942096,0.080312714],"study_design_scores_gemma":[0.00018066449,0.00009773289,0.052755736,0.000036487603,0.000054383392,0.0000015521229,0.00011301566,0.009767432,0.5224701,0.41375074,0.0006105264,0.0001615957],"about_ca_topic_score_codex":0.00007742983,"about_ca_topic_score_gemma":0.000050684877,"teacher_disagreement_score":0.7388254,"about_ca_system_score_codex":0.000068569716,"about_ca_system_score_gemma":0.000098328994,"threshold_uncertainty_score":0.29328695},"labels":[],"label_agreement":null},{"id":"W4410436552","doi":"10.1142/s1793351x25440015","title":"Translative Research Assistant: A Retrieval-Augmented Generation Pipeline Refinement with Keyword Extraction Using Extended Scalable Betweenness Centrality","year":2025,"lang":"en","type":"article","venue":"International Journal of Semantic Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Betweenness centrality; Computer science; Pipeline (software); Scalability; Information retrieval; Centrality; Keyword extraction; Keyword search; Artificial intelligence; Data mining; Database","score_opus":0.07189166716247476,"score_gpt":0.42396534476847936,"score_spread":0.3520736776060046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410436552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19950436,0.00015128143,0.7978556,0.0017302,0.00039078784,0.00013465564,0.0000013078,0.000038587506,0.00019320102],"genre_scores_gemma":[0.8567918,0.000031695006,0.14276823,0.000056641908,0.00025224942,6.449401e-7,0.000004572117,0.000008324046,0.00008585563],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99665207,0.00030826763,0.0009567877,0.00036244316,0.00141015,0.00031029538],"domain_scores_gemma":[0.99584925,0.0002985484,0.0006900746,0.00026867745,0.0028204797,0.000072981566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024973364,0.00017156226,0.00032368675,0.00086404127,0.00026845935,0.00031783545,0.0009074156,0.000062931904,0.000011330914],"category_scores_gemma":[0.00018654621,0.00014763625,0.00012283852,0.0012067469,0.000082056096,0.00080793403,0.00019255964,0.00050661556,9.5206923e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012821868,0.0019797923,0.011658648,0.00014718002,0.0023975726,0.0008227039,0.0033354792,0.062173326,0.45106012,0.032817982,0.0010038574,0.43132114],"study_design_scores_gemma":[0.0012478816,0.00015027955,0.004581675,0.0010320693,0.00008087803,0.00013276075,0.00018214555,0.90043724,0.08729305,0.004085945,0.00056451245,0.00021154828],"about_ca_topic_score_codex":0.00006781174,"about_ca_topic_score_gemma":0.000035053898,"teacher_disagreement_score":0.8382639,"about_ca_system_score_codex":0.0006389716,"about_ca_system_score_gemma":0.00027433602,"threshold_uncertainty_score":0.60204315},"labels":[],"label_agreement":null},{"id":"W4410512048","doi":"10.33423/jabe.v27i3.7646","title":"New Recommendation Agent to Identify Innovators Utilizing User-Generated Content","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Business and Economics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Content (measure theory); Information retrieval; World Wide Web; Internet privacy; Mathematics","score_opus":0.03911475642310851,"score_gpt":0.293659834904992,"score_spread":0.25454507848188346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410512048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27199835,0.00002886586,0.7250419,0.0021029406,0.00028440976,0.00007402983,4.3917672e-7,0.000021713842,0.00044730003],"genre_scores_gemma":[0.8058714,0.00032518362,0.19215593,0.0014400169,0.00010024554,0.0000038744383,0.0000025779475,0.000008644218,0.00009207916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990835,0.0000066725725,0.0005560407,0.00018217336,0.00004398943,0.00012757776],"domain_scores_gemma":[0.9991314,0.000023330302,0.0003702882,0.00016820196,0.00023056215,0.00007622926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133425,0.000111678004,0.0002753379,0.00039972985,0.000074637224,0.0002518633,0.0003292016,0.000046973855,0.0000072248467],"category_scores_gemma":[0.000018625838,0.00010497328,0.00003859281,0.00063995854,0.0000098003475,0.00048669314,0.00019172709,0.00009869713,0.0000026977962],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008131354,0.000055102908,0.0008714724,0.000023066083,0.00016419952,0.000003595315,0.0001826154,0.0031485434,0.018183159,0.1648583,0.006240032,0.8061886],"study_design_scores_gemma":[0.0050556995,0.00022297147,0.095934674,0.00041564845,0.00027835421,0.0000826086,0.0010680135,0.02772364,0.21579105,0.12750572,0.52418184,0.0017397869],"about_ca_topic_score_codex":0.000018930172,"about_ca_topic_score_gemma":0.00001548292,"teacher_disagreement_score":0.80444884,"about_ca_system_score_codex":0.000121374156,"about_ca_system_score_gemma":0.00011713591,"threshold_uncertainty_score":0.42806864},"labels":[],"label_agreement":null},{"id":"W4410637109","doi":"10.1145/3701716.3715869","title":"Query Understanding in LLM-based Conversational Information Seeking","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Singapore Management University; Universiteit van Amsterdam; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Information retrieval; World Wide Web; Natural language processing","score_opus":0.01799660445673285,"score_gpt":0.27139216909930397,"score_spread":0.2533955646425711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410637109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040474234,0.0000041256467,0.9790915,0.0012586922,0.000043107048,0.00006804115,1.7366887e-7,0.00023673932,0.01889284],"genre_scores_gemma":[0.8768607,0.0000010191944,0.12173678,0.0013319082,0.0000025264583,0.0000070175147,0.0000040602786,9.2311234e-7,0.000055071323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994478,0.00002043481,0.00018855243,0.000103301725,0.00013646012,0.000103424594],"domain_scores_gemma":[0.99961865,0.00010535718,0.00004944958,0.00017724335,0.000035421745,0.000013861375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021019016,0.00005570813,0.00007369897,0.00049063127,0.000048434245,0.000089188914,0.00024342703,0.000032792876,0.000012897345],"category_scores_gemma":[0.000040748226,0.000055775687,0.000028277836,0.0007385789,0.00001684585,0.0014061212,0.00006617827,0.000065318396,0.0000085767415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001698644,0.000011238153,0.0037265222,0.0000074266723,0.0000041732333,6.3752077e-7,0.000102747166,0.0014843204,0.00009710019,0.9905778,0.00028696438,0.0036993655],"study_design_scores_gemma":[0.00027983193,0.0000092029395,0.0017063445,0.000037437225,0.0000021531794,2.3761491e-7,0.00013824868,0.8636652,0.002859727,0.12986958,0.001333374,0.00009863548],"about_ca_topic_score_codex":0.000037195507,"about_ca_topic_score_gemma":0.000056542096,"teacher_disagreement_score":0.87645596,"about_ca_system_score_codex":0.00043167142,"about_ca_system_score_gemma":0.000100732184,"threshold_uncertainty_score":0.22744665},"labels":[],"label_agreement":null},{"id":"W4411113273","doi":"10.18653/v1/2024.inlg-main.17","title":"Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Paraphrase; Automatic summarization; Computer science; Natural language processing; Artificial intelligence; Transfer of learning; Information retrieval","score_opus":0.026775842732887505,"score_gpt":0.3087025949968748,"score_spread":0.2819267522639873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411113273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043461053,0.00009530485,0.9937878,0.0004075463,0.000050551236,0.00035991237,0.0000036573995,0.0006765869,0.00027250193],"genre_scores_gemma":[0.8367543,0.0000168621,0.16275762,0.00016974978,0.000013100346,0.00008298188,0.000013997201,0.000013676781,0.00017767087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888295,0.000048021873,0.00019961884,0.0004898222,0.00018621735,0.0001933467],"domain_scores_gemma":[0.999258,0.0003785579,0.000023976376,0.00021426068,0.000055535424,0.00006966836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018285992,0.00016038198,0.00015181612,0.00019396408,0.00011689953,0.00028356348,0.000215348,0.00005172407,0.0000071787445],"category_scores_gemma":[0.00001343365,0.0001393883,0.00008726135,0.00021486118,0.000027835538,0.0013986313,0.000029791072,0.0001741379,0.0000018009788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026718992,0.00008532831,0.000025006973,0.00004675292,0.000027590682,0.000012845412,0.00024643648,0.8408003,0.0030987726,0.062229123,0.000039081435,0.09336203],"study_design_scores_gemma":[0.00024323526,0.00011822129,0.00006897549,0.000034847028,0.00001783247,0.0000013612477,0.000017405351,0.9788987,0.015113029,0.0049060113,0.0004156423,0.00016475114],"about_ca_topic_score_codex":0.000020912958,"about_ca_topic_score_gemma":0.000011019743,"teacher_disagreement_score":0.83240825,"about_ca_system_score_codex":0.000038280443,"about_ca_system_score_gemma":0.000020411948,"threshold_uncertainty_score":0.568409},"labels":[],"label_agreement":null},{"id":"W4411236083","doi":"10.1145/3744644","title":"LLM-Cure: LLM-Based Competitor User Review Analysis for Feature Enhancement","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University; Université du Québec à Montréal","funders":"","keywords":"Computer science; Feature (linguistics); Artificial intelligence","score_opus":0.046042394086885305,"score_gpt":0.3511223933018579,"score_spread":0.3050799992149726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411236083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008232068,0.0038914825,0.9928234,0.0020869249,0.00027502925,0.00031574583,0.000014014098,0.0005079813,0.0000030716938],"genre_scores_gemma":[0.0021936577,0.0013871327,0.9943723,0.0012718361,0.00001741005,0.00029246265,0.000016176924,0.000012451091,0.0004365596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986686,0.00015690272,0.00027811594,0.0005159799,0.00011668456,0.00026368792],"domain_scores_gemma":[0.9966114,0.0022124585,0.000072649585,0.00090844894,0.00012569837,0.000069334266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000729087,0.00022573455,0.00060333114,0.0005590197,0.00013276901,0.000029620585,0.00055181363,0.0001353144,0.000012094041],"category_scores_gemma":[0.00066307717,0.00021407453,0.0003016563,0.0013744934,0.00003071026,0.00011905199,0.000019335268,0.00025083774,0.0000012582498],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012022748,0.00096921425,0.00077038404,0.0039716265,0.0062939217,0.000015079669,0.00026286847,0.15437125,0.008860749,0.025132656,0.0033370536,0.795895],"study_design_scores_gemma":[0.003181192,0.0017853136,0.004920556,0.0030102816,0.009698323,0.000021331984,0.000035356315,0.11391682,0.2884494,0.0067203143,0.5653564,0.0029047488],"about_ca_topic_score_codex":0.0000080860555,"about_ca_topic_score_gemma":0.000008983767,"teacher_disagreement_score":0.7929902,"about_ca_system_score_codex":0.000063029176,"about_ca_system_score_gemma":0.00004334993,"threshold_uncertainty_score":0.87297064},"labels":[],"label_agreement":null},{"id":"W4411259709","doi":"10.1101/2025.06.13.25329541","title":"Automation of Systematic Reviews with Large Language Models","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University Health Network; Ottawa Hospital; University of Alberta; St. Michael's Hospital; University of British Columbia; Mount Sinai Hospital; University of Calgary; McGill University; University of Ottawa; Vector Institute; Wilfrid Laurier University; University of Waterloo; University of Toronto","funders":"","keywords":"Automation; Computer science; Systems engineering; Engineering; Mechanical engineering","score_opus":0.03430894453732251,"score_gpt":0.3234808861615266,"score_spread":0.28917194162420407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411259709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021320125,0.003465275,0.9907868,0.00005830746,0.00006276121,0.0012998823,0.0000076048323,0.0003938107,0.0017935443],"genre_scores_gemma":[0.44764292,0.0005356172,0.5496737,0.00011001727,0.000023350613,0.0007046095,0.000018208433,0.000014827014,0.0012767856],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792075,0.00032203313,0.00074932625,0.000471603,0.00036181932,0.00017446704],"domain_scores_gemma":[0.9967693,0.000111913265,0.00087409385,0.0020471157,0.00016129948,0.000036261077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012284374,0.00024159368,0.0010284637,0.00029967987,0.000031764623,0.000051634204,0.001539202,0.00012350595,0.000004702901],"category_scores_gemma":[0.00017474768,0.00017117978,0.00019048614,0.00048250402,0.000020589596,0.0002564962,0.0008822593,0.00024779481,0.000010207982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013370955,0.0006220863,0.001617758,0.4984612,0.00087796914,0.000090345464,0.016297642,0.019839592,0.0017490378,0.44918117,0.0013929028,0.009856931],"study_design_scores_gemma":[0.00016556523,0.0000386017,0.00009788044,0.03897478,0.00025409058,0.000004615091,0.00004408657,0.9292596,0.0053945915,0.025163831,0.00013027208,0.00047207554],"about_ca_topic_score_codex":0.000012600625,"about_ca_topic_score_gemma":0.000020877926,"teacher_disagreement_score":0.90942,"about_ca_system_score_codex":0.000061152205,"about_ca_system_score_gemma":0.00006774404,"threshold_uncertainty_score":0.6980509},"labels":[],"label_agreement":null},{"id":"W4411656759","doi":"10.51847/xz17igjvgz","title":"10.51847/xZ17iGjvGz","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Cluster analysis; Computer science; Data mining; Artificial intelligence; Algorithm","score_opus":0.005534351542979675,"score_gpt":0.2057611130604097,"score_spread":0.20022676151743002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411656759","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006963736,0.00003122738,0.014576399,0.00045132532,0.0000012084981,0.000107521795,0.0000010278376,0.0008836186,0.983878],"genre_scores_gemma":[0.00032768145,4.1767092e-7,0.049931284,0.00016850626,0.000038672642,0.000017196133,0.0000017382569,0.00001070477,0.9495038],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990309,0.000027670618,0.00015663757,0.00032931674,0.00020621705,0.00024924605],"domain_scores_gemma":[0.9990467,0.00003344663,0.00002788318,0.0007299144,0.000044048058,0.00011802458],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011989368,0.00012010446,0.00015183697,0.00010605815,0.00006712861,0.00007902843,0.00091739517,0.000039956583,0.92140454],"category_scores_gemma":[0.000017978027,0.00011696407,0.000068936984,0.00056524394,0.000020533767,0.0003591641,0.00013751292,0.00007474923,0.9604621],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031460545,0.00002023379,1.0502226e-7,7.1294744e-7,0.0000064899123,0.0000054508723,0.000010069373,0.00008331202,0.00012357898,0.000076928634,0.013445499,0.9862245],"study_design_scores_gemma":[0.000050574494,0.00006379283,0.000013779967,0.000005748253,0.000004670806,0.0000050829003,8.068489e-8,0.0045829606,0.0004763668,0.00016441595,0.994476,0.00015648002],"about_ca_topic_score_codex":0.000007665107,"about_ca_topic_score_gemma":1.0265236e-7,"teacher_disagreement_score":0.986068,"about_ca_system_score_codex":0.000036034136,"about_ca_system_score_gemma":0.000016033999,"threshold_uncertainty_score":0.47696564},"labels":[],"label_agreement":null},{"id":"W4411721468","doi":"10.54097/7hwf8v07","title":"The Impact of Evolving Regulatory Policies on Content Strategies: A Case Study of Xiaohongshu (Red Note) Bloggers","year":2025,"lang":"en","type":"article","venue":"Academic journal of management and social sciences","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Content (measure theory); Advertising; Business; Mathematics","score_opus":0.04622755882596701,"score_gpt":0.384249712616817,"score_spread":0.33802215379085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411721468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98915833,0.00047874835,0.008249547,0.0006099691,0.00006199096,0.0001745181,2.525777e-7,0.000012198758,0.001254453],"genre_scores_gemma":[0.99882716,0.00028721188,0.0007656829,0.00004091333,0.000022707436,0.0000019917695,1.7455886e-8,0.0000017066906,0.00005262735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9984737,0.000138389,0.0005471382,0.00015120587,0.0004961246,0.00019344341],"domain_scores_gemma":[0.99874645,0.00023655414,0.0007160082,0.00012898109,0.00014576064,0.000026242618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019035161,0.00010524688,0.0002687175,0.00033253702,0.00044912274,0.00008777577,0.00098793,0.00004574803,9.656789e-7],"category_scores_gemma":[0.00004854161,0.00006291118,0.00012993102,0.00071572216,0.00043939025,0.0005817469,0.00025031128,0.00021810815,4.422569e-8],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021503621,0.0010776569,0.101104714,0.00016316016,0.0026512006,0.0004490215,0.09525396,0.004053009,0.0055871643,0.44118726,0.008827828,0.33943],"study_design_scores_gemma":[0.0031798754,0.005136083,0.30858037,0.0006527133,0.0005643757,0.00013441946,0.52289975,0.012298573,0.0018314789,0.14374085,0.00030820424,0.0006733146],"about_ca_topic_score_codex":0.0002953638,"about_ca_topic_score_gemma":0.00003213984,"teacher_disagreement_score":0.42764577,"about_ca_system_score_codex":0.00007417829,"about_ca_system_score_gemma":0.00009465148,"threshold_uncertainty_score":0.34543344},"labels":[],"label_agreement":null},{"id":"W4412445659","doi":"10.1109/eurocon64445.2025.11073281","title":"Relation on Hesitation in Intuitionistic Fuzzy Sets and Decision Making","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Relation (database); Computer science; Fuzzy set; Artificial intelligence; Fuzzy logic; Mathematics; Data mining","score_opus":0.010991742315215805,"score_gpt":0.32447154964383296,"score_spread":0.31347980732861713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412445659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032826733,0.000021097565,0.95761997,0.00026207967,0.000033751836,0.000075910924,6.208598e-8,0.00012559292,0.009034797],"genre_scores_gemma":[0.6930366,0.0000063002735,0.30671018,0.00019931736,0.0000016936372,0.0000056161607,7.428452e-7,0.0000012000712,0.000038293954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945235,0.000023551538,0.00014780315,0.00020813457,0.00009967691,0.00006851047],"domain_scores_gemma":[0.99949265,0.0002523273,0.000035079353,0.00018072168,0.000029566545,0.00000967283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016689446,0.000052390304,0.00006931512,0.0003260115,0.000060867013,0.00007274304,0.0001158182,0.000034767112,0.000002547587],"category_scores_gemma":[0.000107022825,0.000049193703,0.000012874478,0.00050507934,0.000010937295,0.00034056968,0.00006803075,0.00006237885,0.0000072612397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041848834,0.000012614046,0.001414852,0.0000028563354,0.0000015004308,0.0000018399389,0.000051594834,0.0004072348,0.00008334002,0.5649651,0.00011563184,0.43293923],"study_design_scores_gemma":[0.000087019325,0.00002078491,0.06272681,0.00010860564,0.0000020146892,6.0741877e-7,0.0000074353434,0.10727075,0.00023244604,0.82944363,0.000048902653,0.000050993604],"about_ca_topic_score_codex":0.0000046975633,"about_ca_topic_score_gemma":0.00004784268,"teacher_disagreement_score":0.6602099,"about_ca_system_score_codex":0.000075014956,"about_ca_system_score_gemma":0.000011281344,"threshold_uncertainty_score":0.2006061},"labels":[],"label_agreement":null},{"id":"W4412554184","doi":"10.22214/ijraset.2025.73052","title":"Enhancing Technical Documentation through Intelligent Text Summarization Techniques","year":2025,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Documentation; Computer science; Technical documentation; Information retrieval; Natural language processing; World Wide Web; Programming language","score_opus":0.03231267546222466,"score_gpt":0.425018475019682,"score_spread":0.3927057995574573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412554184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023314874,0.00010088322,0.991537,0.0041311015,0.00022816795,0.0003348805,4.8131756e-7,0.00029253666,0.0010434834],"genre_scores_gemma":[0.65253747,0.00032778506,0.34681982,0.00007070271,0.000032676136,0.0001772621,9.475714e-7,0.0000057673246,0.000027582315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99797046,0.000010554389,0.0003965155,0.0004231782,0.0007541529,0.00044512266],"domain_scores_gemma":[0.9986731,0.00019131205,0.00007134238,0.0002630995,0.000752355,0.00004882039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003047896,0.00011361869,0.00014992166,0.003590064,0.00026080408,0.00041929472,0.0020242422,0.0001208347,0.0000015513231],"category_scores_gemma":[0.0007411943,0.00010998378,0.000028891007,0.003291316,0.0003456563,0.00079317356,0.0007611953,0.0005912049,0.0000016772076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071220147,0.000023478073,0.00004805837,0.0000069902662,0.0000075466914,0.000004735202,0.00004140143,0.00011651549,0.25241736,0.6377565,0.00007439762,0.10949584],"study_design_scores_gemma":[0.00017194916,0.000061471525,0.00005861698,0.00014333223,0.000002004579,0.000045104433,0.00010421167,0.01561668,0.50762945,0.4630862,0.012953136,0.00012784082],"about_ca_topic_score_codex":0.000008252045,"about_ca_topic_score_gemma":0.000009957508,"teacher_disagreement_score":0.65020597,"about_ca_system_score_codex":0.00078757823,"about_ca_system_score_gemma":0.00023453939,"threshold_uncertainty_score":0.44850084},"labels":[],"label_agreement":null},{"id":"W4412887723","doi":"10.18653/v1/2025.findings-acl.1160","title":"Understanding the Influence of Synthetic Data for Text Embedders","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Samsung; National Science Foundation","keywords":"Computer science; Information retrieval; Data science","score_opus":0.08669165571493846,"score_gpt":0.34819054553802975,"score_spread":0.2614988898230913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412887723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050669775,0.000040265753,0.9928261,0.0018071901,0.000021709659,0.00017878614,0.000002366727,0.00012318378,0.004493679],"genre_scores_gemma":[0.9019654,0.000010508368,0.09737827,0.00033269488,0.0000027226497,0.000011403936,0.0000011779507,0.000002539622,0.00029527277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99927086,0.000022484339,0.00017798303,0.00028369966,0.000116174444,0.00012878986],"domain_scores_gemma":[0.99764407,0.00048649727,0.00006992794,0.0017259895,0.000059632934,0.0000138684945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003680667,0.00006736262,0.00011423271,0.00009655236,0.000099647434,0.00005329858,0.0024193441,0.000023814508,0.0000040937616],"category_scores_gemma":[0.00024376571,0.000044031913,0.000038431503,0.00051194883,0.000100955076,0.00050045026,0.0006846165,0.00004742552,0.0000012570503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020589703,0.000015657439,0.00010635829,0.000019454797,0.000038654547,2.2470502e-7,0.00010032375,0.0014992943,0.0009657632,0.98682964,0.0037598107,0.006662784],"study_design_scores_gemma":[0.00012664664,0.000025534468,0.00028013968,0.00006924062,0.000037964455,8.158871e-7,0.00036887568,0.46837285,0.0060683694,0.5222933,0.002228804,0.00012743569],"about_ca_topic_score_codex":0.00000989307,"about_ca_topic_score_gemma":0.0000228161,"teacher_disagreement_score":0.90145874,"about_ca_system_score_codex":0.00003659465,"about_ca_system_score_gemma":0.00005170902,"threshold_uncertainty_score":0.44957834},"labels":[],"label_agreement":null},{"id":"W4412889548","doi":"10.18653/v1/2025.acl-short.15","title":"Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s Characteristics","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut de Valorisation des Données; Nvidia","keywords":"Calibration; Computer science; Confidence interval; Statistics; Distribution (mathematics); Mathematics","score_opus":0.024640111490662857,"score_gpt":0.28667247297568743,"score_spread":0.26203236148502457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412889548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040857136,0.000041159175,0.95796925,0.0008232846,0.000064318985,0.0001558425,0.0000023973653,0.00004534491,0.00004126145],"genre_scores_gemma":[0.9854705,0.00001080557,0.014167568,0.00020646567,0.000023636418,0.000011685063,0.000007848165,0.0000019012296,0.00009959844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920774,0.00008396445,0.00029575604,0.00017113322,0.00014019154,0.000101242025],"domain_scores_gemma":[0.99918044,0.00011329254,0.00015363042,0.0004341714,0.00010964872,0.00000883316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003619334,0.000070335605,0.000102402315,0.000055406792,0.00013214246,0.0001247815,0.0005062921,0.000031751864,0.0000023531238],"category_scores_gemma":[0.00017372085,0.00004088519,0.000033091,0.0005262332,0.0000709425,0.0004147112,0.00017746177,0.00008693907,2.752731e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003834978,0.00004104517,0.0074567706,0.00001781532,0.000015856298,0.0000012292938,0.00038934572,0.0018885485,0.13068692,0.797408,0.00035554968,0.06173508],"study_design_scores_gemma":[0.00003463309,0.000006207811,0.003668769,0.000017040154,0.00000703503,6.8197636e-7,0.000028650691,0.9188461,0.074581355,0.0027130246,0.000050423678,0.00004610376],"about_ca_topic_score_codex":0.0003411067,"about_ca_topic_score_gemma":0.0001588022,"teacher_disagreement_score":0.94461334,"about_ca_system_score_codex":0.0000682873,"about_ca_system_score_gemma":0.000088794084,"threshold_uncertainty_score":0.16672495},"labels":[],"label_agreement":null},{"id":"W4413183628","doi":"10.14722/madweb.2025.23004","title":"Evaluating the Strength and Availability of Multilingual Passphrase Authentication","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Authentication (law); Computer security","score_opus":0.033463372864654374,"score_gpt":0.3962153046769616,"score_spread":0.3627519318123072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413183628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43568256,0.000060577535,0.562407,0.00045666692,0.00001766238,0.00011969702,3.2424023e-7,0.00010083876,0.0011546434],"genre_scores_gemma":[0.8149038,0.0000040875134,0.18458621,0.000052127376,0.0000025284266,0.000007632776,3.1991286e-7,9.707749e-7,0.00044234406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932736,0.00007612275,0.00019682408,0.00020079174,0.00012817538,0.00007069738],"domain_scores_gemma":[0.99894375,0.00033001136,0.00007362433,0.0005280658,0.0001116141,0.00001296593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065799034,0.00005142252,0.00008281123,0.000046492176,0.00006670371,0.000027610786,0.0003281339,0.000019485185,0.000013157593],"category_scores_gemma":[0.0004538294,0.000033167635,0.000027402411,0.0002885794,0.00007551855,0.0001310469,0.00021103378,0.000052466123,0.00000133535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051427323,0.00011197633,0.0050254,0.000026516907,0.000030989988,1.794553e-7,0.0008869422,0.000024831725,0.028500656,0.13781524,0.00009030598,0.8274818],"study_design_scores_gemma":[0.00017417362,0.000059613172,0.013197147,0.000020644904,0.00003205712,4.0038367e-7,0.00013041352,0.71566576,0.20406681,0.06644252,0.00012475734,0.00008571712],"about_ca_topic_score_codex":0.000031666077,"about_ca_topic_score_gemma":0.000020394156,"teacher_disagreement_score":0.8273961,"about_ca_system_score_codex":0.000014676075,"about_ca_system_score_gemma":0.00003854463,"threshold_uncertainty_score":0.1352537},"labels":[],"label_agreement":null},{"id":"W4413367878","doi":"10.18280/mmep.120703","title":"Twitter Sentiment Analysis via Chaotic Quantum Fruit Fly Optimization: Enhancing Feature Selection and Classification","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chaotic; Feature selection; Selection (genetic algorithm); Computer science; Quantum; Sentiment analysis; Feature (linguistics); Artificial intelligence; On the fly; Pattern recognition (psychology); Machine learning; Physics","score_opus":0.015239658600163863,"score_gpt":0.23862027633162247,"score_spread":0.22338061773145862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413367878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038728635,0.0001907146,0.99496305,0.00040952314,0.000022152806,0.00014840133,1.5440094e-7,0.00033837775,0.000054789325],"genre_scores_gemma":[0.5349222,0.00003489336,0.4648202,0.000019837002,0.000008795288,0.000030158542,0.0000019372478,0.000007136704,0.000154866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901253,0.000016259402,0.00026629158,0.0003688603,0.00014469656,0.00019138731],"domain_scores_gemma":[0.99951434,0.000073681076,0.000060147686,0.00023134658,0.000062292456,0.000058190966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025443875,0.00016222186,0.00026637464,0.00035087662,0.00010439278,0.00017362346,0.00012908824,0.000090074136,0.0000027146016],"category_scores_gemma":[0.00001502065,0.00014971319,0.00005781636,0.0009032508,0.0000138850655,0.00021979955,0.000071395865,0.00015444776,0.0000015463776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.1652526e-7,0.000020650163,0.000034259363,0.00015826059,0.00011926114,2.8647844e-7,0.00025457828,0.97645164,0.001190173,0.021335607,0.0000067582587,0.0004278859],"study_design_scores_gemma":[0.000059418457,0.000011598602,0.000028939388,0.00011098742,0.00016252084,0.0000034395775,0.000006026509,0.9826774,0.0008135129,0.015957255,0.000026617656,0.00014226772],"about_ca_topic_score_codex":0.0000027132671,"about_ca_topic_score_gemma":7.031426e-7,"teacher_disagreement_score":0.5310493,"about_ca_system_score_codex":0.000044245462,"about_ca_system_score_gemma":0.0000074072673,"threshold_uncertainty_score":0.6105127},"labels":[],"label_agreement":null},{"id":"W4413677204","doi":"10.1016/j.ipm.2025.104335","title":"Class-Missing Semi-supervised document key information extraction via synergistic refinement estimation","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Vector Institute; Western University","funders":"Key Research and Development Projects of Shaanxi Province; National Natural Science Foundation of China","keywords":"Key (lock); Estimation; Class (philosophy); Computer science; Extraction (chemistry); Information retrieval; Artificial intelligence; Engineering; Chemistry; Chromatography; Computer security","score_opus":0.005924988358388565,"score_gpt":0.27765318649217363,"score_spread":0.27172819813378507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413677204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024616512,0.000048697915,0.9618654,0.0018022301,0.00022708705,0.00055203144,8.5355487e-7,0.00092634646,0.03433118],"genre_scores_gemma":[0.5949916,0.00004073573,0.40219626,0.0019804942,0.00001672731,0.0002530565,0.00014913094,0.000007105069,0.00036486652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752116,0.00004354945,0.0011367955,0.00024496674,0.00071881793,0.00033469943],"domain_scores_gemma":[0.99826443,0.00003327908,0.00066574983,0.0006044683,0.0003625307,0.00006952801],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0006592773,0.00027445884,0.00021970776,0.001097485,0.0005012413,0.0014464387,0.0006468064,0.00009116117,0.000020352543],"category_scores_gemma":[0.00006663564,0.0002788583,0.00007750291,0.0013890556,0.00003534571,0.017404746,0.0003307033,0.00017696038,0.00012700482],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009897685,0.00002920091,0.000009039434,0.0005069859,0.000036270987,9.3580707e-7,0.00059709453,0.016538074,0.00006595727,0.04277629,0.0011242701,0.938306],"study_design_scores_gemma":[0.00053246785,0.00002678821,0.0005825903,0.0003829224,0.000074390045,0.0000028114746,0.00020382856,0.89801353,0.0024501614,0.028691536,0.06871055,0.00032844738],"about_ca_topic_score_codex":0.00001958758,"about_ca_topic_score_gemma":0.0000020391658,"teacher_disagreement_score":0.93797755,"about_ca_system_score_codex":0.0006611741,"about_ca_system_score_gemma":0.000083047256,"threshold_uncertainty_score":0.9999664},"labels":[],"label_agreement":null},{"id":"W4413975987","doi":"10.4018/ijisss.388002","title":"LLM-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network for Sentiment Analysis","year":2025,"lang":"en","type":"article","venue":"International Journal of Information Systems in the Service Sector","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Graph; Information fusion; Sentiment analysis; Artificial intelligence; Fusion; Data mining; Theoretical computer science","score_opus":0.009639930156432422,"score_gpt":0.2799848287921413,"score_spread":0.2703448986357089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413975987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025152056,0.000042211435,0.97097695,0.0022001744,0.00066578295,0.00050894066,0.000017158767,0.000045701137,0.00039105274],"genre_scores_gemma":[0.9332557,0.000014022281,0.06438582,0.0019764395,0.00015195271,0.0000625967,0.00013784382,0.0000038460394,0.000011795091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970181,0.00015996027,0.0014832104,0.00010220441,0.0010401332,0.00019639624],"domain_scores_gemma":[0.9957337,0.00025830654,0.0014181879,0.0003339385,0.0022099353,0.00004596833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017276368,0.00017363972,0.00033732556,0.0016342938,0.00011119339,0.00059164513,0.0016957307,0.00008418204,0.0000053308986],"category_scores_gemma":[0.000079427526,0.00011632713,0.00021681206,0.0022190127,0.000021435877,0.004571537,0.00012691921,0.00023498188,0.0000053826016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070435693,0.00021300484,0.017298535,0.0002024858,0.0026812423,0.000009157915,0.0106207365,0.8454538,0.000048741826,0.10088665,0.0047709933,0.017110309],"study_design_scores_gemma":[0.0029848297,0.00024372924,0.014396901,0.000558393,0.000266944,0.00010294949,0.001371817,0.93821037,0.00033857446,0.005702761,0.035462752,0.0003599528],"about_ca_topic_score_codex":0.00033097077,"about_ca_topic_score_gemma":0.00022758405,"teacher_disagreement_score":0.90810364,"about_ca_system_score_codex":0.00024922707,"about_ca_system_score_gemma":0.000162219,"threshold_uncertainty_score":0.57052475},"labels":[],"label_agreement":null},{"id":"W4414359746","doi":"10.24963/ijcai.2025/816","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Function (biology); Variety (cybernetics); Code (set theory); Comprehension; Knowledge base; Base (topology)","score_opus":0.014202416373039149,"score_gpt":0.30295157743381,"score_spread":0.28874916106077086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414359746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006607809,0.00021037777,0.9948306,0.0002482725,0.0002794877,0.00017767862,0.000002500924,0.00076352904,0.0028267526],"genre_scores_gemma":[0.76385266,0.00000793503,0.23450756,0.0004737448,0.00004153144,0.00003638668,0.000024699428,0.00000594341,0.0010495697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988698,0.000036314977,0.00026450062,0.00048320735,0.0001798226,0.00016634833],"domain_scores_gemma":[0.9985085,0.0008367403,0.0001228442,0.0003635052,0.00014201329,0.000026406218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019416687,0.00012764739,0.00016332092,0.00014548696,0.00028541585,0.00015949167,0.00030781154,0.00008614012,0.00006700097],"category_scores_gemma":[0.00032413457,0.000114619084,0.00009391839,0.0005375103,0.000018819286,0.00052595994,0.00014553267,0.00011839702,0.000016676644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009520712,0.00003444551,0.0015771271,0.000005739237,0.00006292298,5.0456634e-7,0.00003564665,0.004947376,0.0019649258,0.15343916,0.017969487,0.81986743],"study_design_scores_gemma":[0.00016928087,0.000101104284,0.0021091956,0.000058620302,0.000045455963,2.7489543e-7,0.000035954083,0.47187707,0.00068914384,0.46381056,0.060925167,0.00017818157],"about_ca_topic_score_codex":0.000013651462,"about_ca_topic_score_gemma":0.000034191722,"teacher_disagreement_score":0.8196893,"about_ca_system_score_codex":0.000089287394,"about_ca_system_score_gemma":0.000021847061,"threshold_uncertainty_score":0.46740305},"labels":[],"label_agreement":null},{"id":"W4414588928","doi":"10.3390/app151910506","title":"Mind the Link: Discourse Link-Aware Hallucination Detection in Summarization","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Privy Council Office","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center; National Research Foundation of Korea; National Research Foundation","keywords":"Automatic summarization; Meaning (existential); Representation (politics); Relation (database); Content (measure theory); Semantic relation; Structuring","score_opus":0.01175317348728903,"score_gpt":0.30321453504426277,"score_spread":0.2914613615569737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414588928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088280765,0.00004560454,0.9809246,0.0045914105,0.00011283604,0.00024331595,2.573454e-7,0.00010109546,0.005152788],"genre_scores_gemma":[0.97976065,0.0000157056,0.019740986,0.00018690093,0.000046415822,0.000056765064,0.000001545817,0.000002399512,0.00018862312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876976,0.00004846902,0.00022769961,0.0004380985,0.00031281088,0.00020316962],"domain_scores_gemma":[0.9993283,0.00014371068,0.00010891461,0.00034915938,0.000050759652,0.000019123574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008527323,0.000102568796,0.00010735543,0.00035525043,0.00038510855,0.00022684394,0.0009887208,0.000061451006,0.0000034958898],"category_scores_gemma":[0.000050621056,0.000072717914,0.000029979985,0.0027718288,0.00023333903,0.000544683,0.00018707877,0.00014221642,0.00000990742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015168476,0.000012203337,0.00036243192,0.0000027433387,0.0000029104237,4.6092467e-7,0.0003345239,0.0019209041,0.0042417403,0.07797719,0.000015411953,0.915128],"study_design_scores_gemma":[0.0003074931,0.00006559073,0.011159028,0.00005729714,0.000020762564,0.0000015889367,0.00065966597,0.69073224,0.15600167,0.13650721,0.0041140397,0.00037342124],"about_ca_topic_score_codex":0.000033801425,"about_ca_topic_score_gemma":0.0005284306,"teacher_disagreement_score":0.9709326,"about_ca_system_score_codex":0.00007047882,"about_ca_system_score_gemma":0.00008467295,"threshold_uncertainty_score":0.29653504},"labels":[],"label_agreement":null},{"id":"W4415203880","doi":"10.5753/jbcs.2025.5815","title":"Cross-Lingual Keyword Extraction for Pesticide Terminology in Brazilian Portuguese and English","year":2025,"lang":"en","type":"article","venue":"Journal of the Brazilian Computer Society","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; Universität St. Gallen","keywords":"Terminology; Portuguese; Standardization; Brazilian Portuguese; Pesticide; Representation (politics)","score_opus":0.009630347366461907,"score_gpt":0.3190914924121837,"score_spread":0.3094611450457218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415203880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21976334,0.00041681775,0.7767258,0.0014072104,0.0013176379,0.00021296008,0.0000014558364,0.00006619469,0.000088584326],"genre_scores_gemma":[0.5698844,0.00013690544,0.42695937,0.0019627542,0.00054939714,0.000009343791,7.774648e-7,0.00001554609,0.000481457],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99828506,0.000098124474,0.00073251594,0.00033894036,0.00023208797,0.0003132977],"domain_scores_gemma":[0.998043,0.0004086782,0.0005489247,0.00049019576,0.00043534607,0.00007387959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088195276,0.00019553187,0.00040304218,0.00017053926,0.00018319878,0.00019557706,0.0012932603,0.00016537677,0.0000017992027],"category_scores_gemma":[0.00019477341,0.00015217043,0.00045908516,0.0005463079,0.00018236718,0.0008415558,0.00047682712,0.00052896264,3.2812375e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000817802,0.00036768976,0.06570276,0.00013910464,0.0003328516,0.000051423594,0.004887884,0.0022718706,0.0020547796,0.006942989,0.015952652,0.90121424],"study_design_scores_gemma":[0.0034616143,0.00049285026,0.7348248,0.0005655421,0.00014313852,0.00031751554,0.00020149414,0.15247568,0.009506484,0.059225745,0.03809747,0.0006876599],"about_ca_topic_score_codex":0.000006306098,"about_ca_topic_score_gemma":0.000017268212,"teacher_disagreement_score":0.9005266,"about_ca_system_score_codex":0.00016078459,"about_ca_system_score_gemma":0.00019808761,"threshold_uncertainty_score":0.620533},"labels":[],"label_agreement":null},{"id":"W4415273246","doi":"10.1007/978-981-95-3462-3_5","title":"Analysis of Metadata and Cough Signal Complexities in Tuberculosis Screening","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Centre Hospitalier de l’Université de Montréal; Université TÉLUQ","funders":"","keywords":"Metadata; Preprocessor; Hurst exponent; Linear discriminant analysis; Time series; Data pre-processing; SIGNAL (programming language); Novelty","score_opus":0.0229232635157959,"score_gpt":0.2808472809139578,"score_spread":0.2579240173981619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415273246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013896817,0.0010439359,0.996683,0.0002772675,0.000080151134,0.00023118149,0.00002469754,0.00010413071,0.0014166606],"genre_scores_gemma":[0.19682665,0.00011533251,0.80223465,0.00051203783,0.00003644372,0.0000086943965,0.000020509204,0.000015073755,0.00023060454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99609065,0.000064052714,0.00086165534,0.0015644697,0.000930446,0.0004887156],"domain_scores_gemma":[0.9967686,0.0009873258,0.000409186,0.0014768726,0.00026490516,0.000093091076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001085994,0.00049992505,0.0013541981,0.004872364,0.00013160896,0.00037484794,0.002962472,0.00023736864,0.000016618491],"category_scores_gemma":[0.00008806288,0.00048338345,0.0002489957,0.00377144,0.00084567,0.0011937583,0.0023496575,0.0006143323,5.328749e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011534756,0.00005222327,0.001936614,0.0000994647,0.0006035898,0.000068308356,0.0011462396,0.092770025,0.00022581697,0.12514298,0.000012153363,0.77793103],"study_design_scores_gemma":[0.00014154568,0.00006456776,0.0012453066,0.0003931844,0.00025084204,0.0000055028718,7.506649e-7,0.8659879,0.0014791561,0.1297583,0.0001677442,0.0005051819],"about_ca_topic_score_codex":0.00021150602,"about_ca_topic_score_gemma":0.0010085659,"teacher_disagreement_score":0.7774259,"about_ca_system_score_codex":0.00017143397,"about_ca_system_score_gemma":0.00022722637,"threshold_uncertainty_score":0.99976176},"labels":[],"label_agreement":null},{"id":"W4415373758","doi":"10.1108/ejm-04-2025-0301","title":"Understanding the defining characteristics of a high-quality conceptual article","year":2025,"lang":"en","type":"article","venue":"European Journal of Marketing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Operationalization; Rubric; Conceptual framework; Conceptual model; Quality (philosophy); Empirical research; The Conceptual Framework","score_opus":0.052879564351633386,"score_gpt":0.2909858425233979,"score_spread":0.2381062781717645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415373758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19519542,0.000097353186,0.7973007,0.0005027757,0.00011206598,0.000027118445,5.7599385e-7,0.0000283253,0.0067356694],"genre_scores_gemma":[0.9490955,0.00002089207,0.050629463,0.00017120023,0.000037555783,1.6025406e-7,1.3763264e-7,0.0000066344933,0.00003846375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9964342,0.0021836546,0.0008235511,0.00012532185,0.00027204078,0.00016121632],"domain_scores_gemma":[0.99690896,0.0016213129,0.00094957417,0.00029895394,0.00018389686,0.00003729099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01160778,0.000088912384,0.0002424505,0.000121248435,0.00014408384,0.0000814631,0.00082693895,0.00001187729,0.0000064835954],"category_scores_gemma":[0.0026153342,0.000064526874,0.00011325193,0.00041902013,0.00013417432,0.00024841947,0.00029337557,0.00026217088,0.0000019522313],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042377927,0.00015175676,0.029437598,0.00009651168,0.00041155133,0.0002341711,0.004437931,0.00041823147,0.031061523,0.72396845,0.0017715024,0.20758697],"study_design_scores_gemma":[0.0027921968,0.00046710556,0.9052956,0.0027160237,0.00028447053,0.00015185533,0.007905021,0.007427356,0.0229037,0.045850947,0.0033810386,0.00082468527],"about_ca_topic_score_codex":9.786072e-7,"about_ca_topic_score_gemma":3.7526445e-7,"teacher_disagreement_score":0.875858,"about_ca_system_score_codex":0.00007042566,"about_ca_system_score_gemma":0.00004923287,"threshold_uncertainty_score":0.40230483},"labels":[],"label_agreement":null},{"id":"W4415422573","doi":"10.1016/j.eswa.2025.130088","title":"DGSEP: Dual-stage generative model with sequence-oriented labeling and element-to-tuple prompting improves aspect sentiment triplet extraction","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Sichuan Province Science and Technology Support Program; Key Research and Development Program of Sichuan Province; Chengdu Science and Technology Bureau; Department of Science and Technology of Sichuan Province; National Natural Science Foundation of China","keywords":"Fuse (electrical); Generative grammar; Generative model; Sequence (biology); Task (project management); Sentiment analysis","score_opus":0.018136075905115134,"score_gpt":0.32024835108470256,"score_spread":0.30211227517958744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415422573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057888525,0.0003411065,0.98983055,0.00070104504,0.000027321807,0.0022482122,0.000010040463,0.00046990745,0.0005829891],"genre_scores_gemma":[0.4153042,0.000025004285,0.576437,0.00019307736,0.000051689676,0.0058492264,0.000024096284,0.00002060132,0.0020950728],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980867,0.000053932803,0.00041018514,0.0008178176,0.00032237757,0.00030901065],"domain_scores_gemma":[0.998541,0.000055354896,0.00025724148,0.0007596747,0.00027360278,0.00011315443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025125314,0.00025262148,0.00028889388,0.00026508764,0.00048585015,0.00023828223,0.00028257424,0.000052166255,0.0000012475396],"category_scores_gemma":[0.000010844438,0.0001993479,0.000029662851,0.0010203436,0.00005076145,0.0005289472,0.00014024256,0.00013675855,0.0000039917704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004616181,0.00028745714,0.00032292138,0.00010455205,0.00032801114,0.000008844508,0.0036575345,0.03526955,0.698669,0.2511355,0.0007828176,0.009387603],"study_design_scores_gemma":[0.00051416404,0.00013300784,0.00002196907,0.00016319392,0.000033334745,0.00001682171,0.0011784587,0.91262174,0.0753367,0.00036589007,0.0092189275,0.00039581908],"about_ca_topic_score_codex":0.00014918027,"about_ca_topic_score_gemma":0.000054792585,"teacher_disagreement_score":0.8773522,"about_ca_system_score_codex":0.0002440318,"about_ca_system_score_gemma":0.0001368497,"threshold_uncertainty_score":0.8129171},"labels":[],"label_agreement":null},{"id":"W4415598779","doi":"10.1115/detc2025-163043","title":"Cognitive Demands and Individual Differences in Product Similarity Judgements: A Context-Dependent Model","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Similarity (geometry); Cognition; Context (archaeology); Product (mathematics); Schema (genetic algorithms); Pairwise comparison","score_opus":0.04925063824614321,"score_gpt":0.3173307582133334,"score_spread":0.26808011996719017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415598779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10467864,0.0032588053,0.88588554,0.0013855856,0.00011491287,0.0011036743,0.000028789938,0.00019235798,0.003351719],"genre_scores_gemma":[0.9797483,0.0008059334,0.015724156,0.0015793047,0.000019786457,0.00015008978,0.0000058556498,0.000011849848,0.001954732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954325,0.0002771251,0.00097010884,0.0018388301,0.00076337345,0.00071807794],"domain_scores_gemma":[0.9981788,0.00029483694,0.0002484881,0.0007545268,0.0003737282,0.00014963113],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011918459,0.0005588321,0.0009511409,0.0008633119,0.00028534452,0.0005899597,0.0012387792,0.0001896849,0.000040639516],"category_scores_gemma":[0.00042008018,0.00051891425,0.00014437523,0.0014112191,0.00042884034,0.0014151932,0.0023928832,0.0006258426,0.000005222752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011954555,0.0015410421,0.15883611,0.00019394427,0.0010818057,0.000040430365,0.004124988,0.00021450353,0.00010878259,0.06487666,0.00043093332,0.76843125],"study_design_scores_gemma":[0.0026658075,0.00028609624,0.05493021,0.0007432614,0.0005568255,0.0000041485064,0.001134259,0.81096077,0.008047778,0.11956237,0.000052275347,0.00105622],"about_ca_topic_score_codex":0.00020160717,"about_ca_topic_score_gemma":0.001147159,"teacher_disagreement_score":0.8750697,"about_ca_system_score_codex":0.00013388689,"about_ca_system_score_gemma":0.0003319801,"threshold_uncertainty_score":0.99972624},"labels":[],"label_agreement":null},{"id":"W65121486","doi":"10.1007/978-3-642-23863-5_1","title":"Autonomous and Adaptive Identification of Topics in Unstructured Text","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Novelty; Identification (biology); Flexibility (engineering); Artificial intelligence; Process (computing); Natural language processing; Information retrieval; Programming language","score_opus":0.016527156940934352,"score_gpt":0.2503990093970874,"score_spread":0.23387185245615308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W65121486","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002476175,0.00036573177,0.9975729,0.000121411125,0.00025003773,0.00027154037,0.0000024037965,0.00008369691,0.0010846896],"genre_scores_gemma":[0.48696443,0.000065306805,0.5126097,0.000119471006,0.00006063772,0.0000061606365,0.0000015405514,0.000014535604,0.00015817402],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974947,0.000028497016,0.0006596037,0.0010715439,0.00043685778,0.00030882974],"domain_scores_gemma":[0.99806106,0.00013276398,0.00048964925,0.0010549839,0.00019257114,0.0000689959],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000512248,0.00032378937,0.0004994017,0.0010548279,0.00006516246,0.00010684701,0.0018554209,0.00025328272,0.0000058678247],"category_scores_gemma":[0.00005831743,0.00030897208,0.00007088488,0.0005943591,0.00068564893,0.0005674376,0.0008368284,0.00045723564,0.0000027331296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034776047,0.000013841629,0.00012764308,0.000017541843,0.0000067502538,0.000015993488,0.00095756195,0.0016451838,0.00043321098,0.09003289,0.0000012768469,0.9067446],"study_design_scores_gemma":[0.0001536692,0.00012330557,0.0020877807,0.00018653568,0.000009686091,0.000025796773,2.485019e-7,0.15662678,0.01559282,0.824498,0.00022819958,0.00046719966],"about_ca_topic_score_codex":0.00004465018,"about_ca_topic_score_gemma":0.00015984898,"teacher_disagreement_score":0.9062774,"about_ca_system_score_codex":0.0001967439,"about_ca_system_score_gemma":0.00021486542,"threshold_uncertainty_score":0.9999362},"labels":[],"label_agreement":null},{"id":"W67066386","doi":"","title":"A hybrid approach to the identification and expansion of abbreviations","year":2000,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Task (project management); Class (philosophy); Natural language processing; Identification (biology); Word (group theory); Artificial intelligence; Domain (mathematical analysis); Information retrieval; Engineering","score_opus":0.013420753987818133,"score_gpt":0.2619721861350616,"score_spread":0.24855143214724348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W67066386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016499046,0.000039005226,0.97772586,0.00070685626,0.0000049324326,0.00013018081,4.4304326e-7,0.00008041177,0.004813268],"genre_scores_gemma":[0.8139172,0.000029753512,0.18497773,0.00013357103,0.0000057162606,0.000021896449,0.0000011733111,0.0000016585691,0.00091128465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995018,0.000023549388,0.00015099978,0.00015807107,0.000110497225,0.00005504578],"domain_scores_gemma":[0.9994505,0.000021852537,0.000036635374,0.0004306159,0.000039489103,0.000020887906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018489624,0.000038762602,0.000059491682,0.000049184328,0.00005897732,0.000036769416,0.0003198084,0.000007821275,0.0000127307585],"category_scores_gemma":[0.000014128734,0.00002533357,0.000020549433,0.0002570525,0.00001577363,0.00022771655,0.000050568306,0.000023724742,0.000015555768],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014898542,0.00006109524,0.0000621069,0.000006733288,0.000009841002,1.4396059e-7,0.00078259263,0.00078126736,0.00863498,0.13077953,0.0031556874,0.8557245],"study_design_scores_gemma":[0.00023589749,0.00009675106,0.019604087,0.000028822125,0.000043908603,0.00003214095,0.00011876756,0.6203034,0.24796069,0.07090659,0.04021509,0.00045385183],"about_ca_topic_score_codex":0.0000152137645,"about_ca_topic_score_gemma":0.0000017283733,"teacher_disagreement_score":0.8552707,"about_ca_system_score_codex":0.0000064557407,"about_ca_system_score_gemma":0.0000063308134,"threshold_uncertainty_score":0.10330729},"labels":[],"label_agreement":null},{"id":"W6911926465","doi":"10.5281/zenodo.14137274","title":"A survey on audio analysis: Text characterization and summarization","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Automatic summarization; Search engine indexing; Context (archaeology); Multi-document summarization; Transcription (linguistics); Variety (cybernetics)","score_opus":0.03022118782953534,"score_gpt":0.2682771205464275,"score_spread":0.23805593271689215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911926465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007941524,0.00007651145,0.98462,0.00049329427,0.00005251905,0.00021116137,0.00010188565,0.0021164285,0.0043866937],"genre_scores_gemma":[0.9930309,0.00017869251,0.00172375,0.00014168979,0.00005513989,7.841545e-8,0.0036024097,0.00042466418,0.0008426448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981949,0.00038957148,0.00023556489,0.00061058387,0.0003392617,0.00023013794],"domain_scores_gemma":[0.9988897,0.000054491433,0.000076645265,0.0005324583,0.00033861733,0.00010810274],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088573626,0.0001399489,0.00016754663,0.00086449215,0.00086354377,0.0020310802,0.00082881236,0.000057546764,0.00054494716],"category_scores_gemma":[0.00033312364,0.00014092641,0.000059190123,0.0032234718,0.00006864494,0.00076536427,0.00076136575,0.00017874347,0.001027165],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026161099,0.00012667931,0.000109009154,0.000058245314,0.0004381871,0.000024867108,0.0012125281,0.00021877613,0.01618573,0.07567069,0.014067988,0.89186114],"study_design_scores_gemma":[0.00021942094,0.00031537635,0.07290899,0.00007293533,0.00013367024,0.00002445857,0.00002371376,0.16732341,0.0018187013,0.001047866,0.75562936,0.00048208723],"about_ca_topic_score_codex":0.000013915213,"about_ca_topic_score_gemma":0.0000014331455,"teacher_disagreement_score":0.9850894,"about_ca_system_score_codex":0.000106794265,"about_ca_system_score_gemma":0.000003654095,"threshold_uncertainty_score":0.9997507},"labels":[],"label_agreement":null},{"id":"W6930397270","doi":"10.5281/zenodo.12485825","title":"hanstone quartz care and maintenance pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Point (geometry); Product (mathematics); Troubleshooting; Context (archaeology)","score_opus":0.014391820200062227,"score_gpt":0.24995228027409008,"score_spread":0.23556046007402787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930397270","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028006225,0.0018574437,0.1914607,0.0002762985,0.000085217034,0.00027119127,0.00006272292,0.0030908927,0.80289274],"genre_scores_gemma":[0.003586595,0.0014638358,0.03196211,0.00023026574,0.0003230356,1.6516442e-7,0.0006750921,0.010180636,0.95157826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998245,0.00013442214,0.00019046447,0.00076507725,0.0003386587,0.0003263644],"domain_scores_gemma":[0.99864674,0.000008267743,0.00012111985,0.00085628283,0.0002310842,0.00013648452],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002161831,0.00022577611,0.00023188407,0.0005192818,0.0004473857,0.001032958,0.0016599663,0.00012989553,0.008428077],"category_scores_gemma":[0.00011421888,0.00022684602,0.00006570133,0.000649076,0.000176795,0.00019255797,0.002115994,0.00035189657,0.032752875],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019178196,0.000013444853,9.5755276e-8,0.00014549393,0.000036483707,0.000030939555,0.0005318138,9.562636e-7,0.000116070754,0.016069831,0.86394197,0.11911098],"study_design_scores_gemma":[0.000104864004,0.00010688992,0.00000261852,0.00020041832,0.000017809385,0.00006338021,0.000093178714,0.0002529165,0.00008730346,0.0011891157,0.9976377,0.00024384238],"about_ca_topic_score_codex":0.000022254972,"about_ca_topic_score_gemma":0.0000018845559,"teacher_disagreement_score":0.15949859,"about_ca_system_score_codex":0.0001298161,"about_ca_system_score_gemma":0.0000035173891,"threshold_uncertainty_score":0.99608386},"labels":[],"label_agreement":null},{"id":"W6958505310","doi":"10.6084/m9.figshare.6999395","title":"Additional file 3: of The prevalence of low back pain in the emergency department: a descriptive study set in the Charles V. Keating Emergency and Trauma Centre, Halifax, Nova Scotia, Canada","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Low back pain; Back pain; Minimum Data Set; Emergency department; Low income","score_opus":0.031378791300347444,"score_gpt":0.2582453842967842,"score_spread":0.22686659299643674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958505310","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013751285,0.00015094313,0.00004694084,0.00011837691,0.000030684918,0.0009660217,0.9843896,0.000013376197,0.00053277024],"genre_scores_gemma":[0.97553957,0.00000493674,0.0012826329,0.00010794646,0.00004837098,0.0003705468,0.022505462,0.000010283093,0.00013025817],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99808764,0.00049874274,0.00041427897,0.0003025192,0.00047695477,0.00021985431],"domain_scores_gemma":[0.9983951,0.00055412244,0.00031277124,0.0005443304,0.00017100353,0.000022674201],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027283974,0.00014850413,0.00016023542,0.000056441466,0.00008896039,0.000015810236,0.0013311368,0.000029880595,0.47766557],"category_scores_gemma":[0.0014074992,0.00008843733,0.000055566285,0.00088319613,0.000028008975,0.00022184665,0.00022893869,0.00013952126,0.000016000904],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019664346,0.00012361052,0.003999457,0.00011433389,0.000013052441,0.0000035049418,0.0042711906,0.0000055024,0.0000036990748,0.000014330593,0.98930067,0.002148672],"study_design_scores_gemma":[0.0005155561,0.000565474,0.9400438,0.0056668865,0.000030861065,0.00001132005,0.009429723,0.009389469,0.00080068945,0.0012727728,0.031588968,0.0006844468],"about_ca_topic_score_codex":0.010160983,"about_ca_topic_score_gemma":0.49396834,"teacher_disagreement_score":0.96188414,"about_ca_system_score_codex":0.000050815375,"about_ca_system_score_gemma":0.00012602708,"threshold_uncertainty_score":0.99643046},"labels":[],"label_agreement":null},{"id":"W6968187110","doi":"10.5281/zenodo.15745479","title":"Database of economic valuation of river ecosystem services stemming from ecohidrological forest management in Catalonia (Spain)","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Valuation (finance); Ecosystem services; Forest management; Ecosystem; Forest ecology; Ecosystem management; Weighting","score_opus":0.028155607762459022,"score_gpt":0.2720776059287713,"score_spread":0.24392199816631227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968187110","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031331747,0.00015036599,0.07941681,0.00008753158,0.00012110197,0.0010434713,0.91476995,0.0003467718,0.00093084003],"genre_scores_gemma":[0.021138832,0.0002596812,0.0074778055,0.000030346058,0.000034950197,3.0647647e-7,0.97087264,0.00014825643,0.000037157086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99748266,0.00048039845,0.0006836823,0.00071079977,0.00038865404,0.00025377842],"domain_scores_gemma":[0.99756896,0.0000743763,0.0005658249,0.0014879381,0.00023786245,0.00006506155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093612156,0.00021606275,0.0004238616,0.0007960983,0.0002615126,0.00021172546,0.0035545228,0.00012528435,0.00044572246],"category_scores_gemma":[0.00007899101,0.00023131103,0.00008077208,0.00056280487,0.000079697056,0.0005109772,0.0045084674,0.0002501888,0.00025442752],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101183294,0.00048773596,0.000043952576,0.002435405,0.0004747988,0.0000852402,0.0004527543,0.004560362,0.00023551672,0.007675178,0.9325051,0.050942793],"study_design_scores_gemma":[0.00049867394,0.00013390018,0.00034950057,0.0004995357,0.00008538587,0.00000558479,0.000055829576,0.018046992,0.0002266838,0.0008657803,0.9789531,0.00027903396],"about_ca_topic_score_codex":0.000511896,"about_ca_topic_score_gemma":0.00014952285,"teacher_disagreement_score":0.071939,"about_ca_system_score_codex":0.0003014841,"about_ca_system_score_gemma":0.000009220457,"threshold_uncertainty_score":0.943259},"labels":[],"label_agreement":null},{"id":"W6968317102","doi":"10.5281/zenodo.14137275","title":"A survey on audio analysis: Text characterization and summarization","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Automatic summarization; Search engine indexing; Context (archaeology); Multi-document summarization; Transcription (linguistics); Variety (cybernetics)","score_opus":0.03022118782953534,"score_gpt":0.2682771205464275,"score_spread":0.23805593271689215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968317102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007941524,0.00007651145,0.98462,0.00049329427,0.00005251905,0.00021116137,0.00010188565,0.0021164285,0.0043866937],"genre_scores_gemma":[0.9930309,0.00017869251,0.00172375,0.00014168979,0.00005513989,7.841545e-8,0.0036024097,0.00042466418,0.0008426448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981949,0.00038957148,0.00023556489,0.00061058387,0.0003392617,0.00023013794],"domain_scores_gemma":[0.9988897,0.000054491433,0.000076645265,0.0005324583,0.00033861733,0.00010810274],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088573626,0.0001399489,0.00016754663,0.00086449215,0.00086354377,0.0020310802,0.00082881236,0.000057546764,0.00054494716],"category_scores_gemma":[0.00033312364,0.00014092641,0.000059190123,0.0032234718,0.00006864494,0.00076536427,0.00076136575,0.00017874347,0.001027165],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026161099,0.00012667931,0.000109009154,0.000058245314,0.0004381871,0.000024867108,0.0012125281,0.00021877613,0.01618573,0.07567069,0.014067988,0.89186114],"study_design_scores_gemma":[0.00021942094,0.00031537635,0.07290899,0.00007293533,0.00013367024,0.00002445857,0.00002371376,0.16732341,0.0018187013,0.001047866,0.75562936,0.00048208723],"about_ca_topic_score_codex":0.000013915213,"about_ca_topic_score_gemma":0.0000014331455,"teacher_disagreement_score":0.9850894,"about_ca_system_score_codex":0.000106794265,"about_ca_system_score_gemma":0.000003654095,"threshold_uncertainty_score":0.9997507},"labels":[],"label_agreement":null},{"id":"W6968664339","doi":"10.5281/zenodo.3965653","title":"A SEMANTIC METADATA ENRICHMENT SOFTWARE ECOSYSTEM BASED ON TOPIC METADATA ENRICHMENTS","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Metadata; Semantic grid; Metadata repository; Metadata modeling; Meta Data Services; Semantic computing; Geospatial metadata; Data element; Database catalog","score_opus":0.04275775834215196,"score_gpt":0.2600206395142916,"score_spread":0.21726288117213965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968664339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047441473,0.000052464966,0.98942596,0.002573871,0.000051756902,0.00046291537,0.00011058113,0.0021387588,0.004709259],"genre_scores_gemma":[0.9335088,0.0000438422,0.06070157,0.0028947315,0.00013239447,3.386151e-7,0.0012200493,0.00085065083,0.0006475976],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99723834,0.00042685727,0.00035737443,0.0008450655,0.0007359568,0.00039639603],"domain_scores_gemma":[0.99780214,0.000053096268,0.00017558289,0.0013286433,0.0003080774,0.00033245533],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005589897,0.00022058887,0.00027539476,0.00025630937,0.0010237311,0.0017823806,0.0035097718,0.00005156695,0.0012386421],"category_scores_gemma":[0.0009102559,0.00021536194,0.000097179254,0.0011658142,0.000039224127,0.0014519964,0.0024385548,0.00025861492,0.0022815913],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001662619,0.0012901827,0.00007610263,0.00066154776,0.00070702744,0.00035439726,0.002272973,0.0037555925,0.010258651,0.108409725,0.31392208,0.5581255],"study_design_scores_gemma":[0.0004644892,0.00039675867,0.00011029047,0.000036141115,0.00003908201,0.000014894244,0.00003467469,0.040657856,0.002202882,0.0003369639,0.9554032,0.00030275367],"about_ca_topic_score_codex":0.000004861518,"about_ca_topic_score_gemma":2.6252428e-7,"teacher_disagreement_score":0.9330344,"about_ca_system_score_codex":0.0001709199,"about_ca_system_score_gemma":0.000008496281,"threshold_uncertainty_score":0.9996744},"labels":[],"label_agreement":null},{"id":"W6986709931","doi":"","title":"Raison et sentiment : nationalisme et antinationalisme dans le Québec des années 1935-1939","year":2001,"lang":"fr","type":"other","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Context (archaeology); Perspective (graphical); Government (linguistics)","score_opus":0.009681276199352716,"score_gpt":0.2072358239816379,"score_spread":0.19755454778228518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986709931","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015376088,0.02029994,0.5018856,0.009816356,0.0005907396,0.00065241015,0.000119506665,0.0007253034,0.45053408],"genre_scores_gemma":[0.19532931,0.001626105,0.06300506,0.0010257954,0.00028518456,0.00006582513,0.0003158235,0.00015113829,0.7381958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954473,0.00056246767,0.0006582427,0.0012783947,0.0013755453,0.00067808625],"domain_scores_gemma":[0.9969674,0.00029051478,0.0008048506,0.0008654816,0.00068394234,0.00038780615],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00058817,0.00077146525,0.0006663127,0.00079785933,0.0066326046,0.0002788829,0.0014118345,0.00049371226,0.0005810599],"category_scores_gemma":[0.000134546,0.00091877574,0.0005661879,0.0009919145,0.0012840668,0.0016811633,0.0009244659,0.0005806222,0.00016927124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000045650704,0.0006421548,0.0120531125,0.000077002165,0.00056812464,0.0018156515,0.01823001,0.007129494,0.00578901,0.9409493,0.0044689504,0.008231535],"study_design_scores_gemma":[0.001119826,0.00010681828,0.03309487,0.00050941086,0.00027375593,0.0017218414,0.0026965584,0.010857106,0.005736618,0.008872734,0.9337338,0.0012766562],"about_ca_topic_score_codex":0.32558292,"about_ca_topic_score_gemma":0.22224434,"teacher_disagreement_score":0.9320766,"about_ca_system_score_codex":0.009099948,"about_ca_system_score_gemma":0.0059842793,"threshold_uncertainty_score":0.9996509},"labels":[],"label_agreement":null},{"id":"W7027413287","doi":"","title":"Chlorine dioxide as a potable water disinfectant : application, residuals, and by-products monitoring","year":2010,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Chlorine dioxide; Potassium permanganate; Chlorite; Chlorine; Diethanolamine; Triethanolamine; Chloramine; Permanganate; Trihalomethane; Disinfectant","score_opus":0.006066921726660929,"score_gpt":0.21328831197699288,"score_spread":0.20722139025033195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027413287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444398,0.00040077357,0.051463302,0.0011685847,0.00024978613,0.00042057037,0.0000074862055,0.00037496747,0.0014747102],"genre_scores_gemma":[0.9427529,0.00091342593,0.049206093,0.000014353157,0.00014857127,0.0000052647288,0.00024833938,0.000050003135,0.006661036],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99842066,0.000033281554,0.00014304262,0.0007254569,0.00037911773,0.0002984332],"domain_scores_gemma":[0.99837804,0.00003149274,0.00027012185,0.0009014384,0.00032004731,0.00009888574],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020264395,0.00026816528,0.00039514905,0.00027334082,0.00029441266,0.000063945336,0.0009589507,0.0002384434,0.0000027919807],"category_scores_gemma":[0.000032763895,0.00029172117,0.00007479369,0.00035358052,0.00007035156,0.0007148025,0.00033767958,0.0003809451,0.000029454102],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085454296,0.00019455292,0.011998276,0.00040836004,0.00021789985,0.00004995855,0.0017952905,0.000012142905,0.9602338,0.0044286437,0.0030572433,0.017518362],"study_design_scores_gemma":[0.00042961678,0.00013298026,0.03818406,0.00016376087,0.00020363276,0.000012217955,0.0036092685,0.0002711825,0.9237058,0.0053114844,0.027106991,0.0008689835],"about_ca_topic_score_codex":0.002383067,"about_ca_topic_score_gemma":0.023321398,"teacher_disagreement_score":0.036528,"about_ca_system_score_codex":0.00007005869,"about_ca_system_score_gemma":0.0000474988,"threshold_uncertainty_score":0.9999535},"labels":[],"label_agreement":null},{"id":"W7036213512","doi":"","title":"Best available scientific information on the effects of deposition of heavy metals from long-range atmospheric transport","year":2006,"lang":"en","type":"other","venue":"NERC Open Research Archive (Natural Environment Research Council)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Deposition (geology); Heavy metals; Air pollution; Atmosphere (unit); Pollution","score_opus":0.0505802275379201,"score_gpt":0.30473740211399536,"score_spread":0.25415717457607523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036213512","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059567373,0.012699324,0.15298577,0.0012827627,0.00053818914,0.021030087,0.0010044608,0.00032099313,0.8041817],"genre_scores_gemma":[0.16308805,0.010764967,0.16126686,0.00017013976,0.0004056439,0.003869604,0.0019765543,0.0006850329,0.65777314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9814067,0.0021701627,0.0008301292,0.0013459577,0.013027409,0.0012196423],"domain_scores_gemma":[0.992224,0.0026781699,0.000500968,0.0034163308,0.0009459753,0.0002345873],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.011563132,0.0004942705,0.0008500299,0.00052698294,0.00066038396,0.000615124,0.006641552,0.000262827,0.0006245755],"category_scores_gemma":[0.0011423437,0.00035211694,0.00029029566,0.0017935757,0.0024879458,0.0013725847,0.0025076994,0.002176295,0.00067476026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004495687,0.001390543,0.00030758005,0.0008887422,0.0005670452,0.000110292494,0.0008422519,0.00023080377,0.0284622,0.008406636,0.92682284,0.0315215],"study_design_scores_gemma":[0.0020680306,0.0031182852,0.002811332,0.003939868,0.00013387656,0.000005886312,0.0001356106,0.012870493,0.064712256,0.016961042,0.8919039,0.00133943],"about_ca_topic_score_codex":0.019895481,"about_ca_topic_score_gemma":0.003564708,"teacher_disagreement_score":0.15713131,"about_ca_system_score_codex":0.0017018898,"about_ca_system_score_gemma":0.0012310897,"threshold_uncertainty_score":0.99989307},"labels":[],"label_agreement":null},{"id":"W7096651494","doi":"","title":"Published by Canadian Center of Science and Education 191 Testing the Accuracy of Text Deconstruction Using PTree Tool","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Correctness; Parsing; Deconstruction (building); Java; Relation (database); Flexibility (engineering); Parse tree; Tree (set theory)","score_opus":0.03378848661564744,"score_gpt":0.29689182451678287,"score_spread":0.26310333790113544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096651494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7432823,0.000076543176,0.24660075,0.00087739323,0.00017212423,0.00024082101,0.0000023975215,0.00006183796,0.008685837],"genre_scores_gemma":[0.78395677,0.0000010528616,0.21590984,0.000098028584,0.000008813386,0.000002312159,5.099246e-7,0.000002101354,0.000020593003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911803,0.000023556831,0.00021623378,0.00021497409,0.00027020377,0.00015701953],"domain_scores_gemma":[0.99831545,0.000086685235,0.00019711458,0.00039465041,0.00089989934,0.00010619622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000686005,0.00006318798,0.00009234805,0.00026913141,0.00012346794,0.00014836241,0.0005972618,0.000021301714,0.0000034063655],"category_scores_gemma":[0.0016946717,0.0000461715,0.000013252046,0.0012985579,0.0003823765,0.0021132445,0.00014707868,0.000051591076,3.034253e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018424689,0.00005868979,0.070387274,0.000012873573,0.000010740914,2.3574843e-7,0.00078177353,0.000062570914,0.05275698,0.023123465,0.003866909,0.8489366],"study_design_scores_gemma":[0.0008800448,0.00021369528,0.035287034,0.00023556138,0.00006353817,0.00027994433,0.002996683,0.5442175,0.33416513,0.07434027,0.0063577783,0.0009627697],"about_ca_topic_score_codex":0.030090416,"about_ca_topic_score_gemma":0.004252011,"teacher_disagreement_score":0.8479739,"about_ca_system_score_codex":0.000161191,"about_ca_system_score_gemma":0.001534795,"threshold_uncertainty_score":0.9763683},"labels":[],"label_agreement":null},{"id":"W7098708152","doi":"","title":"REDUCED POWER AT TAKE-OFF AND COLLISION WITH TERRAIN","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Terrain; Collision; Function (biology); Power (physics); Fault (geology); Aviation","score_opus":0.00579598134202386,"score_gpt":0.2401106088972919,"score_spread":0.23431462755526805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098708152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29106343,0.00005695164,0.7004028,0.0012545388,0.0000145993135,0.00010866913,2.5465468e-7,0.0003557656,0.006743027],"genre_scores_gemma":[0.66891557,0.0000111573745,0.32984582,0.00026849183,0.0000047727344,0.000006049229,5.845454e-7,0.0000052792825,0.00094228215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99919355,0.000012841483,0.00011168329,0.00033552008,0.000185503,0.00016089415],"domain_scores_gemma":[0.9993855,0.000018365545,0.00004772128,0.00043150774,0.000043994107,0.000072955976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009246228,0.00010459223,0.000120858655,0.000081632315,0.00009533159,0.000062648236,0.000288216,0.00003589182,0.000016655958],"category_scores_gemma":[0.0000115216935,0.00007250203,0.000022791693,0.00031331606,0.000054330758,0.0004013381,0.00022157557,0.00005363886,0.00001599085],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001528809,0.00058995787,0.0030205753,0.00002538863,0.00018741698,0.00039674173,0.00916755,0.0022762457,0.31005216,0.5196377,0.009482344,0.14501102],"study_design_scores_gemma":[0.0027424158,0.0015790105,0.0101118395,0.00015229704,0.0000352073,0.0003728169,0.00021787084,0.0061634565,0.86646134,0.076669894,0.03406209,0.001431788],"about_ca_topic_score_codex":0.000020653315,"about_ca_topic_score_gemma":0.00007792757,"teacher_disagreement_score":0.5564091,"about_ca_system_score_codex":0.000082034145,"about_ca_system_score_gemma":0.000024893332,"threshold_uncertainty_score":0.2956547},"labels":[],"label_agreement":null},{"id":"W7100179867","doi":"","title":"Text Processing","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Relevance (law); Key (lock); Focus (optics); Ranking (information retrieval); Work (physics); Quarter (Canadian coin); Recommender system","score_opus":0.010890496970892501,"score_gpt":0.27193809495669846,"score_spread":0.26104759798580596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100179867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034418865,0.000024593877,0.9745873,0.0016038934,0.0000102154,0.000022118546,3.379669e-8,0.00067740056,0.02273024],"genre_scores_gemma":[0.63017017,0.0000040856994,0.366266,0.00019054872,0.00001149041,0.000003962274,1.9278533e-8,0.000002305811,0.0033514274],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995289,0.0000073513165,0.0000763625,0.00017387749,0.00009941894,0.00011407522],"domain_scores_gemma":[0.9995902,0.000021437669,0.000028078974,0.0002899223,0.000040252307,0.00003009183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006518345,0.000046298053,0.000053672084,0.000051783725,0.000035129167,0.00003855978,0.00044541026,0.000015707321,0.00003920239],"category_scores_gemma":[0.000018772009,0.000024234685,0.00002357398,0.00020356484,0.000019587704,0.00069876655,0.000116879375,0.000016092466,0.00013122211],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4763106e-7,0.00000559134,0.0001535054,6.284218e-7,0.0000010702533,0.0000011657276,0.0000137821835,1.2821725e-7,0.01143379,0.07582393,0.0006083479,0.9119579],"study_design_scores_gemma":[0.00032021105,0.00006925386,0.0019237082,0.00007612799,0.0000059525723,0.000020054336,0.000010251507,0.011686951,0.53635454,0.34357694,0.105420664,0.000535359],"about_ca_topic_score_codex":0.0000012857961,"about_ca_topic_score_gemma":0.0000020459245,"teacher_disagreement_score":0.91142255,"about_ca_system_score_codex":0.000018348255,"about_ca_system_score_gemma":0.000014793218,"threshold_uncertainty_score":0.16866386},"labels":[],"label_agreement":null},{"id":"W7100658452","doi":"","title":"Adaptation of a Keyphrase Extractor for Japanese","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Extractor; Software; Adaptation (eye); Selection (genetic algorithm); Information extraction; Matching (statistics)","score_opus":0.026469365737060692,"score_gpt":0.315559452077982,"score_spread":0.28909008634092126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100658452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022619162,0.000029135817,0.9758156,0.00003898534,0.000022252338,0.00013805054,5.427061e-7,0.00016677911,0.001169524],"genre_scores_gemma":[0.5523354,0.0000013541171,0.4474566,0.000026551363,0.000008198817,0.0000053824892,9.12608e-7,0.0000022602424,0.00016337502],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994062,0.000008122461,0.00019155584,0.00015098661,0.00012165872,0.000121440266],"domain_scores_gemma":[0.999246,0.0002280533,0.00008628498,0.0002781469,0.00012539042,0.00003613904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042266442,0.00005471006,0.00009686054,0.000109722925,0.000021218873,0.000011164036,0.00028599572,0.000029450326,0.000007589584],"category_scores_gemma":[0.00007386092,0.00004708473,0.0000632782,0.00024702295,0.000016316404,0.00034488417,0.00003414897,0.000024609051,0.0000028776642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005570345,0.000252729,0.00041728918,0.000050392537,0.000034965473,0.0000064247615,0.0018479599,0.00024726833,0.1291317,0.39139873,0.00041421578,0.47614262],"study_design_scores_gemma":[0.00080652663,0.00040635394,0.0045208754,0.000031606556,0.000026772854,0.000008756383,0.00061532116,0.25029653,0.68648547,0.047658436,0.00869449,0.0004488685],"about_ca_topic_score_codex":0.000037405713,"about_ca_topic_score_gemma":0.00006387597,"teacher_disagreement_score":0.55735373,"about_ca_system_score_codex":0.000017246397,"about_ca_system_score_gemma":0.000013726961,"threshold_uncertainty_score":0.19200595},"labels":[],"label_agreement":null},{"id":"W7120589744","doi":"","title":"Análise visual de tópicos no Twitter em conexão com debates políticos","year":2017,"lang":"en","type":"dissertation","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Social media; Government (linguistics); Set (abstract data type); Parliament; Dissemination; Cluster analysis; Topic model; Politics","score_opus":0.019344523219971974,"score_gpt":0.2897597519075543,"score_spread":0.27041522868758233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7120589744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09556533,0.0038962306,0.46454412,0.020700637,0.0101972325,0.0054580187,0.00023358823,0.008809328,0.39059553],"genre_scores_gemma":[0.96925724,0.00028950625,0.021972802,0.00044756822,0.00083572796,0.0005775409,0.0010060823,0.00015573305,0.0054578246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99340117,0.0005119309,0.0012953947,0.0018549493,0.0015065428,0.0014299956],"domain_scores_gemma":[0.99351496,0.00034626975,0.0016638053,0.0022411789,0.0014310238,0.000802779],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00083381665,0.0011790897,0.0012796461,0.0010988109,0.0015459058,0.0016489013,0.0038388076,0.0014813805,0.00007832557],"category_scores_gemma":[0.0011498657,0.0011963253,0.00068274,0.0007072999,0.000041337415,0.0016688048,0.0005114991,0.001616834,0.00009884628],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005453237,0.0019457884,0.0006245579,0.0006408104,0.0011187396,0.0013056636,0.0062362286,0.00007848169,0.01929818,0.92452306,0.011178902,0.03250427],"study_design_scores_gemma":[0.0013592589,0.0002234103,0.0039399457,0.00072475435,0.00032552323,0.0007655322,0.00039931445,0.007885125,0.015558367,0.0039948067,0.9627274,0.0020965359],"about_ca_topic_score_codex":0.000005233603,"about_ca_topic_score_gemma":0.0003683327,"teacher_disagreement_score":0.9515485,"about_ca_system_score_codex":0.001255814,"about_ca_system_score_gemma":0.0014919351,"threshold_uncertainty_score":0.9998149},"labels":[],"label_agreement":null},{"id":"W7130592618","doi":"10.1109/fllm67465.2025.11391003","title":"Automated Research Article Classification and Recommendation Using NLP and Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; York University","funders":"","keywords":"Cosine similarity; Support vector machine; Random forest; Information overload; Complement (music); Statistical classification; Feature extraction; Feature (linguistics)","score_opus":0.1414599886026211,"score_gpt":0.44178727865896866,"score_spread":0.30032729005634756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130592618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12534738,0.00054544397,0.8662752,0.0044346466,0.00005135367,0.0003109024,7.427864e-7,0.00075288257,0.0022814507],"genre_scores_gemma":[0.8878155,0.00058579486,0.11059231,0.000099814875,0.000013878413,0.0000098138935,0.0000054115662,0.000009772244,0.00086773466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733126,0.000735495,0.000480629,0.00077545847,0.00026737538,0.00040976456],"domain_scores_gemma":[0.99855614,0.0003968174,0.00014543587,0.00039189673,0.0004046198,0.00010511842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023794873,0.00017791081,0.00024050023,0.0007467402,0.000955042,0.0006822697,0.00025878762,0.00013459049,0.00005311682],"category_scores_gemma":[0.00043466996,0.00018212743,0.000028984621,0.0022831738,0.00025728298,0.0011187322,0.0007597211,0.0005482919,0.000007048296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024333493,0.00012592123,0.026049584,0.00007711286,0.00006766933,0.0000024910448,0.0006836627,0.0002106978,0.09168,0.051751968,0.00029776862,0.8290288],"study_design_scores_gemma":[0.0002377077,0.00007265382,0.011735723,0.000081349295,0.000027589851,0.0000052372575,0.00019999374,0.9686329,0.010793041,0.0065779337,0.0014779826,0.00015788537],"about_ca_topic_score_codex":0.00027594058,"about_ca_topic_score_gemma":0.00006549495,"teacher_disagreement_score":0.96842223,"about_ca_system_score_codex":0.0001920935,"about_ca_system_score_gemma":0.00009321614,"threshold_uncertainty_score":0.74269414},"labels":[],"label_agreement":null},{"id":"W7147479603","doi":"10.1109/icaft66710.2025.11452853","title":"Unsupervised Key-Value Pair selection on Enterprise Documents through Generative type Transformer Framework","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generative grammar; Transformer; Unsupervised learning; Automation; Generative model; Generalization","score_opus":0.014170597863199184,"score_gpt":0.3244799686035344,"score_spread":0.3103093707403352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7147479603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039186105,0.0005768495,0.9591161,0.0042791497,0.0010257817,0.00095371157,0.0000036410172,0.0007247095,0.02940145],"genre_scores_gemma":[0.5380042,0.0011521792,0.4413683,0.008839259,0.00014802818,0.00009189223,0.000009311735,0.000039994284,0.010346831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9952361,0.00046154676,0.0009861757,0.001649547,0.00079603074,0.00087062217],"domain_scores_gemma":[0.9976439,0.00028724672,0.00021239682,0.0011977887,0.0005038362,0.00015486356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039312252,0.0007675163,0.00076004205,0.0004753331,0.00071382313,0.0005302727,0.0013798887,0.00052117236,0.00077897456],"category_scores_gemma":[0.0001413315,0.0007045475,0.00044040286,0.00430753,0.00017723923,0.0019201295,0.00019398727,0.0009714093,0.00025948725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037298715,0.0012968207,0.0016561655,0.00009215813,0.0010819118,0.000016234117,0.006626955,0.0034561255,0.005815984,0.832734,0.011959646,0.13489102],"study_design_scores_gemma":[0.0011362577,0.0017392267,0.0003669318,0.00092910364,0.00035174968,0.000004329956,0.0002337064,0.18769024,0.42313072,0.3331638,0.049912833,0.0013410989],"about_ca_topic_score_codex":0.00016278028,"about_ca_topic_score_gemma":0.000042957246,"teacher_disagreement_score":0.5340856,"about_ca_system_score_codex":0.0006328365,"about_ca_system_score_gemma":0.00041614968,"threshold_uncertainty_score":0.99954057},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01541633088549207,"score_gpt":0.2851988313401981,"score_spread":0.26978250045470603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W81794110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002339268,0.00013582889,0.9950093,0.0014372047,0.00045059927,0.00023416146,0.0000044812427,0.000039055492,0.00035009623],"genre_scores_gemma":[0.9786858,0.00003436556,0.019778261,0.00006941454,0.000088509594,0.000022175102,0.0000017407158,0.000004203801,0.0013155133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885976,0.000045887824,0.00060677866,0.000050917715,0.00032803227,0.00010860824],"domain_scores_gemma":[0.9969102,0.00014656823,0.0019867104,0.000104858445,0.0008209301,0.000030727937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012025529,0.00007787719,0.00019346157,0.0002281673,0.00014639106,0.00029086694,0.00037310703,0.00006147919,2.441534e-7],"category_scores_gemma":[0.00041406302,0.00005251212,0.00013825757,0.00024848373,0.0000089635305,0.0023555895,0.000057054585,0.00010523121,0.0000017842418],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019255733,0.00012484692,0.006310654,0.00019085198,0.0012146275,2.921027e-7,0.035891503,0.1747512,0.00046951967,0.65255207,0.019738749,0.10856311],"study_design_scores_gemma":[0.0029269496,0.0013675307,0.0030715866,0.00043638775,0.0001816322,0.000051484818,0.005451752,0.055437885,0.020675022,0.020051701,0.8898531,0.00049496774],"about_ca_topic_score_codex":0.000008474117,"about_ca_topic_score_gemma":0.0000025308996,"teacher_disagreement_score":0.97634655,"about_ca_system_score_codex":0.00042341792,"about_ca_system_score_gemma":0.000030402596,"threshold_uncertainty_score":0.28048366},"labels":[],"label_agreement":null},{"id":"W86593375","doi":"10.4018/978-1-60566-058-5.ch020","title":"Theories of Meaning in Schema Matching","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Schema matching; Schema (genetic algorithms); Matching (statistics); Conceptual schema; Computer science; Epistemology; Schema migration; Information retrieval; Database schema; Psychology; Data mining; Data integration; Semi-structured model; Social psychology; Gender schema theory; Mathematics; Philosophy; Database design","score_opus":0.012164443046926097,"score_gpt":0.2655339347594541,"score_spread":0.253369491712528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W86593375","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032763935,0.00020736252,0.1696646,0.000031035517,0.00004429319,0.00012644955,0.0000044657536,0.00025429565,0.8296347],"genre_scores_gemma":[0.6981322,0.000014782147,0.2746864,0.00038331762,0.00010853112,0.00000953809,0.0000017035001,0.000041782023,0.026621774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982461,0.000021266862,0.0005292157,0.00051071076,0.00042074567,0.00027197614],"domain_scores_gemma":[0.998561,0.000048285554,0.00039108345,0.0008416265,0.00009861859,0.00005934361],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023531535,0.00034254286,0.00061113643,0.00018116782,0.00004140782,0.00006488456,0.0011570607,0.00025376584,0.000004495439],"category_scores_gemma":[0.000020862202,0.00034256175,0.00020456563,0.000058531783,0.00008751551,0.0001775281,0.00039928107,0.0003059316,0.000012711477],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004035517,0.00000465778,0.0000048383367,0.0000123833115,0.00002214066,0.00004169866,0.00014207404,0.000014102042,0.000087574765,0.9441419,0.00002042968,0.05550415],"study_design_scores_gemma":[0.00010644968,0.000042508396,0.000007671514,0.0003570376,0.000015576348,0.0000149380385,0.000005895029,0.00008019131,0.0012301081,0.9964615,0.0013868122,0.00029127643],"about_ca_topic_score_codex":0.000044367942,"about_ca_topic_score_gemma":0.000108128916,"teacher_disagreement_score":0.80301297,"about_ca_system_score_codex":0.0001971071,"about_ca_system_score_gemma":0.0000969201,"threshold_uncertainty_score":0.99990267},"labels":[],"label_agreement":null},{"id":"W86784885","doi":"10.48009/2_iis_2005_296-302","title":"DO YOU HEAR WHAT I HEAR? ADVANCES IN WEB-BASED PERCEPTUAL TESTING AND TRAINING","year":2005,"lang":"en","type":"article","venue":"Issues in Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Perception; Training (meteorology); Psychology; Computer science; Cognitive psychology; Neuroscience; Geography","score_opus":0.027014595235242994,"score_gpt":0.3105845741142363,"score_spread":0.28356997887899327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W86784885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3353268,0.029286187,0.6112202,0.00352288,0.0009334199,0.0022148734,0.000008895918,0.0023009882,0.015185784],"genre_scores_gemma":[0.916685,0.000263589,0.082750306,0.00017084062,0.00004829879,0.000057044796,0.0000033634803,0.000005479809,0.000016104183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848336,0.00008550686,0.0006313495,0.00019683236,0.0003402899,0.0002626384],"domain_scores_gemma":[0.9991432,0.00018668921,0.00020712285,0.000309379,0.00010002135,0.000053614327],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088478386,0.00015000107,0.00027859374,0.000554447,0.00006926646,0.0006925311,0.00033788552,0.00007607305,0.0000032942885],"category_scores_gemma":[0.00019154817,0.00014624473,0.000024952025,0.0007719154,0.000048631646,0.014557093,0.00007873412,0.0001613556,0.000028592915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007708734,0.00002538772,0.006911407,0.00012795403,0.0000041066783,0.0000044138496,0.040629208,0.07143183,0.00015320368,0.006716312,0.00008919038,0.8738993],"study_design_scores_gemma":[0.00061504036,0.00007354657,0.0010396525,0.00082376885,0.0000019494978,0.000023706605,0.011662192,0.895632,0.00017612164,0.0002680876,0.08935919,0.00032471155],"about_ca_topic_score_codex":0.000050879855,"about_ca_topic_score_gemma":0.00005665505,"teacher_disagreement_score":0.87357455,"about_ca_system_score_codex":0.00013647889,"about_ca_system_score_gemma":0.00004507967,"threshold_uncertainty_score":0.9992258},"labels":[],"label_agreement":null},{"id":"W923756419","doi":"","title":"University of Waterloo at TREC 2014 Contextual Suggestion: Experiments with suggestion clustering","year":2014,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Point of interest; Task (project management); Point (geometry); Similarity (geometry); Cluster analysis; Information retrieval; World Wide Web; Special Interest Group; Artificial intelligence; Mathematics","score_opus":0.01781061543086193,"score_gpt":0.24038491729818853,"score_spread":0.2225743018673266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W923756419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26303977,0.000038117676,0.73461235,0.00016652484,0.000048892554,0.0001563924,0.0000025617278,0.0002773454,0.001658067],"genre_scores_gemma":[0.96947986,0.00002705749,0.028015839,0.00003211186,0.000019714229,0.000001014999,0.000009070095,0.000011158564,0.0024041461],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983216,0.000156059,0.00024599314,0.0005483609,0.0004311122,0.00029690244],"domain_scores_gemma":[0.9984159,0.0001187243,0.00026320375,0.00073556096,0.00033547185,0.00013112815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003266698,0.00022248544,0.00035823463,0.00013717994,0.0001730044,0.00005506869,0.0008748384,0.00010653495,0.00015825884],"category_scores_gemma":[0.000053468797,0.00020462816,0.00007064814,0.00034379077,0.00023197492,0.00043252896,0.00043671433,0.00015328657,0.0000785789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004294624,0.0009669009,0.032602195,0.00035660816,0.0005350962,0.00019204365,0.020991009,0.0023870585,0.47332367,0.12494903,0.004742731,0.334659],"study_design_scores_gemma":[0.0050357766,0.0035358048,0.025307402,0.0006443459,0.00017078845,0.00012629628,0.0007715307,0.32701156,0.6203047,0.002460223,0.012501664,0.0021299017],"about_ca_topic_score_codex":0.00020604781,"about_ca_topic_score_gemma":0.00022738003,"teacher_disagreement_score":0.7065965,"about_ca_system_score_codex":0.00014771103,"about_ca_system_score_gemma":0.000067148765,"threshold_uncertainty_score":0.8344494},"labels":[],"label_agreement":null},{"id":"W9417692","doi":"10.1007/978-3-319-06483-3_22","title":"Combining Textual Pre-game Reports and Statistical Data for Predicting Success in the National Hockey League","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bigram; Trigram; Computer science; League; Classifier (UML); Artificial intelligence; Machine learning; Natural language processing; Data mining","score_opus":0.03321151851607614,"score_gpt":0.3239491014298272,"score_spread":0.29073758291375107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9417692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016198344,0.0001212411,0.99778646,0.00050627923,0.00023479083,0.00058242935,0.000032942335,0.00012215831,0.00045170842],"genre_scores_gemma":[0.5310388,0.000009788749,0.46772218,0.00086102716,0.00024036312,0.000025198837,0.000056521327,0.000018301855,0.000027811479],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546355,0.000077918274,0.0007700944,0.001891245,0.0012872219,0.0005099873],"domain_scores_gemma":[0.99438375,0.003178279,0.0004861257,0.0015877024,0.00027557366,0.00008855447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040036887,0.00038891597,0.0005152494,0.00057182397,0.0002506949,0.0006787469,0.00414134,0.00021190886,0.0000022754882],"category_scores_gemma":[0.0013352222,0.00030777033,0.00004871008,0.0004411184,0.0007250454,0.0008212043,0.0023543243,0.00075613294,8.24052e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019298053,0.00008138977,0.0033090645,0.00013892434,0.00003788868,0.0001899343,0.0023133915,0.025607461,0.00007248724,0.22275916,0.0003137091,0.7451573],"study_design_scores_gemma":[0.00014986467,0.000116525334,0.00082437636,0.00020019196,0.000010329453,0.00015817382,4.049352e-7,0.7578703,0.000056436747,0.23935297,0.0009236997,0.00033669182],"about_ca_topic_score_codex":0.00004594671,"about_ca_topic_score_gemma":0.00031720236,"teacher_disagreement_score":0.7448206,"about_ca_system_score_codex":0.0001486087,"about_ca_system_score_gemma":0.00035328532,"threshold_uncertainty_score":0.9999374},"labels":[],"label_agreement":null},{"id":"W98088564","doi":"10.29173/cais472","title":"Team Co-occurence in Internet Search Engine Queries: An Analysis of the Excite Data Set","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Computer science; Search engine; Term (time); Zipf's law; The Internet; Information retrieval; Data set; Data mining; Distribution (mathematics); Statistics; World Wide Web; Mathematics; Artificial intelligence; Physics","score_opus":0.04172340190283944,"score_gpt":0.30678274582578985,"score_spread":0.2650593439229504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98088564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987843,0.000058328198,0.009414001,0.0008481209,0.00003966189,0.0004540685,0.00020239703,0.00007246665,0.0010679753],"genre_scores_gemma":[0.9923613,0.000064202985,0.0071878703,0.00012165314,0.000018654398,0.000032077645,0.000019167117,0.000014791422,0.0001802552],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971997,0.00007987789,0.0008152427,0.00066398445,0.000788003,0.00045318744],"domain_scores_gemma":[0.97970396,0.00021390151,0.0009183678,0.00134351,0.017694864,0.00012536856],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011931869,0.00030457828,0.000778582,0.0005842141,0.000069008616,0.0014363804,0.010762711,0.0001427415,0.000036676476],"category_scores_gemma":[0.0059689004,0.00020715222,0.00021318007,0.0026667763,0.00063736626,0.017621921,0.0032192976,0.00042147608,0.0000016610672],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058068734,0.00043546202,0.8502474,0.00028064064,0.0007523241,0.0000011753559,0.061188187,0.00020628823,0.033338062,0.031345896,0.0031213001,0.019025208],"study_design_scores_gemma":[0.0005327486,0.0004263399,0.5075501,0.00050169276,0.00045011315,0.000013669934,0.0040132315,0.3277034,0.14420165,0.0075471234,0.006309176,0.00075074594],"about_ca_topic_score_codex":0.002020921,"about_ca_topic_score_gemma":0.00019710798,"teacher_disagreement_score":0.34269726,"about_ca_system_score_codex":0.0000716302,"about_ca_system_score_gemma":0.00022092497,"threshold_uncertainty_score":0.99960023},"labels":[],"label_agreement":null}]}