{"meta":{"query_hash":"66b9019c05d7","filters":{"venue":"Computational Linguistics"},"cohort_total":61,"direct_labels_cover":0,"predictions_cover":61,"exported":61,"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/66b9019c05d7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computational+Linguistics"},"results":[{"id":"W117485591","doi":"10.1162/coli.2004.30.1.107","title":"Book Review","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"","field":"","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","funders":"","keywords":"Computer science","score_opus":0.021598479154666134,"score_gpt":0.3148972048835334,"score_spread":0.2932987257288673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W117485591","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055786164,0.25105265,0.003417157,0.061384246,0.05969365,0.00015172733,0.0017465885,0.00093312404,0.62106293],"genre_scores_gemma":[0.0017098582,0.06814925,0.0009175711,0.00888394,0.009157655,0.000067390116,0.0009812454,0.00029213587,0.90984094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945825,0.00006457455,0.000019366898,0.00006952725,0.00033633193,0.00005193845],"domain_scores_gemma":[0.9977939,0.0005525414,0.0001090755,0.00015309246,0.0010510071,0.00034037227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000759406,0.0006337518,0.0008332442,0.004100085,0.0010561323,0.003427048,0.0013138033,0.0015493024,0.29022413],"category_scores_gemma":[0.0044513624,0.00032256966,0.00043459426,0.0045079156,0.00068406377,0.0025697385,0.0014462486,0.0020145597,0.23095591],"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":[0.0000055923356,0.0000061046403,0.000022722583,0.000114139846,0.0000015940343,0.000013834947,0.000009400558,0.000021731475,0.000036965073,0.001710917,0.9261311,0.07192583],"study_design_scores_gemma":[0.0000015340598,0.0000023134935,0.000050974675,0.00008505309,0.0000016450103,0.00002833407,0.000010271691,0.000010219086,0.000018722998,0.000512618,0.99927694,0.0000014271409],"about_ca_topic_score_codex":0.0034797285,"about_ca_topic_score_gemma":0.009108613,"teacher_disagreement_score":0.29022413,"about_ca_system_score_codex":0.0016703948,"about_ca_system_score_gemma":0.0030193212,"threshold_uncertainty_score":0.9708965},"labels":[],"label_agreement":null},{"id":"W1502796908","doi":"10.1162/coli.2002.28.4.560","title":"<i>Patterns of Text: In Honour of Michael Hoey</i> Mike Scott and Geoff Thompson (editors) (University of Liverpool) Amsterdam: John Benjamins, 2001, vii+323 pp; hardbound, ISBN 90-272-2572-9 and 1-55619-792-6, $100.00, € 110.00","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":13,"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; University of Pennsylvania","keywords":"Honour; Sociology; Media studies; Political science; Law","score_opus":0.029277488832886354,"score_gpt":0.21196384906464022,"score_spread":0.18268636023175386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502796908","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001684145,0.5540652,0.05853755,0.23020142,0.12778972,0.0001266526,0.0014239193,0.0012077775,0.024963543],"genre_scores_gemma":[0.016864663,0.5506685,0.07087468,0.036949772,0.15869166,0.00033131606,0.0047569918,0.0032634018,0.15759905],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997221,0.0009778745,0.0002805398,0.00056331477,0.0008492219,0.000108059154],"domain_scores_gemma":[0.9899616,0.0052455706,0.00051261997,0.0008167813,0.0026330291,0.0008303625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005373801,0.0022206318,0.0019033889,0.004931834,0.0016174136,0.008956538,0.0026509822,0.002234509,0.018289207],"category_scores_gemma":[0.010585446,0.0010276131,0.0010694055,0.007494085,0.005291115,0.023236746,0.0051737186,0.0035544746,0.018551685],"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":[0.000042200645,0.000010869716,0.00020492425,0.0006996752,0.000021854063,0.00007427692,0.0007370842,0.00013922568,0.00042046665,0.0055557787,0.80749357,0.18460016],"study_design_scores_gemma":[0.000007748016,0.000009592868,0.00032275415,0.00040655793,0.000014170121,0.00024595746,0.00059318583,0.00023081186,0.00022449637,0.008233084,0.9896932,0.000018355171],"about_ca_topic_score_codex":0.0064510475,"about_ca_topic_score_gemma":0.012834829,"teacher_disagreement_score":0.018289207,"about_ca_system_score_codex":0.0016257206,"about_ca_system_score_gemma":0.0021327618,"threshold_uncertainty_score":0.061183512},"labels":[],"label_agreement":null},{"id":"W1521465908","doi":"10.1162/089120101300346831","title":"Book Reviews","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.04113790453060918,"score_gpt":0.34483954249689,"score_spread":0.3037016379662808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521465908","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039872972,0.122251086,0.0020008658,0.011274223,0.018517716,0.00008476105,0.002066456,0.00081642787,0.8425897],"genre_scores_gemma":[0.0011471672,0.035357945,0.0011125364,0.0038435622,0.0037414124,0.000045569144,0.001637296,0.00026917493,0.9528454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994771,0.000043773773,0.000020751486,0.000085169486,0.00032672787,0.00004658703],"domain_scores_gemma":[0.9989611,0.00021048424,0.000056736546,0.00009302871,0.0004957977,0.00018296852],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005074873,0.00070812635,0.00077941024,0.0031467092,0.000801998,0.0037867434,0.0014296896,0.0014025425,0.44097692],"category_scores_gemma":[0.0022493643,0.00033125715,0.0005030032,0.0037538493,0.000536686,0.0025298162,0.0011480214,0.0017136405,0.42304608],"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":[0.000008630473,0.000014277553,0.000027365792,0.00016266207,0.000002224839,0.000017260194,0.00001943318,0.000031940806,0.0001082719,0.0036118901,0.89751846,0.09847755],"study_design_scores_gemma":[0.0000017599873,0.0000025112224,0.00006527056,0.00007123148,0.00000113546,0.000030068082,0.000011237958,0.000007660838,0.000017814835,0.00072358217,0.99906605,0.0000017437615],"about_ca_topic_score_codex":0.0026386546,"about_ca_topic_score_gemma":0.006597462,"teacher_disagreement_score":0.44097692,"about_ca_system_score_codex":0.0011596427,"about_ca_system_score_gemma":0.0015120719,"threshold_uncertainty_score":0.79737854},"labels":[],"label_agreement":null},{"id":"W1538392035","doi":"10.1162/coli.2003.29.3.507","title":"Book Review","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"","field":"","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","score_opus":0.024111771610737083,"score_gpt":0.3140361472330895,"score_spread":0.2899243756223524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538392035","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005735532,0.22453152,0.0034759026,0.054738846,0.053525615,0.00015846411,0.0016513743,0.00096502184,0.6603797],"genre_scores_gemma":[0.0015253167,0.054126117,0.000819212,0.0073692077,0.0072564464,0.000059763686,0.000831939,0.00025977698,0.92775226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994692,0.000062073945,0.000018557457,0.00006840056,0.00033215227,0.000049502978],"domain_scores_gemma":[0.99787664,0.00052465056,0.000106422034,0.00015511272,0.0010137439,0.00032334003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007433808,0.0006557263,0.0008778538,0.004101939,0.0011271954,0.0035390125,0.0013015084,0.001534525,0.29446024],"category_scores_gemma":[0.0042763096,0.00031746188,0.0004535963,0.004568199,0.0006709411,0.002603012,0.0014516348,0.001930701,0.2405877],"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":[0.000005683262,0.00000633657,0.00002405365,0.00011025579,0.0000015630281,0.000014403555,0.000010454663,0.000021434296,0.000036990983,0.0016967055,0.925099,0.07297317],"study_design_scores_gemma":[0.0000015317265,0.0000024049527,0.000053638058,0.00008232118,0.0000017384152,0.000028500383,0.000011418699,0.000010988882,0.00001907453,0.0005148419,0.99927205,0.0000014318413],"about_ca_topic_score_codex":0.0037537229,"about_ca_topic_score_gemma":0.009990189,"teacher_disagreement_score":0.29446024,"about_ca_system_score_codex":0.0016582601,"about_ca_system_score_gemma":0.0030985593,"threshold_uncertainty_score":0.9850676},"labels":[],"label_agreement":null},{"id":"W1894075015","doi":"10.1162/coli_a_00226","title":"CODRA: A Novel Discriminative Framework for Rhetorical Analysis","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":186,"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":"Parsing; Computer science; Natural language processing; Rhetorical question; Discriminative model; Artificial intelligence; Coherence (philosophical gambling strategy); Probabilistic logic; Parse tree; Classifier (UML); Linguistics; Margin (machine learning); Machine learning; Mathematics","score_opus":0.07786810095225595,"score_gpt":0.37519876686569953,"score_spread":0.2973306659134436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1894075015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003956604,0.0005497567,0.9885156,0.00028875857,0.000048191923,0.00011115683,0.00095971377,0.0038667172,0.00170348],"genre_scores_gemma":[0.17848986,0.00051393866,0.80902547,0.00040364754,0.00029711658,0.0005195447,0.0054091667,0.0012945102,0.004046726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633443,0.0014186562,0.00019468025,0.0011136064,0.00071882,0.0002197965],"domain_scores_gemma":[0.99228066,0.0043906807,0.00075755664,0.0014392374,0.00086086476,0.0002709751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043811863,0.0017611989,0.0015589945,0.0069141574,0.0017376158,0.0028412247,0.0038734989,0.0021213496,0.005917545],"category_scores_gemma":[0.012827323,0.001136831,0.0017011046,0.004333582,0.0022253226,0.004854862,0.0033675919,0.003643182,0.0033482776],"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":[0.0002632594,0.0002956001,0.0052366294,0.00076266774,0.00020144435,0.00035136068,0.0009168882,0.046637055,0.015375774,0.17852832,0.026256088,0.72517484],"study_design_scores_gemma":[0.00004108062,0.00006886266,0.0020230599,0.00007312797,0.000059912683,0.0004856064,0.00013740738,0.77746105,0.005572089,0.18205494,0.03194838,0.00007450148],"about_ca_topic_score_codex":0.0066156816,"about_ca_topic_score_gemma":0.013948265,"teacher_disagreement_score":0.0069141574,"about_ca_system_score_codex":0.0016078675,"about_ca_system_score_gemma":0.0028933615,"threshold_uncertainty_score":0.023170173},"labels":[],"label_agreement":null},{"id":"W1978620866","doi":"10.1162/coli.2008.34.2.145","title":"Semantic Role Labeling: An Introduction to the Special Issue","year":2008,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Field (mathematics); Computational linguistics; Identification (biology); Computational model; Semantic role labeling; Artificial intelligence; Natural language processing; Data science; Key (lock); Semantics (computer science)","score_opus":0.01392567728635698,"score_gpt":0.2788210233112759,"score_spread":0.26489534602491893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978620866","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015131038,0.11140237,0.120702736,0.108761564,0.5509495,0.0004921966,0.0014128347,0.001771003,0.10299473],"genre_scores_gemma":[0.010033012,0.12064396,0.057750743,0.033648025,0.63264966,0.00077625725,0.0036780136,0.0025266209,0.13829371],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981395,0.0005108117,0.00027643688,0.00042751266,0.0005210843,0.00012472138],"domain_scores_gemma":[0.99050444,0.0058010416,0.00046382844,0.00069468585,0.0017388973,0.00079713826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038175555,0.0016167276,0.0018372805,0.0046720714,0.0027734505,0.0077905147,0.0019890477,0.0041521583,0.032827985],"category_scores_gemma":[0.010496428,0.0010864943,0.001887413,0.0035957475,0.0031203895,0.013293463,0.0034175601,0.010047957,0.02249422],"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":[0.000027138987,0.000067600915,0.0001974107,0.00031080144,0.00001582576,0.00009813481,0.0001373242,0.00025420735,0.0004874906,0.022256937,0.8864222,0.08972489],"study_design_scores_gemma":[0.0000039369434,0.000024682844,0.0002786157,0.00026180365,0.000009207161,0.00035328724,0.0000995176,0.00039428822,0.00012993996,0.014843602,0.98358303,0.000018096058],"about_ca_topic_score_codex":0.0010502697,"about_ca_topic_score_gemma":0.001758201,"teacher_disagreement_score":0.032827985,"about_ca_system_score_codex":0.0020239237,"about_ca_system_score_gemma":0.002021655,"threshold_uncertainty_score":0.109820485},"labels":[],"label_agreement":null},{"id":"W2017292107","doi":"10.1162/coli_a_00143","title":"Computing Lexical Contrast","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":100,"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; National Research Council Canada","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Contrast (vision); Computer science; Natural language processing; Artificial intelligence; Word (group theory); Meaning (existential); Focus (optics); Linguistics; Information retrieval; Psychology; Philosophy","score_opus":0.020473053507219972,"score_gpt":0.3092489102287959,"score_spread":0.28877585672157596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017292107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6477583,0.0025458706,0.2844786,0.00091863895,0.000525663,0.00060965854,0.012439431,0.0033634074,0.04736044],"genre_scores_gemma":[0.8689468,0.00030246607,0.11663323,0.00018647958,0.00015153557,0.00036002582,0.011235234,0.0002736791,0.0019105489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952253,0.00074719236,0.00068535237,0.0016975742,0.0012604741,0.0003840722],"domain_scores_gemma":[0.9888359,0.0067430777,0.0007787124,0.0010893891,0.002070561,0.00048241916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023437354,0.00090478634,0.0014648095,0.011683117,0.0016506898,0.004957482,0.0011349526,0.0015334842,0.008647076],"category_scores_gemma":[0.024712952,0.000533111,0.0010112422,0.006615039,0.0011194934,0.008883035,0.0032862942,0.0011340771,0.0026129358],"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":[0.0027019903,0.0006660275,0.160423,0.0017754966,0.0007319567,0.0016989597,0.002535648,0.013450382,0.0489909,0.08746205,0.023318775,0.6562448],"study_design_scores_gemma":[0.0005158137,0.0014900909,0.1436443,0.0004652763,0.000872473,0.0050581284,0.0063725873,0.28215855,0.049055215,0.41531098,0.094644524,0.00041216676],"about_ca_topic_score_codex":0.0014944297,"about_ca_topic_score_gemma":0.0017379217,"teacher_disagreement_score":0.011683117,"about_ca_system_score_codex":0.0012138683,"about_ca_system_score_gemma":0.0010387083,"threshold_uncertainty_score":0.028927386},"labels":[],"label_agreement":null},{"id":"W2046436395","doi":"10.1162/089120100561755","title":"The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach","year":2000,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":221,"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":"Rhetorical question; Computer science; Automatic summarization; Parsing; Natural language processing; Artificial intelligence; Linguistics; Context (archaeology); Natural language understanding; Natural language; Philosophy; History","score_opus":0.020461250025670744,"score_gpt":0.28202723553398357,"score_spread":0.26156598550831284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046436395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013765123,0.00039678995,0.98039573,0.00040418204,0.000034177407,0.0001192183,0.00020515008,0.0017450151,0.0029347439],"genre_scores_gemma":[0.16334963,0.0005380128,0.8322905,0.000107219574,0.000097889475,0.00015960836,0.0011505153,0.00082482444,0.0014818683],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977932,0.0011568957,0.00012182246,0.0003718965,0.00048252993,0.00007371001],"domain_scores_gemma":[0.98816663,0.008296403,0.00068294245,0.0015015631,0.0012270652,0.00012527993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00255761,0.00088418415,0.0010734204,0.004258771,0.0014150916,0.0050429683,0.0016372411,0.0013281349,0.003956576],"category_scores_gemma":[0.01841367,0.0008874147,0.0011244622,0.0025472958,0.003182783,0.0067814128,0.0017282186,0.0022745458,0.0019295325],"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":[0.0001796173,0.00017936296,0.0027020914,0.0012935248,0.000116805226,0.00040812246,0.00441657,0.045707464,0.037285108,0.29270095,0.005571573,0.6094388],"study_design_scores_gemma":[0.000049783514,0.00019009541,0.0021428436,0.0002429165,0.0001090402,0.00046397164,0.0013345274,0.5034836,0.03129079,0.42767268,0.032928783,0.00009093446],"about_ca_topic_score_codex":0.0006661028,"about_ca_topic_score_gemma":0.00093304086,"teacher_disagreement_score":0.0050429683,"about_ca_system_score_codex":0.00086548354,"about_ca_system_score_gemma":0.0013694259,"threshold_uncertainty_score":0.013526082},"labels":[],"label_agreement":null},{"id":"W2048760284","doi":"10.1162/089120104323093267","title":"Inferable Centers, Centering Transitions, and the Notion of Coherence","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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 British Columbia","funders":"","keywords":"Cohesion (chemistry); Coherence (philosophical gambling strategy); Computer science; Indeterminacy (philosophy); Transition (genetics); Linguistics; Identity (music); Natural language processing; Epistemology; Mathematics; Philosophy","score_opus":0.010828978407771098,"score_gpt":0.2574355551626614,"score_spread":0.24660657675489034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048760284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29876566,0.0013270038,0.68793035,0.00093887834,0.000047340032,0.00013398506,0.0008495854,0.0006238596,0.009383372],"genre_scores_gemma":[0.8705785,0.00029496822,0.12709217,0.00008487521,0.000056939767,0.00014810053,0.00076863996,0.00013825725,0.0008375297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642074,0.0015021523,0.0003399249,0.00100609,0.00047025646,0.00026075973],"domain_scores_gemma":[0.9881436,0.0073672133,0.0014393365,0.0017110524,0.0010162203,0.0003224969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032854413,0.00042450163,0.00054367224,0.0045529054,0.0029158858,0.0031759797,0.0011655859,0.0010069606,0.0021527277],"category_scores_gemma":[0.01347225,0.0005575725,0.0006674048,0.004312677,0.006104614,0.010486696,0.0032482196,0.001722391,0.00021345177],"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":[0.00023307354,0.000047587033,0.005720591,0.00021523016,0.000027056672,0.0003328026,0.011027159,0.005095951,0.005330502,0.9142862,0.0010077823,0.056676026],"study_design_scores_gemma":[0.000039421582,0.00010226263,0.010437445,0.00010002269,0.00012667953,0.00035090232,0.004512637,0.06351352,0.014849172,0.8836205,0.022237455,0.00010993581],"about_ca_topic_score_codex":0.0029404827,"about_ca_topic_score_gemma":0.003577682,"teacher_disagreement_score":0.0045529054,"about_ca_system_score_codex":0.0015245918,"about_ca_system_score_gemma":0.0014450935,"threshold_uncertainty_score":0.01737529},"labels":[],"label_agreement":null},{"id":"W2051593977","doi":"10.1162/coli_a_00002","title":"Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":302,"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":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Paraphrase; Computer science; Natural language processing; Task (project management); Artificial intelligence; Parallel corpora; Field (mathematics); Linguistics; Machine translation","score_opus":0.06410955906269462,"score_gpt":0.40156873393396203,"score_spread":0.3374591748712674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051593977","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012093974,0.030935701,0.94376403,0.0013705837,0.00012204945,0.00095785473,0.0023462516,0.0042715934,0.0041379067],"genre_scores_gemma":[0.05460917,0.019108256,0.9149152,0.00045814825,0.00016279898,0.0008902143,0.0072048553,0.00081288326,0.0018385034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98880017,0.0052458486,0.0014358081,0.0014577333,0.002913964,0.0001464791],"domain_scores_gemma":[0.94835085,0.03835462,0.0018615134,0.0047159623,0.006364801,0.00035224247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0104788225,0.0017598983,0.0026343726,0.007297795,0.00095831417,0.0034425997,0.005062104,0.0019202672,0.0039218846],"category_scores_gemma":[0.03765097,0.0011637366,0.0016905803,0.009864944,0.001401756,0.0058853915,0.0022303658,0.0020935056,0.0034577977],"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":[0.00017806429,0.00031503785,0.0012340406,0.0037613797,0.00010972399,0.00010865229,0.0006247784,0.0040202504,0.007104069,0.006241766,0.0054965927,0.9708057],"study_design_scores_gemma":[0.0006051477,0.0016917941,0.011819505,0.0041715205,0.00088692,0.0060038255,0.004444236,0.4604189,0.13922341,0.12083806,0.24929361,0.0006031058],"about_ca_topic_score_codex":0.0017435033,"about_ca_topic_score_gemma":0.0023429238,"teacher_disagreement_score":0.0104788225,"about_ca_system_score_codex":0.00094619987,"about_ca_system_score_gemma":0.0018568035,"threshold_uncertainty_score":0.055417955},"labels":[],"label_agreement":null},{"id":"W2064296938","doi":"10.1162/coli_a_00064","title":"A Strategy for Information Presentation in Spoken Dialog Systems","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":35,"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":"Ames Research Center; Atomic Energy of Canada Limited; National Aeronautics and Space Administration","keywords":"Dialog box; Computer science; Structuring; Dialog system; Process (computing); Presentation (obstetrics); User satisfaction; Human–computer interaction; Information retrieval; World Wide Web","score_opus":0.06398151558250546,"score_gpt":0.27997948751890905,"score_spread":0.21599797193640358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064296938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073882765,0.0006360658,0.979122,0.00092746614,0.00016279674,0.00047823024,0.000084913656,0.0037310862,0.0074691707],"genre_scores_gemma":[0.17024484,0.0005164403,0.81628233,0.00084741006,0.00017345152,0.0012715757,0.00024778015,0.0005221314,0.009894004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99388605,0.003331413,0.0004494616,0.00091342797,0.001253006,0.00016659923],"domain_scores_gemma":[0.9948985,0.0028630018,0.00034553534,0.0009449609,0.0007223396,0.00022578474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041529136,0.0023625328,0.0011083173,0.0017254385,0.0016870277,0.004986439,0.002877066,0.0034430642,0.006273338],"category_scores_gemma":[0.0133602265,0.0009415048,0.0011570135,0.0010129132,0.002904812,0.00517786,0.0033322053,0.0020559318,0.0038106672],"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":[0.0008624864,0.00046041954,0.0014856581,0.0013011921,0.00024050921,0.0012071917,0.009580569,0.025991842,0.130729,0.29332748,0.018115465,0.51669824],"study_design_scores_gemma":[0.00047287755,0.0016915117,0.0011466765,0.0004682843,0.00027553653,0.0023269965,0.0025029636,0.4424582,0.08469159,0.27734512,0.18621776,0.00040232347],"about_ca_topic_score_codex":0.0011522701,"about_ca_topic_score_gemma":0.0008716763,"teacher_disagreement_score":0.006273338,"about_ca_system_score_codex":0.0011719938,"about_ca_system_score_gemma":0.0011533957,"threshold_uncertainty_score":0.02196294},"labels":[],"label_agreement":null},{"id":"W2068580719","doi":"10.1162/coli_r_00056","title":"<b>Cross-Language Information Retrieval Jian-Yun Nie</b> (University of Montreal) San Rafael, CA: Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 8), 2010, xv+125 pp; paperbound, ISBN 978-1-59829-863-5, $40.00; ebook, ISBN 978-1-59829-864-3, $30.00 or by subscription","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Information Retrieval and Search Behavior","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":"Volume (thermodynamics); Jian; Humanities; Computer science; Art; Literature; Physics","score_opus":0.024129246993715218,"score_gpt":0.2563956028276577,"score_spread":0.2322663558339425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068580719","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022434092,0.5107715,0.092183284,0.019148579,0.01339346,0.00033143425,0.0026851823,0.0062577925,0.35298544],"genre_scores_gemma":[0.019518558,0.18875322,0.05626382,0.005099879,0.005004984,0.00022044076,0.0043950984,0.001704731,0.71903926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993174,0.00010013702,0.000053448905,0.0001711605,0.00028328475,0.00007452261],"domain_scores_gemma":[0.99888474,0.00027638723,0.000061089595,0.00011664987,0.00051819347,0.00014295621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011813422,0.0015783102,0.0011478476,0.0029273566,0.0008911594,0.004977027,0.0011768367,0.0013796831,0.13717215],"category_scores_gemma":[0.0020035526,0.00051047315,0.000532015,0.007739763,0.001302264,0.004538843,0.001581177,0.0013930174,0.092516385],"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":[0.000025438887,0.00001766613,0.00017249615,0.0005372689,0.000019288875,0.00007698784,0.00011889159,0.00021273977,0.0015498234,0.005817858,0.65926987,0.33218163],"study_design_scores_gemma":[0.0000052056216,0.000016624295,0.00084029103,0.00025773185,0.000012054062,0.00038892328,0.00013355238,0.00073893194,0.00056914386,0.0025014416,0.9945163,0.00001986348],"about_ca_topic_score_codex":0.028257048,"about_ca_topic_score_gemma":0.03322936,"teacher_disagreement_score":0.13717215,"about_ca_system_score_codex":0.002236812,"about_ca_system_score_gemma":0.002388394,"threshold_uncertainty_score":0.45888656},"labels":[],"label_agreement":null},{"id":"W2077818552","doi":"10.1162/coli.2010.36.1.36104","title":"Automatically Identifying the Source Words of Lexical Blends in English","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"University of Toronto","keywords":"Computer science; Natural language processing; Lexicon; Artificial intelligence; Task (project management); Set (abstract data type); Identification (biology); Word (group theory); Source text; Linguistics; Programming language","score_opus":0.013274499254340271,"score_gpt":0.29620196724369235,"score_spread":0.2829274679893521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077818552","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9248342,0.0010666247,0.062561646,0.00041955922,0.00008583207,0.00011023999,0.0030352783,0.001577151,0.00630935],"genre_scores_gemma":[0.9448154,0.00048359134,0.047611803,0.00007942822,0.000046219913,0.00006215484,0.0041070282,0.00033039539,0.0024639892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990075,0.00024424188,0.00018821619,0.000358569,0.00014854336,0.000053047366],"domain_scores_gemma":[0.99576145,0.0027162265,0.00059595157,0.0003164616,0.0005270848,0.00008294561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545212,0.000705841,0.0005604802,0.0021538998,0.00084324635,0.0013727536,0.0005703391,0.0006234822,0.004629331],"category_scores_gemma":[0.0048730285,0.0005177396,0.00049559027,0.0016388639,0.0007904175,0.004932688,0.0013134448,0.00067825185,0.0017797464],"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":[0.0017308524,0.00039587406,0.1301558,0.003000718,0.00022539042,0.0045432593,0.012854994,0.006506252,0.1806267,0.015099924,0.015488085,0.6293721],"study_design_scores_gemma":[0.0002342961,0.0006191266,0.32825944,0.0006218338,0.00058108394,0.011042084,0.019117331,0.3299426,0.17919199,0.03495542,0.095079005,0.00035576362],"about_ca_topic_score_codex":0.003005474,"about_ca_topic_score_gemma":0.0047369264,"teacher_disagreement_score":0.004629331,"about_ca_system_score_codex":0.00051726453,"about_ca_system_score_gemma":0.0004126126,"threshold_uncertainty_score":0.015486717},"labels":[],"label_agreement":null},{"id":"W2084046180","doi":"10.1162/coli_a_00049","title":"Lexicon-Based Methods for Sentiment Analysis","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3255,"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; University of Toronto; Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentiment analysis; Lexicon; Polarity (international relations); Natural language processing; Artificial intelligence; Negation; Consistency (knowledge bases); Orientation (vector space); Word (group theory); Process (computing); Reliability (semiconductor); Linguistics; Mathematics","score_opus":0.08804081832030412,"score_gpt":0.3846883079456333,"score_spread":0.29664748962532916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084046180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012882927,0.0014313121,0.98315823,0.00038878573,0.00031007818,0.000406241,0.0021492587,0.0030226517,0.007845165],"genre_scores_gemma":[0.045336884,0.0022307371,0.93637496,0.00039025216,0.0005900786,0.0012928011,0.007213166,0.000841814,0.005729201],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958007,0.0015425266,0.0004785838,0.00063625077,0.0014078915,0.00013401979],"domain_scores_gemma":[0.99447435,0.0029821282,0.00048461577,0.0007069867,0.001249119,0.00010278383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030452975,0.0020717187,0.0015420294,0.00900719,0.0014191739,0.0053936513,0.0018230806,0.0013767272,0.012928959],"category_scores_gemma":[0.01324147,0.00086831144,0.0019707284,0.007577281,0.0010170842,0.0037888756,0.0022795778,0.0023612832,0.014274262],"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":[0.0001124247,0.00016799835,0.0018883673,0.0014215712,0.00043687847,0.00025717905,0.0006165473,0.008685959,0.010404882,0.103362426,0.06512037,0.8075254],"study_design_scores_gemma":[0.00011854346,0.00009532741,0.0032335354,0.00053438,0.00024625778,0.0006830376,0.00077222905,0.36462542,0.009748445,0.38001645,0.23973009,0.00019620186],"about_ca_topic_score_codex":0.0018193896,"about_ca_topic_score_gemma":0.002607475,"teacher_disagreement_score":0.012928959,"about_ca_system_score_codex":0.0011462938,"about_ca_system_score_gemma":0.0016088362,"threshold_uncertainty_score":0.043251693},"labels":[],"label_agreement":null},{"id":"W2092527610","doi":"10.1162/089120102760173625","title":"Near-Synonymy and Lexical Choice","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":258,"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; Natural language processing; Denotation (semiotics); Artificial intelligence; Context (archaeology); Lexicon; Lexical choice; Set (abstract data type); Selection (genetic algorithm); Lexical semantics; Ontology; Lexical item; Linguistics","score_opus":0.02487434097093336,"score_gpt":0.28440130432046784,"score_spread":0.25952696334953446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092527610","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021573396,0.00020851874,0.9677023,0.00071761594,0.0000503013,0.00010364211,0.0002081746,0.00019474399,0.009241168],"genre_scores_gemma":[0.46403012,0.0002978935,0.5263891,0.00029721714,0.00007738081,0.0004240198,0.00062551425,0.00013733086,0.0077213557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967014,0.0010054677,0.00030510023,0.0010240866,0.00076087145,0.00020300734],"domain_scores_gemma":[0.9966118,0.0017314921,0.00035998473,0.0007326696,0.00040062953,0.00016340181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020688106,0.00067599,0.001127268,0.0025086123,0.0016534659,0.0041449247,0.0031549344,0.0017857943,0.0071521318],"category_scores_gemma":[0.007947455,0.00075842027,0.0029765733,0.0028011203,0.004996182,0.013060553,0.0038125303,0.0022133759,0.0015309411],"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":[0.000036624366,0.000023986113,0.00056430197,0.00007986676,0.00003870005,0.00015193298,0.0005940836,0.02199537,0.0011624619,0.9567356,0.000641158,0.017975945],"study_design_scores_gemma":[0.000014692784,0.000017661667,0.00016301683,0.000022771263,0.00001717957,0.000097507735,0.00012797352,0.09206878,0.0006908448,0.90154225,0.005215084,0.000022352855],"about_ca_topic_score_codex":0.003954945,"about_ca_topic_score_gemma":0.0033679921,"teacher_disagreement_score":0.0071521318,"about_ca_system_score_codex":0.002397544,"about_ca_system_score_gemma":0.0016680879,"threshold_uncertainty_score":0.023926318},"labels":[],"label_agreement":null},{"id":"W2104710058","doi":"10.1162/coli_r_00188","title":"<b>Semi-Supervised Learning and Domain Adaptation in Natural Language Processing</b> <b>Anders Søgaard</b> University of Copenhagen Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 21), 2013, x+93 pp; paperbound, ISBN 978-1-60845-985-8, $40.00; e-book, ISBN 978-1-60845-986-5, $30.00 or by subscription","year":2014,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Domain Adaptation and Few-Shot Learning","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":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Machine learning; Parsing; Test set; Test data; Supervised learning; sort; Adaptation (eye); Information retrieval; Artificial neural network; Psychology","score_opus":0.014480307356805262,"score_gpt":0.24449198145169979,"score_spread":0.23001167409489454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104710058","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035805218,0.10158897,0.8350985,0.016423903,0.0033975542,0.00017531367,0.00081885746,0.003060318,0.035856105],"genre_scores_gemma":[0.076478,0.12626086,0.66823334,0.005805035,0.0089785475,0.0008642737,0.005494001,0.002499365,0.105386555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848205,0.0005489357,0.000100098456,0.0003807381,0.0004231955,0.00006507105],"domain_scores_gemma":[0.99611,0.0028044276,0.0001343699,0.00038498925,0.00044235738,0.00012380058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002664428,0.0010058513,0.0010689639,0.0013888777,0.00043602442,0.0029733344,0.0015299203,0.0017848748,0.016117824],"category_scores_gemma":[0.004145222,0.00073147827,0.00072112214,0.0039607557,0.0024134675,0.004080174,0.0019037891,0.0039167427,0.013201529],"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":[0.00009676299,0.000091427544,0.0003597531,0.0011287162,0.000117681004,0.00012227522,0.00021339947,0.012634038,0.0038793664,0.0393288,0.25813693,0.6838908],"study_design_scores_gemma":[0.00004036436,0.00016585538,0.0029423728,0.000903027,0.0000656615,0.0008170308,0.00022053067,0.20113395,0.0055523133,0.21116678,0.57683307,0.00015889987],"about_ca_topic_score_codex":0.002914996,"about_ca_topic_score_gemma":0.0030528668,"teacher_disagreement_score":0.016117824,"about_ca_system_score_codex":0.0009511617,"about_ca_system_score_gemma":0.001009587,"threshold_uncertainty_score":0.053919435},"labels":[],"label_agreement":null},{"id":"W2105897558","doi":"10.1162/coli.2009.35.4.35402","title":"From Annotator Agreement to Noise Models","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Benchmarking; Computer science; Noise (video); Agreement; Data set; Quality (philosophy); Set (abstract data type); Resource (disambiguation); Data quality; Data mining; Data science; Econometrics; Artificial intelligence; Mathematics; Linguistics; Physics","score_opus":0.028591093906635952,"score_gpt":0.27382490992191555,"score_spread":0.2452338160152796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105897558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022113698,0.0019525926,0.9578827,0.0058099153,0.00043351116,0.00022235229,0.0005374651,0.00047142807,0.0105764195],"genre_scores_gemma":[0.7322374,0.0013377811,0.25349286,0.0030746202,0.00086214935,0.0013749457,0.0015532176,0.001210021,0.004857035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.63175756,0.2636082,0.011168078,0.04028907,0.049277008,0.0039001296],"domain_scores_gemma":[0.3804966,0.5186472,0.021263618,0.051240284,0.026646832,0.0017054531],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27128983,0.0026431722,0.0042583845,0.008287196,0.0046669897,0.015241291,0.0068990276,0.0063411174,0.0032911366],"category_scores_gemma":[0.5429263,0.0023240834,0.002472288,0.0077875005,0.018563123,0.021448838,0.020136822,0.008231635,0.0017194885],"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":[0.0009949803,0.00013838519,0.028930588,0.0016296278,0.0018184512,0.00059200445,0.013594707,0.086880706,0.002239024,0.7240312,0.01169966,0.1274507],"study_design_scores_gemma":[0.00006509005,0.00009787746,0.0038932003,0.00043399984,0.00018802394,0.00026065658,0.0010749721,0.12189319,0.002256125,0.8602432,0.009403256,0.00019044362],"about_ca_topic_score_codex":0.005219304,"about_ca_topic_score_gemma":0.00432706,"teacher_disagreement_score":0.27128983,"about_ca_system_score_codex":0.007126923,"about_ca_system_score_gemma":0.0049663084,"threshold_uncertainty_score":0.89862937},"labels":[],"label_agreement":null},{"id":"W2109830295","doi":"10.1162/coli.2006.32.3.379","title":"Similarity of Semantic Relations","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"University of Waterloo; Johns Hopkins University","keywords":"Analogy; Word (group theory); Similarity (geometry); Vector space model; Semantic similarity; Relation (database); Vector space; Latent semantic analysis","score_opus":0.01936146345015635,"score_gpt":0.25841519200576835,"score_spread":0.239053728555612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109830295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33396602,0.010426541,0.48856002,0.0029460213,0.0008200454,0.0011159485,0.011610308,0.0016962795,0.14885877],"genre_scores_gemma":[0.8810795,0.0021100338,0.10011648,0.00042121042,0.0003368448,0.00064722233,0.009251874,0.00020614309,0.005830756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922525,0.0021548334,0.0009495632,0.0016153692,0.0027121536,0.00031548904],"domain_scores_gemma":[0.99073505,0.0047758413,0.0009562263,0.0017220479,0.0015578436,0.00025305766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002787363,0.00066949276,0.0007959002,0.010898451,0.001171668,0.0049129366,0.0011289772,0.0012224552,0.010314451],"category_scores_gemma":[0.029747467,0.000333848,0.0014021558,0.007791879,0.002504809,0.009063483,0.003523278,0.0011885188,0.0021486098],"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":[0.0004952037,0.0002559614,0.034244165,0.0014639018,0.00079078303,0.0005878806,0.007331467,0.0061908974,0.012394395,0.53222245,0.012750557,0.3912723],"study_design_scores_gemma":[0.00005771829,0.00020781964,0.029556204,0.00029817404,0.00025562083,0.001243078,0.0041926648,0.024877891,0.003406513,0.8615936,0.07420375,0.000106984546],"about_ca_topic_score_codex":0.0014244764,"about_ca_topic_score_gemma":0.0010457778,"teacher_disagreement_score":0.010898451,"about_ca_system_score_codex":0.0014667349,"about_ca_system_score_gemma":0.0009266726,"threshold_uncertainty_score":0.034505308},"labels":[],"label_agreement":null},{"id":"W2111856253","doi":"10.1162/coli.2007.33.1.9","title":"Word-Level Confidence Estimation for Machine Translation","year":2007,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"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; RWTH Aachen University; European Commission","keywords":"Computer science; Word (group theory); Phrase; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Example-based machine translation; Linguistics","score_opus":0.04620772119004527,"score_gpt":0.3427001006526349,"score_spread":0.2964923794625896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111856253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013138332,0.001886627,0.9822025,0.00019254038,0.000062877545,0.00005381737,0.00014505326,0.0008574763,0.0014608563],"genre_scores_gemma":[0.45470232,0.0008907576,0.5411777,0.00018096821,0.0003304452,0.00030712198,0.0010834034,0.0005740719,0.0007533101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.977032,0.010736436,0.0017733746,0.002266762,0.0076903426,0.00050105073],"domain_scores_gemma":[0.8278335,0.14869104,0.0071852445,0.006669271,0.00886376,0.0007571947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017739415,0.0015957851,0.001919982,0.0066141584,0.0011506682,0.0038674525,0.0023892086,0.0025456874,0.0029239294],"category_scores_gemma":[0.18177691,0.00081631675,0.0014772585,0.004514826,0.0024688896,0.0070575476,0.0028166426,0.0030842975,0.0011776631],"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":[0.00093585165,0.00014725141,0.015393497,0.0010058116,0.00070966245,0.00021764298,0.0005819143,0.32882568,0.006068152,0.08984554,0.004041324,0.5522277],"study_design_scores_gemma":[0.000062244544,0.00018459639,0.0034899183,0.00014079454,0.00010628631,0.00036924964,0.00008343089,0.8641735,0.008650952,0.11940042,0.0031953808,0.00014322806],"about_ca_topic_score_codex":0.0014847012,"about_ca_topic_score_gemma":0.00070716674,"teacher_disagreement_score":0.017739415,"about_ca_system_score_codex":0.0015912016,"about_ca_system_score_gemma":0.0012053296,"threshold_uncertainty_score":0.0938161},"labels":[],"label_agreement":null},{"id":"W2119168550","doi":"10.1162/0891201042544884","title":"The Alignment Template Approach to Statistical Machine Translation","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":933,"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; NIST; Machine translation; Evaluation of machine translation; Natural language processing; Example-based machine translation; Artificial intelligence; Phrase; Machine translation software usability; Generalization; Transfer-based machine translation; Translation (biology); Task (project management); Context (archaeology); Feature (linguistics); Rule-based machine translation; Word (group theory); Linguistics","score_opus":0.021864809993940373,"score_gpt":0.2953628508639949,"score_spread":0.2734980408700545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119168550","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032148973,0.0006344055,0.99529654,0.0001381774,0.000114338414,0.00006476677,0.00011830217,0.0012274872,0.0020845283],"genre_scores_gemma":[0.032028638,0.002575733,0.95582753,0.00031317843,0.0005394523,0.00062630436,0.0012090727,0.00087788515,0.0060021975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611264,0.0018079082,0.00028585255,0.0006366392,0.0010363548,0.00012065727],"domain_scores_gemma":[0.996811,0.0013544149,0.00025269474,0.0009296159,0.0005798683,0.00007237609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028895345,0.0015358625,0.0018877751,0.0025173943,0.0008623259,0.0027955528,0.0025713756,0.0019072617,0.0071182833],"category_scores_gemma":[0.007980834,0.00095844525,0.001889473,0.004376983,0.0012772084,0.0030653833,0.0020925466,0.0029320035,0.00947412],"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":[0.00010321522,0.00011957382,0.00048448256,0.00068706775,0.00037799738,0.0002821159,0.00020486473,0.062465634,0.013545807,0.31667095,0.020619951,0.5844383],"study_design_scores_gemma":[0.00004647604,0.00018106682,0.00047337727,0.00008944585,0.00011151533,0.00068993075,0.00005223907,0.46759695,0.011836116,0.41726968,0.101519525,0.00013364301],"about_ca_topic_score_codex":0.0018464096,"about_ca_topic_score_gemma":0.0016765089,"teacher_disagreement_score":0.0071182833,"about_ca_system_score_codex":0.0009297866,"about_ca_system_score_gemma":0.0020747269,"threshold_uncertainty_score":0.02381301},"labels":[],"label_agreement":null},{"id":"W2123215530","doi":"10.1162/coli.08-010-r1-07-048","title":"Unsupervised Type and Token Identification of Idiomatic Expressions","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Atomic Energy of Canada Limited; University of Toronto","keywords":"Linguistics; Identification (biology); Interpretation (philosophy); Computer science; Natural language processing; Literal (mathematical logic); Task (project management); Context (archaeology); Security token; Artificial intelligence; Semantic property; Expression (computer science); Psychology; History","score_opus":0.015640231814246133,"score_gpt":0.29692181395150163,"score_spread":0.2812815821372555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123215530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40255097,0.0005095452,0.5849693,0.00036363796,0.00019201373,0.00030781658,0.0020724307,0.004041636,0.00499272],"genre_scores_gemma":[0.63266,0.00020066522,0.3592974,0.00010093834,0.00009571162,0.0002496105,0.003979844,0.0004924405,0.0029234274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975382,0.0006523495,0.00028638315,0.000813653,0.00048783387,0.00022169942],"domain_scores_gemma":[0.99042165,0.0047399914,0.0012976965,0.0013652724,0.0018841925,0.0002911735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019525915,0.00061215396,0.0009856471,0.0036055981,0.00067212345,0.0016489405,0.0014604228,0.00083563867,0.001613579],"category_scores_gemma":[0.010129006,0.0003166714,0.00071070495,0.002530779,0.0008239504,0.0029319143,0.0010636562,0.0011263314,0.0015348976],"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":[0.0012724007,0.00029305345,0.08236528,0.0005782445,0.00014848409,0.0006804428,0.0013156913,0.0057836697,0.08303012,0.016922254,0.010545213,0.79706526],"study_design_scores_gemma":[0.000086785156,0.00026726333,0.07606187,0.00009126233,0.00020441393,0.002858156,0.001630861,0.7434557,0.11256799,0.049640454,0.012930754,0.00020444687],"about_ca_topic_score_codex":0.001350142,"about_ca_topic_score_gemma":0.0021323499,"teacher_disagreement_score":0.0036055981,"about_ca_system_score_codex":0.00061215134,"about_ca_system_score_gemma":0.0011096236,"threshold_uncertainty_score":0.0103263855},"labels":[],"label_agreement":null},{"id":"W2129909699","doi":"10.1162/coli_a_00085","title":"Learning Entailment Relations by Global Graph Structure Optimization","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"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":"University of Haifa; Azrieli Foundation; Israel Science Foundation","keywords":"Logical consequence; Computer science; Textual entailment; Inference; Graph; Transitive relation; Artificial intelligence; Constraint (computer-aided design); Theoretical computer science; Natural language processing; Mathematics; Combinatorics","score_opus":0.010916148327742984,"score_gpt":0.2556109568737796,"score_spread":0.24469480854603662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129909699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017605506,0.0002164884,0.97826195,0.00031445155,0.000015694923,0.00009843785,0.0002908559,0.002016207,0.0011804512],"genre_scores_gemma":[0.24425685,0.00033846265,0.7493918,0.00023783158,0.00005225518,0.00018614356,0.003054315,0.0005597311,0.0019225727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865615,0.00038649692,0.000076238146,0.00056519767,0.00023677161,0.00007920425],"domain_scores_gemma":[0.996351,0.0026239697,0.00023125479,0.00048777257,0.00025038296,0.000055553945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017179848,0.0015965627,0.0015907557,0.002204729,0.000857718,0.001560144,0.0019881527,0.0015550939,0.004457093],"category_scores_gemma":[0.0064744526,0.0009055479,0.0020964353,0.0018143611,0.0014829104,0.0060425685,0.0019846635,0.0029076238,0.000997568],"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":[0.00021868455,0.00033638754,0.0028270888,0.000493319,0.0002410617,0.00022068135,0.00026852908,0.44304982,0.009199821,0.06211682,0.009620806,0.47140694],"study_design_scores_gemma":[0.000032005188,0.000041473246,0.00025164307,0.000016619599,0.000051766066,0.000045450037,0.000049444167,0.88457036,0.0032932912,0.1103105,0.0013277332,0.000009776571],"about_ca_topic_score_codex":0.00375409,"about_ca_topic_score_gemma":0.010602019,"teacher_disagreement_score":0.004457093,"about_ca_system_score_codex":0.0016925765,"about_ca_system_score_gemma":0.0018427847,"threshold_uncertainty_score":0.0149104595},"labels":[],"label_agreement":null},{"id":"W2131526828","doi":"10.1162/coli.2006.32.2.223","title":"Building and Using a Lexical Knowledge Base of Near-Synonym Differences","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":82,"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; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Ottawa; University of Pennsylvania","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Knowledge base; Artificial intelligence; Mistake; Natural language; Bilingual dictionary; Word (group theory); Linguistics","score_opus":0.026568550280453792,"score_gpt":0.3117453974176719,"score_spread":0.2851768471372181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131526828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042655732,0.00031900854,0.93723714,0.00065424194,0.00012439296,0.00052908587,0.0044864584,0.0050703264,0.008923642],"genre_scores_gemma":[0.17336993,0.00039361144,0.8101042,0.00027997943,0.000053966258,0.00037722106,0.012436222,0.00045217856,0.0025327452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781287,0.0005226783,0.0002644403,0.0007227087,0.0005798735,0.00009743702],"domain_scores_gemma":[0.9941181,0.0031782163,0.00031960165,0.0012107544,0.0010440074,0.00012928329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016403534,0.000929211,0.0010799026,0.0058903093,0.0014389327,0.0021862057,0.0025782466,0.0013080119,0.007434053],"category_scores_gemma":[0.011976357,0.0009000483,0.0011033425,0.0037573427,0.0009858871,0.0072645308,0.0026233378,0.0020393168,0.0034695494],"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":[0.0003297457,0.0006179366,0.007016207,0.0009936413,0.00023710703,0.0024884543,0.0023010732,0.01915643,0.030324498,0.04218738,0.022027684,0.87231976],"study_design_scores_gemma":[0.00032748954,0.00046256202,0.010886828,0.0010020147,0.0006826536,0.0046719736,0.0032770995,0.4281553,0.095396265,0.24101353,0.21367195,0.00045232664],"about_ca_topic_score_codex":0.0033661341,"about_ca_topic_score_gemma":0.0069226124,"teacher_disagreement_score":0.007434053,"about_ca_system_score_codex":0.001021726,"about_ca_system_score_gemma":0.0019797932,"threshold_uncertainty_score":0.024869323},"labels":[],"label_agreement":null},{"id":"W2136930489","doi":"10.1162/coli.2006.32.1.13","title":"Evaluating WordNet-based Measures of Lexical Semantic Relatedness","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1414,"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; University of Pennsylvania","keywords":"WordNet; Computer science; Semantic similarity; Natural language processing; Spelling; Artificial intelligence; Lexical database; Proxy (statistics); Similarity (geometry); Information retrieval; Measure (data warehouse); Linguistics; Machine learning; Data mining","score_opus":0.058731127994592104,"score_gpt":0.34696039051580496,"score_spread":0.28822926252121284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136930489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9230577,0.0030598964,0.06271193,0.00023718434,0.0001257142,0.00025165593,0.001829505,0.0007901886,0.007936302],"genre_scores_gemma":[0.9472552,0.0006117703,0.04735991,0.000035935234,0.00008944846,0.00015330692,0.0036365245,0.00009555333,0.0007623129],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9917888,0.0035219316,0.0010666893,0.0009157127,0.002435959,0.00027095395],"domain_scores_gemma":[0.9540678,0.032822773,0.004065515,0.0026619502,0.005328716,0.0010531364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0080470685,0.001054583,0.0012850834,0.016808625,0.00081500824,0.0018349051,0.0011535381,0.0015792699,0.0015628039],"category_scores_gemma":[0.039030224,0.000245351,0.00060670596,0.009133915,0.0011374116,0.00484967,0.0019232524,0.00065861485,0.00063508534],"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":[0.002853965,0.0019656005,0.29271787,0.001979236,0.0019126602,0.00062227773,0.0020963394,0.09737049,0.031086773,0.014920579,0.0054962793,0.54697794],"study_design_scores_gemma":[0.00038422164,0.004384023,0.26307544,0.00020064371,0.0007751023,0.0017712394,0.0020961978,0.6443692,0.045145057,0.031381596,0.0060375365,0.0003797344],"about_ca_topic_score_codex":0.0018475588,"about_ca_topic_score_gemma":0.0029943145,"teacher_disagreement_score":0.016808625,"about_ca_system_score_codex":0.0008571837,"about_ca_system_score_gemma":0.00075455196,"threshold_uncertainty_score":0.042557478},"labels":[],"label_agreement":null},{"id":"W2137006453","doi":"10.1162/coli_a_00206","title":"Towards Topic-to-Question Generation","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":82,"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":"Computer science; Latent Dirichlet allocation; Predicate (mathematical logic); Natural language processing; Correctness; Artificial intelligence; Topic model; Similarity (geometry); Subsequence; Context (archaeology); String (physics); Information retrieval; Algorithm; Mathematics; Programming language","score_opus":0.08126377489865644,"score_gpt":0.32306504233377414,"score_spread":0.2418012674351177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137006453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013726847,0.0006225101,0.97820115,0.0005552895,0.00015400506,0.00036535464,0.0006025806,0.0039046234,0.001867704],"genre_scores_gemma":[0.20732924,0.00053255295,0.7800468,0.00041189528,0.0003195275,0.00088875426,0.0055727568,0.0007255433,0.004172885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949032,0.002966461,0.00023913918,0.0008930683,0.0007591859,0.00023897048],"domain_scores_gemma":[0.9875201,0.0093567325,0.00035946988,0.0012229141,0.001302,0.00023868658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005216217,0.0014438295,0.0011515679,0.0024283633,0.0008650417,0.001728073,0.0023081836,0.002256634,0.0054711658],"category_scores_gemma":[0.018453216,0.0006162217,0.0019091634,0.0018433856,0.0007617014,0.0033137358,0.0028267521,0.002180405,0.0028086985],"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":[0.00082407496,0.0006193759,0.0044912905,0.0012334565,0.00023869153,0.0006740702,0.002780256,0.06062264,0.027433349,0.067514606,0.037859365,0.7957088],"study_design_scores_gemma":[0.00016225921,0.00011162724,0.0006799815,0.000057452122,0.000082311904,0.00039956975,0.00035705933,0.8532419,0.014239526,0.11093435,0.019689227,0.000044702],"about_ca_topic_score_codex":0.0014056124,"about_ca_topic_score_gemma":0.001634826,"teacher_disagreement_score":0.0054711658,"about_ca_system_score_codex":0.00089017337,"about_ca_system_score_gemma":0.0015182573,"threshold_uncertainty_score":0.027586281},"labels":[],"label_agreement":null},{"id":"W2144719390","doi":"10.1162/coli_a_00077","title":"Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"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":"Atomic Energy of Canada Limited","keywords":"Automatic summarization; Computer science; Salience (neuroscience); Affect (linguistics); Context (archaeology); Information retrieval; Natural language processing; Artificial intelligence; Linguistics; History","score_opus":0.09209636236490953,"score_gpt":0.33507287718669815,"score_spread":0.24297651482178861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144719390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927873,0.00037925752,0.003992212,0.00034751752,0.000011231908,0.000048065816,0.00016197911,0.000049582508,0.0022228332],"genre_scores_gemma":[0.9963242,0.00020511493,0.0022890323,0.00007654227,0.000023074637,0.000042479267,0.0003893563,0.000029769697,0.0006204222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99103165,0.006907159,0.0005690258,0.0005279836,0.000839199,0.00012505037],"domain_scores_gemma":[0.7994827,0.1751615,0.014367292,0.0049472847,0.0051330905,0.0009082447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009096691,0.0002345626,0.00036844387,0.0016197737,0.0011911279,0.0015779585,0.000752532,0.0012207952,0.002076461],"category_scores_gemma":[0.15185654,0.00028962136,0.0002641439,0.0022907942,0.0012581684,0.0043621897,0.0012945832,0.0016253586,0.00047768396],"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":[0.0015224871,0.0010551634,0.543169,0.001358224,0.00029092943,0.0022198202,0.26901254,0.0035975478,0.009458583,0.0121398745,0.006337396,0.1498384],"study_design_scores_gemma":[0.00014263009,0.0016703518,0.7745522,0.0005968929,0.00036038243,0.004066068,0.11678097,0.04575997,0.007867604,0.014671055,0.03330232,0.00022953618],"about_ca_topic_score_codex":0.0017868188,"about_ca_topic_score_gemma":0.002123353,"teacher_disagreement_score":0.009096691,"about_ca_system_score_codex":0.0004787404,"about_ca_system_score_gemma":0.00027079188,"threshold_uncertainty_score":0.048108518},"labels":[],"label_agreement":null},{"id":"W2151552691","doi":"10.1162/089120102762671963","title":"Generating Indicative-Informative Summaries with SumUM","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":140,"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 de Montréal; McGill University","keywords":"Automatic summarization; Computer science; Identification (biology); Information retrieval; Natural language processing; Process (computing); Artificial intelligence","score_opus":0.02829016747849478,"score_gpt":0.24873866525715468,"score_spread":0.2204484977786599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151552691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09463151,0.0017907798,0.8724024,0.0005623887,0.000254802,0.0005361673,0.0014252147,0.023758642,0.0046381922],"genre_scores_gemma":[0.25273958,0.0006821218,0.73593503,0.00016665408,0.00019146474,0.0004197634,0.0045232074,0.00096161524,0.0043804487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774593,0.0011828422,0.00022472306,0.0003146676,0.00046885197,0.0000629391],"domain_scores_gemma":[0.9915404,0.0051701977,0.00077435275,0.00089412235,0.0014328478,0.00018818225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032882001,0.0010263264,0.00087217847,0.0017266942,0.00067557755,0.002016862,0.0010175034,0.0007514986,0.0039211656],"category_scores_gemma":[0.015502134,0.000294746,0.00050501304,0.0015745425,0.000339388,0.0028734638,0.0014833369,0.0006341445,0.002071163],"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":[0.0010147734,0.00028653452,0.002052643,0.00186472,0.00019743889,0.00040943155,0.0029200108,0.021607803,0.047725454,0.009200629,0.017266657,0.8954539],"study_design_scores_gemma":[0.00051412795,0.0019362457,0.0050258613,0.0002635838,0.0006082543,0.00085840863,0.0022844598,0.61609757,0.23319963,0.021204043,0.117760174,0.00024768774],"about_ca_topic_score_codex":0.0005752751,"about_ca_topic_score_gemma":0.0009960994,"teacher_disagreement_score":0.0039211656,"about_ca_system_score_codex":0.0003729771,"about_ca_system_score_gemma":0.00054080534,"threshold_uncertainty_score":0.017389834},"labels":[],"label_agreement":null},{"id":"W2154889602","doi":"10.1162/coli.2010.36.1.36101","title":"A Graph-Theoretic Framework for Semantic Distance","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Semantic similarity; Natural language processing; Artificial intelligence; Coherence (philosophical gambling strategy); Information retrieval; Set (abstract data type); Semantic computing; Semantic Web; Mathematics","score_opus":0.012063363554660086,"score_gpt":0.3012501952456227,"score_spread":0.2891868316909626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154889602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001957671,0.0007313719,0.9910617,0.0006621294,0.000075972035,0.00007563854,0.0002697293,0.00012117278,0.005044563],"genre_scores_gemma":[0.14094748,0.0026087945,0.84823173,0.0005111282,0.00059446204,0.0008032148,0.0013580807,0.0002096842,0.0047354097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945321,0.002396101,0.00045541287,0.0011785583,0.0012695311,0.00016829664],"domain_scores_gemma":[0.99250925,0.0049747825,0.00050845277,0.00085555506,0.00095297495,0.00019910956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005251364,0.0015311671,0.0013603845,0.00934088,0.0025188087,0.004853337,0.0034455718,0.0028235137,0.004236909],"category_scores_gemma":[0.017560605,0.00069472275,0.0021141195,0.010205042,0.0046605505,0.013107541,0.003722858,0.0035527996,0.0014075307],"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":[0.000012155704,0.000020981512,0.00022777682,0.00012509763,0.00004025683,0.000054216038,0.00023496979,0.01366429,0.00032011312,0.95226204,0.0017484678,0.0312895],"study_design_scores_gemma":[0.000005881496,0.000012666226,0.0001168972,0.000025750838,0.0000111034815,0.00006387986,0.000056425568,0.042079695,0.0001778888,0.94823754,0.009197041,0.000015316828],"about_ca_topic_score_codex":0.004344617,"about_ca_topic_score_gemma":0.0027010916,"teacher_disagreement_score":0.00934088,"about_ca_system_score_codex":0.0037202784,"about_ca_system_score_gemma":0.0016904869,"threshold_uncertainty_score":0.027772188},"labels":[],"label_agreement":null},{"id":"W2164948578","doi":"10.1162/089120103321337458","title":"Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":257,"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); Task (project management); Machine translation; Vocabulary; Beam search; Word error rate; Sentence; Translation (biology); Artificial intelligence; Natural language processing; Dynamic programming; Search algorithm; Speech recognition; Set (abstract data type); Algorithm; Linguistics; Programming language","score_opus":0.01830414375166094,"score_gpt":0.31965641621504903,"score_spread":0.3013522724633881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164948578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014083534,0.00013782909,0.9973579,0.00006170898,0.000023110566,0.000034261197,0.000031381398,0.00037788934,0.0005675186],"genre_scores_gemma":[0.02167759,0.00017119285,0.97608644,0.00010596549,0.000032599582,0.00027717944,0.0002047074,0.00022751244,0.001216878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808973,0.00097165554,0.00011424692,0.00031017498,0.00042452133,0.000089611196],"domain_scores_gemma":[0.9977291,0.0015398007,0.00011212955,0.00022372176,0.00035806146,0.000037247435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002154728,0.0011037582,0.0014034577,0.0015253222,0.0007651085,0.0010682808,0.0015756215,0.0013374164,0.00535028],"category_scores_gemma":[0.0062715933,0.00096797367,0.0010908123,0.0031136554,0.0011334885,0.002148295,0.0012496593,0.001946921,0.0023577474],"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":[0.00021296818,0.00012143035,0.00043493017,0.00028256673,0.00016347099,0.00015146837,0.00029468865,0.2715408,0.010630956,0.113588475,0.008608317,0.59396994],"study_design_scores_gemma":[0.000063685104,0.00006043009,0.00010538772,0.000018915709,0.00002505707,0.00007336041,0.000026868063,0.9234301,0.0028920993,0.066458926,0.006819246,0.000025901725],"about_ca_topic_score_codex":0.0031225486,"about_ca_topic_score_gemma":0.0043194434,"teacher_disagreement_score":0.00535028,"about_ca_system_score_codex":0.00074928574,"about_ca_system_score_gemma":0.0017172563,"threshold_uncertainty_score":0.0178985},"labels":[],"label_agreement":null},{"id":"W2166391512","doi":"10.1162/089120101317066122","title":"Automatic Verb Classification Based on Statistical Distributions of Argument Structure","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":199,"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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; National Science Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Verb; Sentence; Argument (complex analysis); Classifier (UML); Predicate (mathematical logic)","score_opus":0.01714931419756963,"score_gpt":0.3015708389109142,"score_spread":0.28442152471334453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166391512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25223574,0.00018228244,0.7391645,0.0002967717,0.000038145998,0.00015791577,0.0006159189,0.0039415783,0.003367217],"genre_scores_gemma":[0.7937898,0.000090302434,0.20212162,0.000069380316,0.000040239887,0.00019695482,0.002203321,0.00027135477,0.001217125],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777883,0.0008937017,0.00016368803,0.00056866114,0.00044758295,0.00014751487],"domain_scores_gemma":[0.98463583,0.011046579,0.0013224498,0.001235742,0.0015916907,0.00016772025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034816982,0.00053998147,0.0007507592,0.0029598977,0.0005772026,0.0017786938,0.0011197393,0.00092800235,0.0015468303],"category_scores_gemma":[0.0184218,0.0003331444,0.00054880057,0.001384856,0.00081181293,0.0029430967,0.00091376435,0.0011377904,0.0013255482],"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":[0.0005950482,0.00043215856,0.06581441,0.00025726852,0.00010328807,0.00020263555,0.00083717133,0.040349167,0.04970795,0.016767776,0.0067420118,0.8181911],"study_design_scores_gemma":[0.000031945594,0.000054987926,0.010830311,0.00002383741,0.000014685691,0.00014692786,0.0001444319,0.95185494,0.014440876,0.020807667,0.0016264728,0.00002299279],"about_ca_topic_score_codex":0.0012300536,"about_ca_topic_score_gemma":0.0019477764,"teacher_disagreement_score":0.0034816982,"about_ca_system_score_codex":0.0007458882,"about_ca_system_score_gemma":0.0008791592,"threshold_uncertainty_score":0.018413186},"labels":[],"label_agreement":null},{"id":"W2168801328","doi":"10.1162/089120103322711587","title":"Embedding Web-Based Statistical Translation Models in Cross-Language Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Machine translation; Natural language processing; Information retrieval; Artificial intelligence; Process (computing); Translation (biology); Machine translation software usability; Language model; Embedding; Example-based machine translation; Programming language","score_opus":0.019591668201522305,"score_gpt":0.3257819259314265,"score_spread":0.3061902577299042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168801328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029683745,0.0006860976,0.9654546,0.00050115946,0.00005434126,0.00007006529,0.00015102152,0.001362248,0.0020367706],"genre_scores_gemma":[0.59846324,0.0013637204,0.39190063,0.0003444765,0.00017761273,0.00036100103,0.0011345301,0.0005012973,0.005753377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977093,0.0015457375,0.00012446423,0.0002656126,0.00027061172,0.00008442893],"domain_scores_gemma":[0.9948868,0.0035503593,0.0003219531,0.00062135246,0.00055888935,0.0000606088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002948029,0.0006858851,0.0009962313,0.0020624246,0.00061531935,0.002010587,0.0008486329,0.0015922906,0.0028926025],"category_scores_gemma":[0.012559234,0.00082487665,0.00107615,0.002539771,0.0010933888,0.004334592,0.0014236307,0.0012577723,0.0024793325],"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":[0.00027245085,0.00024929666,0.0014390044,0.00018700362,0.00015257842,0.00023264941,0.00033341144,0.67946255,0.003470942,0.06309647,0.0029440103,0.24815963],"study_design_scores_gemma":[0.000013765319,0.000026642732,0.000121970064,0.000008505562,0.0000121794965,0.000029343671,0.000024737035,0.9709681,0.0005532609,0.027362023,0.00086719304,0.00001224516],"about_ca_topic_score_codex":0.007951599,"about_ca_topic_score_gemma":0.007478223,"teacher_disagreement_score":0.007951599,"about_ca_system_score_codex":0.0010884337,"about_ca_system_score_gemma":0.0012224395,"threshold_uncertainty_score":0.015810609},"labels":[],"label_agreement":null},{"id":"W2170471032","doi":"10.1162/089120103322753365","title":"Disambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":141,"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":"Engineering and Physical Sciences Research Council; Atomic Energy of Canada Limited","keywords":"Computer science; Adjective; Noun; Natural language processing; Verb; Artificial intelligence; Word (group theory); Heuristic; Argument (complex analysis); Part of speech; Linguistics","score_opus":0.024330433789640626,"score_gpt":0.30231777277498023,"score_spread":0.2779873389853396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170471032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8695164,0.0006923937,0.11766265,0.00026161212,0.00005557213,0.00027069298,0.0027101473,0.003195768,0.005634833],"genre_scores_gemma":[0.8423027,0.0002715034,0.14929533,0.00009192689,0.000027528875,0.00015083898,0.0065135225,0.0002892957,0.0010573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693227,0.00126989,0.00037254707,0.0006800415,0.0006304519,0.00011477616],"domain_scores_gemma":[0.98269373,0.011718534,0.0011201567,0.0017830541,0.0024325412,0.00025194045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038786654,0.000853889,0.0009596024,0.004175608,0.00097741,0.0019458754,0.000637814,0.0007250617,0.0009121499],"category_scores_gemma":[0.017518032,0.00041141175,0.0006133033,0.0032795942,0.000696438,0.0030135524,0.0016253724,0.00070784404,0.0008941206],"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":[0.002014697,0.00063072995,0.093862854,0.0013649003,0.0005414154,0.0006306854,0.0047616283,0.043993376,0.116376735,0.0054104766,0.007701236,0.7227112],"study_design_scores_gemma":[0.0003190016,0.00081118895,0.09614705,0.00017753337,0.0005131208,0.0018705868,0.005853472,0.58939415,0.2513878,0.023155821,0.03000402,0.0003662433],"about_ca_topic_score_codex":0.0036587738,"about_ca_topic_score_gemma":0.007457117,"teacher_disagreement_score":0.004175608,"about_ca_system_score_codex":0.0005978033,"about_ca_system_score_gemma":0.0010463274,"threshold_uncertainty_score":0.02051258},"labels":[],"label_agreement":null},{"id":"W2562910494","doi":"10.1162/coli_a_00278","title":"Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications","year":2016,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":80,"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":"Computational linguistics; Perspective (graphical); Computer science; Linguistics; Field (mathematics); Sociocultural linguistics; Subjectivity; Multidisciplinary approach; Interpretation (philosophy); Sentiment analysis; Affect (linguistics); Artificial intelligence; Natural language processing; Sociology; Natural language; Epistemology; Social science; Comprehension approach","score_opus":0.01678670568591051,"score_gpt":0.3042419730166649,"score_spread":0.2874552673307544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562910494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043684166,0.037960634,0.8640242,0.013294141,0.00076194137,0.0002352429,0.000699972,0.00058639835,0.03875321],"genre_scores_gemma":[0.6299666,0.022022178,0.33824098,0.0018994726,0.0014595254,0.00047672717,0.00082015904,0.00024918318,0.0048651593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972778,0.0016311021,0.00024260473,0.00032613953,0.00042961826,0.000092631184],"domain_scores_gemma":[0.9872922,0.01020006,0.0009754097,0.0005496491,0.0008190267,0.00016367527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004224278,0.00086807733,0.0010691411,0.004118989,0.0010108777,0.007102072,0.0014045929,0.0009520444,0.0037692043],"category_scores_gemma":[0.022440495,0.00059029367,0.0011767072,0.00466716,0.0039264117,0.010803313,0.0020930595,0.002412041,0.00073902524],"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":[0.000083247294,0.00004321932,0.0023965575,0.0011548261,0.00013612454,0.00018294078,0.0021890574,0.009194092,0.0012210296,0.830022,0.0063043823,0.1470725],"study_design_scores_gemma":[0.000008590311,0.000020067258,0.0013323373,0.00031298582,0.000030632196,0.00011579095,0.000697417,0.046039723,0.00043262204,0.9341123,0.016865829,0.00003172772],"about_ca_topic_score_codex":0.0013691096,"about_ca_topic_score_gemma":0.0012955748,"teacher_disagreement_score":0.007102072,"about_ca_system_score_codex":0.0017056763,"about_ca_system_score_gemma":0.0008935955,"threshold_uncertainty_score":0.022340417},"labels":[],"label_agreement":null},{"id":"W2602799059","doi":"10.1162/coli_a_00290","title":"Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease","year":2017,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":28,"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 Rehabilitation Institute; University of Toronto","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health; Alzheimer Society; AGE-WELL; Carnegie Mellon University; Natural Sciences and Engineering Research Council of Canada; University of Pittsburgh","keywords":"Computer science; Confusion; Dementia; Cognitive psychology; Vocabulary; Function (biology); Cognition; Process (computing); Parsing; Spoken language; Decision tree; Artificial intelligence; Natural language processing; Psychology; Disease; Linguistics; Medicine","score_opus":0.030383408812927348,"score_gpt":0.2762257908780106,"score_spread":0.24584238206508324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602799059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8380473,0.0010281545,0.15302041,0.0010304819,0.00011061579,0.0002441776,0.00026755765,0.001992485,0.0042588147],"genre_scores_gemma":[0.9259674,0.0002596741,0.07192369,0.00018253618,0.000035524517,0.00008616488,0.0004289525,0.000068946305,0.0010470517],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99390537,0.0044534206,0.00025133416,0.0007625032,0.00036535304,0.00026197478],"domain_scores_gemma":[0.9884255,0.00895701,0.00084944465,0.00028708103,0.0011027212,0.00037827552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046513267,0.0010975845,0.0008444529,0.0014440118,0.0011624009,0.002510287,0.0007909318,0.0014586069,0.00096514146],"category_scores_gemma":[0.022741817,0.00039155097,0.0005500496,0.00035890186,0.0008199176,0.0026136965,0.002357197,0.0010133494,0.00089603855],"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":[0.0024182484,0.0010410115,0.11044578,0.0010895971,0.00023259273,0.0009254878,0.037997417,0.032169838,0.042816862,0.0029505016,0.0062621012,0.76165056],"study_design_scores_gemma":[0.00010940039,0.0013493744,0.06467492,0.00039260852,0.00028166754,0.0015066063,0.019511025,0.85017604,0.03619826,0.015636947,0.009867811,0.00029538528],"about_ca_topic_score_codex":0.0032756594,"about_ca_topic_score_gemma":0.003939286,"teacher_disagreement_score":0.0046513267,"about_ca_system_score_codex":0.00059847336,"about_ca_system_score_gemma":0.001175967,"threshold_uncertainty_score":0.024598837},"labels":[],"label_agreement":null},{"id":"W2884082915","doi":"10.1162/coli_a_00327","title":"Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey","year":2018,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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":"Simon Fraser University","funders":"Ruhr-Universität Bochum; Universität Hamburg","keywords":"Anaphora (linguistics); Antecedent (behavioral psychology); Computer science; Automatic summarization; Natural language processing; Linguistics; Sentence; Artificial intelligence; Machine translation; Computational linguistics; Field (mathematics); Resolution (logic); Psychology; Philosophy","score_opus":0.018271616867919945,"score_gpt":0.30533072661077887,"score_spread":0.2870591097428589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884082915","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039673117,0.9221705,0.042713072,0.004644895,0.0005447061,0.00008641436,0.00017908939,0.00027205973,0.025421917],"genre_scores_gemma":[0.033568718,0.92874575,0.029298946,0.0018842806,0.0022911332,0.00016386854,0.0005530498,0.00018700442,0.0033072394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558914,0.001525695,0.00065061555,0.0008553069,0.0011826053,0.00019663242],"domain_scores_gemma":[0.9741697,0.022571364,0.00068555016,0.0010182614,0.0012858713,0.00026931512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056603244,0.0010014419,0.002127039,0.017628783,0.0023288147,0.0066418084,0.0023599032,0.0033219496,0.0055925283],"category_scores_gemma":[0.016355056,0.0014677192,0.001615489,0.025834356,0.003978933,0.018890187,0.0044171517,0.003491941,0.0023610024],"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":[0.000059899266,0.00016360448,0.0034173022,0.011712641,0.00017794072,0.00050772115,0.005240136,0.0012060612,0.0006736683,0.16376095,0.02174421,0.7913359],"study_design_scores_gemma":[0.0000162344,0.00005213575,0.0034612517,0.0068646716,0.000110257664,0.0017983335,0.003143752,0.0034333663,0.0006677992,0.14865437,0.831718,0.00007979961],"about_ca_topic_score_codex":0.0028147749,"about_ca_topic_score_gemma":0.0025655585,"teacher_disagreement_score":0.017628783,"about_ca_system_score_codex":0.0021487796,"about_ca_system_score_gemma":0.003422385,"threshold_uncertainty_score":0.029935002},"labels":[],"label_agreement":null},{"id":"W2891212627","doi":"10.1162/coli_a_00333","title":"Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information","year":2018,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"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; University of Ottawa","funders":"","keywords":"Computer science; Social media; Context (archaeology); Perspective (graphical); Process (computing); Interpretation (philosophy); Task (project management); Linguistics; Artificial intelligence; Natural language processing; World Wide Web","score_opus":0.021970997074845143,"score_gpt":0.2991216231871204,"score_spread":0.27715062611227526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891212627","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012125962,0.09839412,0.021117289,0.07413128,0.77328604,0.00020125876,0.0011982165,0.0007549201,0.029704282],"genre_scores_gemma":[0.0038640501,0.061414946,0.0047678486,0.01216064,0.87733656,0.00022008707,0.001598169,0.00074886176,0.03788888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783534,0.0004554582,0.00025365205,0.0006019369,0.0006813648,0.0001723608],"domain_scores_gemma":[0.98810136,0.0066246307,0.00064908445,0.0008626998,0.0021605866,0.0016016125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024757995,0.0021023143,0.002479559,0.006466801,0.0024411702,0.008639533,0.002198193,0.0047352365,0.043394927],"category_scores_gemma":[0.009385281,0.00080297224,0.0020097874,0.0047911047,0.002303127,0.00780822,0.004597565,0.007658649,0.020224677],"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":[0.000031800555,0.000065779575,0.00034066636,0.0007645957,0.00003756266,0.00014820574,0.0002521125,0.0001865742,0.00056200684,0.0073251016,0.922327,0.06795875],"study_design_scores_gemma":[0.000005871868,0.000033772256,0.00061526324,0.0005293423,0.000021135711,0.00030222733,0.00013161896,0.00031680128,0.00012936577,0.006135643,0.9917572,0.000021721491],"about_ca_topic_score_codex":0.0009946963,"about_ca_topic_score_gemma":0.0015587424,"teacher_disagreement_score":0.043394927,"about_ca_system_score_codex":0.001756341,"about_ca_system_score_gemma":0.0021562018,"threshold_uncertainty_score":0.14517051},"labels":[],"label_agreement":null},{"id":"W2895279374","doi":"10.1162/coli_a_00363","title":"Scalable Micro-planned Generation of Discourse from Structured Data","year":2019,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","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":"Computer science; Interpretability; Natural language processing; Scalability; Artificial intelligence; Natural language generation; Sentence; Pipeline (software); Paragraph; Fluency; Text simplification; Natural language understanding; Robustness (evolution); Natural language; Programming language; Database","score_opus":0.08137583821686917,"score_gpt":0.32304697739436655,"score_spread":0.24167113917749738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895279374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011597212,0.00023911726,0.9495867,0.0004327829,0.0001281203,0.00031311784,0.004045073,0.031025302,0.0026325872],"genre_scores_gemma":[0.098622896,0.00019295917,0.88170624,0.00016219438,0.00007755972,0.00038980832,0.013734699,0.0020190943,0.0030945688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986174,0.00043286625,0.00010352433,0.00048448678,0.0003039159,0.000057732675],"domain_scores_gemma":[0.99565303,0.0026105454,0.00022161052,0.0007322887,0.00065607607,0.00012636877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018243723,0.0010039036,0.0007394824,0.0016972892,0.00068932574,0.0016535218,0.0016916131,0.000788645,0.0076516536],"category_scores_gemma":[0.009486726,0.0005961796,0.0012221023,0.0013254888,0.00070986757,0.0026309418,0.002192564,0.0012214081,0.0043866206],"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":[0.0006422142,0.00029728469,0.0031811034,0.0014926012,0.00015361143,0.0010173338,0.002867715,0.03825135,0.054153807,0.05084812,0.07385127,0.7732434],"study_design_scores_gemma":[0.0001494971,0.00014909543,0.00092405453,0.0001088072,0.000075998076,0.0003946891,0.00075096876,0.7789135,0.075950645,0.060524378,0.08197053,0.00008784291],"about_ca_topic_score_codex":0.0026794751,"about_ca_topic_score_gemma":0.004420707,"teacher_disagreement_score":0.0076516536,"about_ca_system_score_codex":0.0007892889,"about_ca_system_score_gemma":0.0019335772,"threshold_uncertainty_score":0.025597334},"labels":[],"label_agreement":null},{"id":"W2986265153","doi":"10.1162/coli_a_00367","title":"On the Linguistic Representational Power of Neural Machine Translation Models","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Natural Language Processing 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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Natural language processing; Machine translation; Artificial intelligence; Interpretability; Semantics (computer science); Rule-based machine translation; Word (group theory); Contrast (vision); Linguistics","score_opus":0.05564198337220849,"score_gpt":0.3233539129337652,"score_spread":0.2677119295615567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986265153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14155184,0.0039680544,0.83159286,0.008338322,0.0001519323,0.000050806324,0.0006413536,0.0019731687,0.011731599],"genre_scores_gemma":[0.910987,0.0018447106,0.082507536,0.0006262787,0.00018196789,0.00008072705,0.0007805653,0.00022319617,0.0027679913],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983962,0.00092781556,0.00008252268,0.00025503643,0.0002538452,0.00008459042],"domain_scores_gemma":[0.9872896,0.009721479,0.0005635863,0.0014478988,0.0008556562,0.000121727615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042717378,0.000984534,0.00072946405,0.0009573865,0.0005879973,0.0025446222,0.001313966,0.0015737354,0.0021771633],"category_scores_gemma":[0.028945982,0.0006340668,0.0007393414,0.0011066487,0.001836443,0.0050288453,0.0016316754,0.0029753058,0.0007315818],"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":[0.00025068253,0.00007495966,0.002945811,0.0002172839,0.0001474907,0.00014618531,0.00040061362,0.7520987,0.005330381,0.1041379,0.0022800483,0.13196997],"study_design_scores_gemma":[0.0000079610745,0.00002995369,0.00035614966,0.000036733363,0.000018075752,0.000027780681,0.000028822338,0.9441421,0.0010956395,0.053554654,0.00069115986,0.0000109517105],"about_ca_topic_score_codex":0.0050890273,"about_ca_topic_score_gemma":0.0048038354,"teacher_disagreement_score":0.0050890273,"about_ca_system_score_codex":0.0012967853,"about_ca_system_score_gemma":0.0007839593,"threshold_uncertainty_score":0.022591352},"labels":[],"label_agreement":null},{"id":"W3008170323","doi":"10.1162/coli_a_00380","title":"The Limitations of Stylometry for Detecting Machine-Generated Fake News","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":15,"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":"Stylometry; Misinformation; Computer science; Artificial intelligence; Authorship attribution; Natural language processing; Machine learning; Computer security","score_opus":0.1728446409505819,"score_gpt":0.37575612472199554,"score_spread":0.20291148377141363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008170323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43381485,0.00645186,0.5081814,0.005847703,0.0005134669,0.00058253825,0.002959309,0.0053095375,0.036339343],"genre_scores_gemma":[0.9215909,0.00081413944,0.07467264,0.00032760782,0.0001795324,0.00015259183,0.0006009091,0.0002047085,0.0014569507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9783839,0.01158027,0.001359219,0.0023120784,0.0058878935,0.0004767102],"domain_scores_gemma":[0.8483234,0.0929692,0.015200296,0.032499284,0.009995834,0.0010120034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0100957705,0.0011568173,0.0010472564,0.0045475494,0.0017012885,0.0050962414,0.0013379852,0.0018592771,0.0019089617],"category_scores_gemma":[0.10895291,0.000600989,0.000523128,0.0026438485,0.0030477797,0.0060870005,0.00265026,0.0016608974,0.0018904336],"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":[0.0014490939,0.00032192294,0.12713553,0.0024369687,0.0003415423,0.00071514625,0.0056682536,0.042975742,0.029250486,0.058945887,0.015308476,0.71545094],"study_design_scores_gemma":[0.000083834595,0.0005733504,0.07861069,0.0011054949,0.00018625612,0.00359343,0.0034878105,0.5919183,0.090395585,0.17712067,0.0525193,0.00040529075],"about_ca_topic_score_codex":0.001800201,"about_ca_topic_score_gemma":0.0019971794,"teacher_disagreement_score":0.0100957705,"about_ca_system_score_codex":0.001154153,"about_ca_system_score_gemma":0.0012228872,"threshold_uncertainty_score":0.05339217},"labels":[],"label_agreement":null},{"id":"W3193068792","doi":"10.1162/coli_a_00422","title":"Probing Classifiers: Promises, Shortcomings, and Advances","year":2021,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"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":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Artificial intelligence; Variety (cybernetics); Classifier (UML); Machine learning; Property (philosophy); Artificial neural network; Deep neural networks; Natural language processing; Epistemology","score_opus":0.03569677429684543,"score_gpt":0.2887908698049079,"score_spread":0.2530940955080625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193068792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017404899,0.098570935,0.7594551,0.09758005,0.0027338502,0.00015598362,0.0005860307,0.0025234597,0.020989707],"genre_scores_gemma":[0.56065357,0.061848525,0.3392277,0.011915313,0.014773954,0.00057183433,0.0010943984,0.00100626,0.008908446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98483,0.0076721157,0.00046026593,0.002329351,0.004201488,0.00050674705],"domain_scores_gemma":[0.90112007,0.0717757,0.0019394085,0.009236936,0.014194125,0.0017338203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03587117,0.0016751926,0.002665594,0.0032462147,0.0018990176,0.007862362,0.004325789,0.005503535,0.0037924557],"category_scores_gemma":[0.09453927,0.0010112543,0.0011449875,0.003755189,0.0048372424,0.024495792,0.0038425038,0.011816834,0.0032707432],"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":[0.0002787897,0.00013459774,0.0036708142,0.0005024605,0.00013540474,0.00008146407,0.00062821346,0.016644903,0.0009037099,0.46999562,0.045917664,0.4611063],"study_design_scores_gemma":[0.000024604618,0.00007951927,0.0006542942,0.00032224122,0.00005599769,0.0001294786,0.00023502858,0.17995542,0.0012066812,0.7693937,0.047880568,0.000062499734],"about_ca_topic_score_codex":0.0042032916,"about_ca_topic_score_gemma":0.001786568,"teacher_disagreement_score":0.03587117,"about_ca_system_score_codex":0.0033029024,"about_ca_system_score_gemma":0.00318854,"threshold_uncertainty_score":0.1897071},"labels":[],"label_agreement":null},{"id":"W3201284223","doi":"10.1162/coli_a_00433","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":93,"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":"Harm; Emotion recognition; Sentiment analysis; Key (lock); Computer science; Psychology; Social psychology; Artificial intelligence; Computer security","score_opus":0.0701563089762093,"score_gpt":0.3225153650597269,"score_spread":0.2523590560835176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201284223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034083616,0.0009790461,0.5513681,0.14617851,0.007276906,0.026665676,0.0033364354,0.003416376,0.2266953],"genre_scores_gemma":[0.19641711,0.0012025884,0.57502884,0.057478108,0.0038860405,0.040673193,0.0028484182,0.0010867757,0.12137898],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85729086,0.09847997,0.011165653,0.0029288905,0.026528703,0.0036059553],"domain_scores_gemma":[0.7320235,0.117730185,0.010906533,0.02744966,0.10710792,0.0047821994],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.105793595,0.00077263435,0.0005910545,0.002721129,0.00462578,0.0074351686,0.0013949628,0.005754403,0.012211549],"category_scores_gemma":[0.15643564,0.0007394137,0.00091605575,0.0013316541,0.00449763,0.0035224361,0.0032487924,0.0062771523,0.012261188],"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":[0.00054907746,0.00054914085,0.004616072,0.0006860491,0.000044797496,0.0010145755,0.008839663,0.002934768,0.011294702,0.32382542,0.44243395,0.20321175],"study_design_scores_gemma":[0.00011542324,0.0003090029,0.0034748525,0.0012762798,0.000030098838,0.00066982856,0.0026354834,0.009259662,0.0087750815,0.06632021,0.9069677,0.00016637723],"about_ca_topic_score_codex":0.0021782492,"about_ca_topic_score_gemma":0.0022014764,"teacher_disagreement_score":0.9942456,"about_ca_system_score_codex":0.005014472,"about_ca_system_score_gemma":0.01603108,"threshold_uncertainty_score":0.5594967},"labels":[],"label_agreement":null},{"id":"W4205635927","doi":"10.1162/coli_a_00426","title":"Deep Learning for Text Style Transfer: A Survey","year":2021,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":162,"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; Politeness; Style (visual arts); Task (project management); Variety (cybernetics); Natural language processing; Artificial intelligence; Transfer of learning; Field (mathematics); Natural language; Deep learning; Natural (archaeology); Linguistics","score_opus":0.04084954962181789,"score_gpt":0.2874410351691519,"score_spread":0.24659148554733404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205635927","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05410707,0.28961685,0.618791,0.0056002056,0.0015020344,0.00030203265,0.002325285,0.0052427575,0.022512734],"genre_scores_gemma":[0.60210806,0.15075538,0.20760031,0.0022134446,0.0030035425,0.00049396016,0.0086853625,0.0008581356,0.024281783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999316,0.00020623788,0.0000646911,0.00020253338,0.00015652044,0.00005407097],"domain_scores_gemma":[0.9985286,0.00084870536,0.0000779972,0.00023252088,0.00024587876,0.00006627622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016144832,0.0012699026,0.0011317789,0.0016625505,0.00032817916,0.0013114737,0.0015718447,0.0009088408,0.0041676373],"category_scores_gemma":[0.0042387987,0.00044085854,0.00093427557,0.0020166123,0.0004133914,0.0022646291,0.0012877875,0.0016816445,0.0022172546],"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":[0.00009439478,0.0002133605,0.0020236133,0.00091770856,0.0001480327,0.000039285635,0.00009490253,0.027951201,0.0021046423,0.0070018326,0.016577754,0.94283336],"study_design_scores_gemma":[0.000057661593,0.00027809327,0.004819018,0.00084091816,0.00018482372,0.00017050563,0.00017938654,0.86500084,0.006584863,0.048879836,0.07294323,0.000060688377],"about_ca_topic_score_codex":0.0027905274,"about_ca_topic_score_gemma":0.0025604214,"teacher_disagreement_score":0.0041676373,"about_ca_system_score_codex":0.0006905592,"about_ca_system_score_gemma":0.00074449,"threshold_uncertainty_score":0.013942182},"labels":[],"label_agreement":null},{"id":"W4220732108","doi":"10.1162/coli_a_00434","title":"Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"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":"Automatic summarization; Computer science; Transformer; Domain adaptation; Natural language processing; Adaptation (eye); Artificial intelligence; Transfer of learning; Task (project management); Information retrieval","score_opus":0.01946222096216806,"score_gpt":0.24978835952530382,"score_spread":0.23032613856313575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220732108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041613773,0.0010438336,0.940353,0.0003195229,0.00010375061,0.00019705274,0.00067497167,0.014135673,0.0015584305],"genre_scores_gemma":[0.60281426,0.00071378774,0.38248953,0.00040513487,0.0001898425,0.00034689924,0.008061384,0.0006782035,0.00430091],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990835,0.00037561485,0.00007757233,0.0002740491,0.00013569584,0.0000535664],"domain_scores_gemma":[0.9973345,0.0012865303,0.00021876594,0.0005303778,0.0005381665,0.00009171294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001941258,0.0009420176,0.0007263044,0.0012157938,0.0003217999,0.0008211022,0.001438743,0.0007898915,0.0017542887],"category_scores_gemma":[0.0074727787,0.0003071917,0.0007701556,0.0010222304,0.00041843313,0.0025344167,0.0012331288,0.0018037517,0.0019102714],"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":[0.00058766274,0.00047530895,0.0024215605,0.00049321406,0.00015331422,0.0002442715,0.0005649574,0.18029541,0.054235484,0.0056987167,0.018757802,0.7360723],"study_design_scores_gemma":[0.00006171205,0.00023279183,0.0006004894,0.000018870429,0.000055442444,0.00008781966,0.00012432103,0.96212,0.024383925,0.007388795,0.0049020047,0.000023909895],"about_ca_topic_score_codex":0.0017716949,"about_ca_topic_score_gemma":0.0028731562,"teacher_disagreement_score":0.001941258,"about_ca_system_score_codex":0.00062581024,"about_ca_system_score_gemma":0.00090411375,"threshold_uncertainty_score":0.010266483},"labels":[],"label_agreement":null},{"id":"W4231077011","doi":"10.4018/978-1-4666-6042-7.ch085","title":"Learning Words from Experience","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Language Development and Disorders","field":"Psychology","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":"Queen's University","funders":"","keywords":"Experiential learning; Psychology; Vocabulary; Quality (philosophy); Word learning; Cognition; Cognitive psychology; Linguistics; Epistemology; Pedagogy","score_opus":0.022908332874132763,"score_gpt":0.29867766466870005,"score_spread":0.2757693317945673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231077011","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20407243,0.03596439,0.03372035,0.0122649465,0.0008331503,0.00006424195,0.0003184043,0.00023132582,0.71253073],"genre_scores_gemma":[0.8098486,0.05223858,0.018385183,0.0030710588,0.00037019953,0.00015238812,0.0005155062,0.00027139994,0.11514703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999736,0.00008000091,0.000011679911,0.00006116597,0.000088063796,0.00002305226],"domain_scores_gemma":[0.9993662,0.00045017793,0.00003882081,0.000052240004,0.000048806945,0.000043742253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004819655,0.00028840976,0.00024937562,0.0003825203,0.00041965433,0.0030426914,0.00042222263,0.0004940117,0.0055165626],"category_scores_gemma":[0.0021143628,0.00018529428,0.0002389421,0.00042291245,0.0029274053,0.0043704873,0.0015428769,0.0013444063,0.0014730507],"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":[0.00006308329,0.000108538734,0.0075642033,0.0007190908,0.000028096785,0.00092934514,0.052496992,0.00063146156,0.008256478,0.46255133,0.017935842,0.44871554],"study_design_scores_gemma":[0.000015328626,0.00017569824,0.01575788,0.0010952483,0.000032360273,0.001546303,0.016238464,0.00046553643,0.004653276,0.3308854,0.629083,0.00005147019],"about_ca_topic_score_codex":0.00086779415,"about_ca_topic_score_gemma":0.0012745624,"teacher_disagreement_score":0.0055165626,"about_ca_system_score_codex":0.00066865043,"about_ca_system_score_gemma":0.00069356174,"threshold_uncertainty_score":0.01845473},"labels":[],"label_agreement":null},{"id":"W4233779307","doi":"10.1162/coli.2000.27.1.140","title":"<i>Construing Experience through Meaning: A Language-based Approach to Cognition</i> M. A. K. Halliday and Christian M. I. M. Matthiessen London: Cassell (Open linguistics series, edited by Robin Fawcett), 1999, xiii+657 pp; paperback, ISBN 0-304-70490-3, $102.00, £65.00","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"Meaning (existential); Philosophy; Linguistics; Cognitive linguistics; Cognitive science; Cognition; Series (stratigraphy); Psychology; Epistemology; Neuroscience","score_opus":0.02494040335504384,"score_gpt":0.29636894422158067,"score_spread":0.27142854086653684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233779307","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070157307,0.5201509,0.0975016,0.091039985,0.0041861353,0.00006003531,0.00024488766,0.00045215042,0.27934867],"genre_scores_gemma":[0.4314135,0.37781495,0.09409912,0.0132327,0.008334087,0.00040794502,0.0007825761,0.0005234064,0.07339159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993592,0.0003726983,0.000037657926,0.00007325124,0.00011714517,0.000040072166],"domain_scores_gemma":[0.9992435,0.0005098146,0.00006714779,0.000056462362,0.00006978451,0.000053221458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012218964,0.0007445776,0.0005217683,0.001858235,0.001254616,0.00883682,0.001398579,0.0020789062,0.0092395535],"category_scores_gemma":[0.0019456262,0.00037880038,0.0007135073,0.0030436246,0.01392588,0.014277464,0.0024092752,0.0029381993,0.0019242556],"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":[0.000034798675,0.000015811145,0.00030824082,0.00082587753,0.00004493502,0.00020464939,0.00858758,0.00049792574,0.000905816,0.79253983,0.09327003,0.10276452],"study_design_scores_gemma":[0.000007809267,0.000014255358,0.0008533137,0.0005528429,0.000016417303,0.000479049,0.0029550248,0.00067708147,0.00026208808,0.78604996,0.20811144,0.000020745481],"about_ca_topic_score_codex":0.0034203317,"about_ca_topic_score_gemma":0.005028068,"teacher_disagreement_score":0.0092395535,"about_ca_system_score_codex":0.0021475642,"about_ca_system_score_gemma":0.0016069562,"threshold_uncertainty_score":0.03090936},"labels":[],"label_agreement":null},{"id":"W4233966082","doi":"10.1162/coli_x_00181","title":"Publications Received","year":2014,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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","score_opus":0.017556002457512956,"score_gpt":0.29004651036624157,"score_spread":0.27249050790872864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233966082","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045888816,0.008215106,0.0013064935,0.0067630257,0.02256957,0.00021713944,0.008018347,0.002477618,0.9499738],"genre_scores_gemma":[0.0013914177,0.005057682,0.000822869,0.0025378538,0.002687374,0.000082669525,0.005900228,0.001009369,0.98051065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638027,0.00029511208,0.00030640894,0.00069769943,0.0020298732,0.00029063935],"domain_scores_gemma":[0.9932318,0.00053080294,0.00032220932,0.0009297899,0.003795922,0.0011895744],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016194746,0.0017194542,0.0018546953,0.0045630177,0.0022040284,0.016587857,0.0024291754,0.0033611518,0.80939347],"category_scores_gemma":[0.009485399,0.00078633183,0.0012426996,0.0060713496,0.00090726354,0.007937112,0.004443865,0.003446402,0.84654695],"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":[0.000021526443,0.000025216066,0.00010540396,0.00034318995,0.0000062476734,0.00006714858,0.000046873687,0.000040097395,0.0001880506,0.0039404603,0.9077531,0.08746271],"study_design_scores_gemma":[0.0000033479844,0.000007955638,0.000109886314,0.00011400713,0.000002045973,0.00006638616,0.00002754459,0.000011823868,0.00004473978,0.0006740009,0.9989334,0.0000049127307],"about_ca_topic_score_codex":0.0015038176,"about_ca_topic_score_gemma":0.0025223177,"teacher_disagreement_score":0.19060653,"about_ca_system_score_codex":0.0021643415,"about_ca_system_score_gemma":0.0037996338,"threshold_uncertainty_score":0.2718771},"labels":[],"label_agreement":null},{"id":"W4235310004","doi":"10.4018/978-1-4666-6042-7.ch077","title":"Integrating Chinese Community into Canadian Society","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Radio, Podcasts, and Digital Media","field":"Social Sciences","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":"University of Alberta","funders":"","keywords":"Set (abstract data type); English as a second language; Language acquisition; Pedagogy; Public relations; Computer science; Knowledge management; Medical education; Mathematics education; Psychology; Political science; Medicine","score_opus":0.02837525078318943,"score_gpt":0.3030507985673399,"score_spread":0.2746755477841505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235310004","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12232408,0.0080118105,0.0012808888,0.0143809775,0.0007831343,0.00012562849,0.00020588565,0.00013064279,0.852757],"genre_scores_gemma":[0.7106005,0.008377899,0.0017810218,0.0012543846,0.00008095638,0.00007088257,0.00017790381,0.00006905441,0.27758738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992716,0.00009375163,0.000014689227,0.00008058998,0.00016310379,0.00037636154],"domain_scores_gemma":[0.999561,0.00004122693,0.000012395733,0.000020917274,0.000116275754,0.000248142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069847493,0.00067026523,0.00027416984,0.001997783,0.025637234,0.006315331,0.00089653255,0.000949124,0.01747609],"category_scores_gemma":[0.00077142444,0.00017875453,0.00027555588,0.0036232758,0.0064598527,0.0028024137,0.004639258,0.0013874724,0.00075813994],"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":[0.000047832295,0.000052531846,0.0073357713,0.0002624471,0.000013736435,0.001451497,0.25302866,0.00038213594,0.0008995646,0.4935782,0.06480132,0.17814629],"study_design_scores_gemma":[0.000008806564,0.000025255365,0.0067821406,0.00015029848,0.00002014002,0.00022572375,0.11077629,0.0003544464,0.00033613085,0.011792334,0.86949116,0.000037332982],"about_ca_topic_score_codex":0.94909364,"about_ca_topic_score_gemma":0.9778861,"teacher_disagreement_score":0.060692947,"about_ca_system_score_codex":0.060692947,"about_ca_system_score_gemma":0.10908432,"threshold_uncertainty_score":0.44036025},"labels":[],"label_agreement":null},{"id":"W4235980152","doi":"10.4018/978-1-4666-6042-7.ch012","title":"Demystifying Domain Specific Languages","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Model-Driven Software Engineering 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":"École de Technologie Supérieure","funders":"","keywords":"Vagueness; Digital subscriber line; Domain-specific language; Computer science; Domain (mathematical analysis); Software engineering; Programming language; Artificial intelligence; Mathematics","score_opus":0.020484544248111955,"score_gpt":0.2533815354641975,"score_spread":0.23289699121608554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235980152","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013086349,0.021184016,0.44972086,0.013719799,0.0021270963,0.00011971024,0.00029041345,0.001764855,0.49798688],"genre_scores_gemma":[0.23646198,0.032594636,0.43101633,0.0063053574,0.0013361853,0.00036675672,0.0011717505,0.0019731557,0.28877378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99922204,0.0003437383,0.000053921558,0.00010961335,0.00022172129,0.00004892152],"domain_scores_gemma":[0.9985051,0.00077262707,0.000057674948,0.00036316403,0.00024442608,0.000057006277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015960367,0.00060970814,0.00031150403,0.0015651009,0.0009184911,0.0045354143,0.0010121578,0.001126059,0.0052917176],"category_scores_gemma":[0.002623998,0.0003368614,0.00057205756,0.0009779428,0.0042542615,0.007770147,0.0026349076,0.003948759,0.0017706183],"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":[0.000002405703,0.000004277295,0.000034610835,0.000058627644,0.0000023328482,0.00003968481,0.0010921898,0.00048792284,0.0005251681,0.97276556,0.0050543807,0.019932805],"study_design_scores_gemma":[0.0000032065004,0.000007048111,0.00006600211,0.00015130686,0.000006525223,0.00021918128,0.00044657494,0.00209295,0.0009793404,0.42224255,0.573775,0.000010309492],"about_ca_topic_score_codex":0.0015706628,"about_ca_topic_score_gemma":0.002305846,"teacher_disagreement_score":0.0052917176,"about_ca_system_score_codex":0.00206214,"about_ca_system_score_gemma":0.0015111688,"threshold_uncertainty_score":0.01770258},"labels":[],"label_agreement":null},{"id":"W4240118341","doi":"10.1162/coli_r_00161","title":"Publications Received","year":2013,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","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","score_opus":0.027100620379252753,"score_gpt":0.27570986432487815,"score_spread":0.2486092439456254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240118341","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004646721,0.008873792,0.0013551482,0.0062841037,0.022974748,0.00022638582,0.007474007,0.0026445675,0.94970256],"genre_scores_gemma":[0.0012836859,0.0050272765,0.00084659754,0.002372196,0.0027457909,0.00007974408,0.005400378,0.0009410529,0.9813033],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99672854,0.00024385391,0.0002707038,0.00064487517,0.0018537253,0.00025839807],"domain_scores_gemma":[0.99386966,0.00047612286,0.00029472102,0.0008166378,0.003432193,0.0011105665],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014396989,0.0017503684,0.0018910266,0.004460081,0.0020912318,0.016135521,0.0023543513,0.0032262574,0.80928415],"category_scores_gemma":[0.00840755,0.00078706833,0.0012810248,0.0057807285,0.00086390047,0.007423947,0.004201639,0.003481594,0.84746933],"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":[0.000021851052,0.000028880933,0.000108418266,0.00036250002,0.0000067398055,0.00006994638,0.000044934415,0.00004498029,0.00021512869,0.0036175048,0.898413,0.09706603],"study_design_scores_gemma":[0.0000034847944,0.000008435983,0.000112616945,0.000116187795,0.0000022069626,0.0000707027,0.000026043354,0.000012871768,0.000048002486,0.0006502685,0.998944,0.0000051470843],"about_ca_topic_score_codex":0.0014542429,"about_ca_topic_score_gemma":0.0024559211,"teacher_disagreement_score":0.19071585,"about_ca_system_score_codex":0.002003154,"about_ca_system_score_gemma":0.003626665,"threshold_uncertainty_score":0.27203304},"labels":[],"label_agreement":null},{"id":"W4245430175","doi":"10.1162/coli_r_00117","title":"Publications Received","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Semantic Web and Ontologies","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":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.04609064291162508,"score_gpt":0.3010136732916446,"score_spread":0.2549230303800195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245430175","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047135545,0.009190298,0.0013743822,0.006729559,0.023295024,0.00021835993,0.008739651,0.0024783972,0.94750303],"genre_scores_gemma":[0.001472327,0.0056992876,0.00087993994,0.002443935,0.0028527165,0.000085400934,0.0066472394,0.0010183802,0.9789008],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962302,0.00030412825,0.00031800923,0.0007400173,0.0020996518,0.00030790197],"domain_scores_gemma":[0.9931379,0.0005668585,0.0003459083,0.0009753671,0.003715839,0.0012580787],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016599906,0.0018477961,0.0019415332,0.0047878684,0.0022311711,0.016974779,0.002450981,0.0033735025,0.80491704],"category_scores_gemma":[0.009736205,0.00079752563,0.0012864316,0.006438709,0.0009579335,0.00797632,0.0045500514,0.003489423,0.8368673],"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":[0.000024028968,0.000027070579,0.000117668205,0.00038218818,0.000007060631,0.0000727725,0.00005024279,0.00004646934,0.00020159791,0.004420797,0.9026265,0.0920236],"study_design_scores_gemma":[0.0000035012183,0.000008315246,0.00011586396,0.00011871162,0.0000022144773,0.00006833262,0.000027473767,0.000012716449,0.00004625266,0.000744416,0.9988471,0.000005133316],"about_ca_topic_score_codex":0.0016050532,"about_ca_topic_score_gemma":0.0027115366,"teacher_disagreement_score":0.19508296,"about_ca_system_score_codex":0.002228146,"about_ca_system_score_gemma":0.0039435783,"threshold_uncertainty_score":0.2782622},"labels":[],"label_agreement":null},{"id":"W4250326346","doi":"10.1162/coli_r_00106","title":"Briefly Noted","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Text and Document Classification Technologies","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","score_opus":0.028066313871546286,"score_gpt":0.2845006114861258,"score_spread":0.25643429761457953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250326346","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009761539,0.0069656773,0.011754706,0.011782077,0.017565561,0.00026357852,0.011206121,0.00380304,0.93568313],"genre_scores_gemma":[0.0045973603,0.0038592212,0.0052029975,0.0036989388,0.0017286413,0.00017510366,0.007398213,0.0015835712,0.97175604],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977049,0.00036702753,0.00022926285,0.0006009305,0.0008299167,0.00026790382],"domain_scores_gemma":[0.99760145,0.00036091602,0.00017464004,0.0005522084,0.0009494567,0.00036130758],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013804073,0.0014678815,0.001152048,0.0027471334,0.0027356967,0.009323098,0.0023482454,0.0028288027,0.61005485],"category_scores_gemma":[0.0070065884,0.00055365585,0.000996172,0.0044957073,0.0012422795,0.008018515,0.0045044012,0.0029058575,0.5779294],"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":[0.000040068608,0.00001935639,0.00025137662,0.00024551482,0.000007899786,0.0000657247,0.00022639941,0.00006459303,0.00022988881,0.04176563,0.860777,0.09630644],"study_design_scores_gemma":[0.0000021088258,0.000005285101,0.00009324764,0.000054291984,0.0000016519626,0.00004794729,0.000065505876,0.000022704817,0.000057337147,0.0023176202,0.9973283,0.000004052216],"about_ca_topic_score_codex":0.003938876,"about_ca_topic_score_gemma":0.0074574063,"teacher_disagreement_score":0.38994515,"about_ca_system_score_codex":0.0022390096,"about_ca_system_score_gemma":0.0028998316,"threshold_uncertainty_score":0.55620944},"labels":[],"label_agreement":null},{"id":"W4280632712","doi":"10.1162/coli_a_00447","title":"Noun2Verb: Probabilistic Frame Semantics for Word Class Conversion","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Verb; Principle of compositionality; Semantics (computer science); Programming language","score_opus":0.016793507886842647,"score_gpt":0.27922083496854416,"score_spread":0.2624273270817015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280632712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028870443,0.00006687344,0.9668657,0.00029019953,0.000041153235,0.000050556097,0.00024212325,0.0015608214,0.0020121853],"genre_scores_gemma":[0.75242186,0.00008956412,0.24486539,0.00014037141,0.00003687329,0.0002004268,0.0006064351,0.00034712598,0.0012919719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987594,0.00060870056,0.00005231245,0.00029488106,0.00021419016,0.0000706176],"domain_scores_gemma":[0.996763,0.0020529612,0.0002555358,0.00058079226,0.0002486709,0.0000989387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021152415,0.0005150759,0.0005936728,0.00066505297,0.0007021105,0.001746831,0.0022771172,0.00096492446,0.005434425],"category_scores_gemma":[0.00824252,0.0005531334,0.001310401,0.00050091685,0.0018795271,0.003441574,0.0017818833,0.0017617716,0.0006006217],"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":[0.00035142316,0.00021777264,0.0033558707,0.00023173357,0.000113160015,0.0003975972,0.0015436512,0.36813393,0.012723621,0.48363134,0.0061385483,0.12316136],"study_design_scores_gemma":[0.000018148177,0.000024527964,0.00027725802,0.000008795659,0.0000069689295,0.000049634396,0.000042983265,0.87788206,0.0013000536,0.11868253,0.0016926249,0.000014460242],"about_ca_topic_score_codex":0.0075375643,"about_ca_topic_score_gemma":0.0077747884,"teacher_disagreement_score":0.0075375643,"about_ca_system_score_codex":0.0012881339,"about_ca_system_score_gemma":0.0010994215,"threshold_uncertainty_score":0.018179953},"labels":[],"label_agreement":null},{"id":"W4383822224","doi":"10.1162/coli_a_00485","title":"Obituary: Yorick Wilks","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","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":"Obituary; Computer science; Philosophy; Theology","score_opus":0.06742586085169608,"score_gpt":0.41015240737440634,"score_spread":0.3427265465227103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383822224","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007011048,0.03251196,0.0005918498,0.29408517,0.5011037,0.00007482895,0.0016245398,0.0009545474,0.16835228],"genre_scores_gemma":[0.004765656,0.008866462,0.00022202362,0.05747,0.05275971,0.00005826013,0.00080112874,0.00048842985,0.8745683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902916,0.00015986589,0.00007102779,0.0002332241,0.00037296236,0.00013378853],"domain_scores_gemma":[0.99769443,0.0004282099,0.00017498326,0.00016267173,0.0011177802,0.0004219223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010666304,0.001038211,0.0009160322,0.0011437301,0.0032087073,0.0042972816,0.0009927778,0.0034664385,0.1877274],"category_scores_gemma":[0.0077583482,0.00046121443,0.00052299694,0.0006564201,0.0010239664,0.0032598982,0.0026395556,0.0063955407,0.15804423],"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":[0.000010229127,0.0000023057223,0.000020933294,0.00001921231,9.684497e-7,0.000033898763,0.000018708539,0.0000050261037,0.000022087204,0.00040108073,0.9962471,0.0032184818],"study_design_scores_gemma":[0.0000019312388,0.0000037754924,0.00008493145,0.000059585334,9.5135135e-7,0.000050971583,0.000041339503,0.00000867052,0.000041647047,0.0001504465,0.99955267,0.0000030255023],"about_ca_topic_score_codex":0.0057875235,"about_ca_topic_score_gemma":0.008839944,"teacher_disagreement_score":0.1877274,"about_ca_system_score_codex":0.001790916,"about_ca_system_score_gemma":0.0016518208,"threshold_uncertainty_score":0.62801075},"labels":[],"label_agreement":null},{"id":"W4389613952","doi":"10.1162/coli_a_00501","title":"Stance Detection with Explanations","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","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 British Columbia","funders":"","keywords":"Computer science; Automatic summarization; Artificial intelligence; Parsing; Benchmark (surveying); Machine learning; Focus (optics); Grammaticality; Natural language processing; Linguistics","score_opus":0.02863169177005188,"score_gpt":0.26809391849028813,"score_spread":0.23946222672023626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389613952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20961457,0.0063972846,0.7385594,0.0026578805,0.00046234723,0.0006710536,0.013786606,0.017654693,0.0101961475],"genre_scores_gemma":[0.7088115,0.0008199917,0.27216762,0.00024136434,0.0003297065,0.00019967381,0.01473169,0.00025389914,0.0024444666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998616,0.00043149356,0.00012332093,0.00032235926,0.00040176362,0.000105036284],"domain_scores_gemma":[0.99119663,0.0052050115,0.001311971,0.00077143934,0.0012927842,0.00022224338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014555064,0.001054901,0.00055490684,0.0085789375,0.0006047592,0.0013616158,0.0009264894,0.0015860912,0.0027081114],"category_scores_gemma":[0.014499505,0.0003262233,0.0009229287,0.00267564,0.00047285963,0.0024262434,0.0013662721,0.001457186,0.0018410209],"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":[0.00084614847,0.00028005816,0.047922954,0.001342828,0.00031059803,0.0011594258,0.0012107486,0.024347538,0.01736165,0.01881768,0.03806642,0.8483339],"study_design_scores_gemma":[0.00008834033,0.00021426297,0.015914274,0.0004342632,0.00022324873,0.0007338021,0.00067671324,0.8560657,0.024208313,0.06648106,0.03488279,0.0000772199],"about_ca_topic_score_codex":0.0013218989,"about_ca_topic_score_gemma":0.0019064323,"teacher_disagreement_score":0.0085789375,"about_ca_system_score_codex":0.00059509446,"about_ca_system_score_gemma":0.0010078653,"threshold_uncertainty_score":0.009059548},"labels":[],"label_agreement":null},{"id":"W4391017630","doi":"10.1162/coli_a_00510","title":"Context-aware Transliteration of Romanized South Asian Languages","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"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":"Institute for Catastrophic Loss Reduction","keywords":"Transliteration; Computer science; Romanization; Natural language processing; Context (archaeology); Artificial intelligence; Sentence; Word (group theory); Linguistics; History","score_opus":0.01638905617639773,"score_gpt":0.29555217385449595,"score_spread":0.2791631176780982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391017630","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7515755,0.004817926,0.1586324,0.0013041827,0.0015821299,0.0005128802,0.01262435,0.052764576,0.016186018],"genre_scores_gemma":[0.85275126,0.0008536799,0.108624965,0.00037336024,0.00020311454,0.00022335847,0.027539866,0.0015277937,0.007902643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985709,0.00049016613,0.00014057387,0.00057207246,0.00011351388,0.0001127341],"domain_scores_gemma":[0.99709725,0.0011616655,0.00019828016,0.000694044,0.0007234067,0.00012532703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014278732,0.001698411,0.0011612235,0.0010408731,0.0009955268,0.0012615751,0.0011229011,0.00071162835,0.0056648157],"category_scores_gemma":[0.0056190076,0.00038991374,0.0011655283,0.00088627136,0.0004469261,0.0019470396,0.0021127567,0.0016467762,0.006483205],"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":[0.0017993454,0.00036606137,0.01171306,0.0022092555,0.00059496757,0.001829821,0.0021872912,0.054054983,0.06950298,0.0019801315,0.044878058,0.808884],"study_design_scores_gemma":[0.00032474077,0.00076223054,0.015092881,0.00037225106,0.0007037601,0.0016888913,0.0033201973,0.6984207,0.19458543,0.007834885,0.07663178,0.00026234981],"about_ca_topic_score_codex":0.007757365,"about_ca_topic_score_gemma":0.013982844,"teacher_disagreement_score":0.007757365,"about_ca_system_score_codex":0.00080582325,"about_ca_system_score_gemma":0.001420765,"threshold_uncertainty_score":0.0189507},"labels":[],"label_agreement":null},{"id":"W4392367355","doi":"10.1162/coli_a_00512","title":"A Novel Alignment-based Approach for PARSEVAL Measuress","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing 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":"Computer science; Parsing; Sentence; Natural language processing; Artificial intelligence; Lexical analysis; Parseval's theorem; Machine translation; Word (group theory); Linguistics","score_opus":0.055118956961616714,"score_gpt":0.3166822825463177,"score_spread":0.26156332558470097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392367355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030356308,0.000096251264,0.99321496,0.00005673958,0.000041871426,0.00007835103,0.00011804564,0.0025008132,0.0008572582],"genre_scores_gemma":[0.074866384,0.000058048874,0.9228679,0.00005621077,0.0000668062,0.00030440217,0.0003279857,0.00095134997,0.0005009735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97773224,0.008279352,0.0024966216,0.0030246873,0.007912829,0.0005543766],"domain_scores_gemma":[0.96939653,0.0110075725,0.0023374509,0.006130014,0.010565776,0.0005626985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012469096,0.0018520508,0.0016846322,0.008922711,0.0014896762,0.006395544,0.0033589208,0.0017103471,0.00350377],"category_scores_gemma":[0.06463953,0.0009641323,0.0014111028,0.005906713,0.001942964,0.0057391836,0.0036089986,0.003224266,0.002086804],"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":[0.00034309123,0.00023314399,0.0062838458,0.00042605426,0.000276684,0.00015342321,0.00083402864,0.037479386,0.027265357,0.17481688,0.008157616,0.7437305],"study_design_scores_gemma":[0.00004753155,0.00031385053,0.0035115806,0.00013935649,0.00011289986,0.00045894235,0.0001682673,0.78897065,0.03853088,0.14590667,0.021652197,0.00018720087],"about_ca_topic_score_codex":0.0016745699,"about_ca_topic_score_gemma":0.0015531679,"teacher_disagreement_score":0.012469096,"about_ca_system_score_codex":0.0018963577,"about_ca_system_score_gemma":0.0019688031,"threshold_uncertainty_score":0.06594366},"labels":[],"label_agreement":null},{"id":"W4401117478","doi":"10.1162/coli_a_00533","title":"Exploring Temporal Sensitivity in the Brain Using Multi-timescale Language Models: An EEG Decoding Study","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Cognitive Science and Mapping","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":"Electroencephalography; Decoding methods; Sensitivity (control systems); Computer science; Language model; Speech recognition; Artificial intelligence; Psychology; Neuroscience; Algorithm","score_opus":0.2609003131987414,"score_gpt":0.37658984532571577,"score_spread":0.11568953212697436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401117478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8839622,0.0011146878,0.10969015,0.00064343715,0.000091063055,0.000062971274,0.0013435158,0.00041809047,0.0026739344],"genre_scores_gemma":[0.9913271,0.0002900843,0.0072366497,0.000036603582,0.000038672188,0.000021056145,0.00049598736,0.000050755352,0.0005030179],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99983835,0.000065409164,0.000008111284,0.000045642013,0.000023825047,0.000018672356],"domain_scores_gemma":[0.9988267,0.000895798,0.00008243828,0.00006748711,0.00009689058,0.000030654068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005509623,0.00042053353,0.00025542374,0.00034407686,0.000097578064,0.0005623199,0.00025404495,0.00032900617,0.0018945211],"category_scores_gemma":[0.005558606,0.0001660008,0.00039105825,0.0004713114,0.0002768536,0.0006570507,0.00037888216,0.00083315885,0.00044437824],"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":[0.002070166,0.0005948612,0.056154847,0.0009943305,0.0006450095,0.0014889285,0.0020342865,0.28459746,0.2877164,0.0073383916,0.008461322,0.347904],"study_design_scores_gemma":[0.00004433974,0.00019935812,0.052409004,0.00005596789,0.00009923266,0.00031832253,0.00023371876,0.9239294,0.013557109,0.0074166628,0.0016891615,0.000047778645],"about_ca_topic_score_codex":0.0017443117,"about_ca_topic_score_gemma":0.0017869261,"teacher_disagreement_score":0.0018945211,"about_ca_system_score_codex":0.00015559494,"about_ca_system_score_gemma":0.00014477124,"threshold_uncertainty_score":0.0063378215},"labels":[],"label_agreement":null},{"id":"W4404534114","doi":"10.1162/coli_a_00545","title":"The Emergence of Chunking Structures with Hierarchical RNN","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Time Series Analysis and Forecasting","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":"Canadian Institute for Advanced Research; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; University of Alberta; DeepMind; Canadian Institute for Advanced Research","keywords":"Chunking (psychology); Computer science; Natural language processing; Artificial intelligence","score_opus":0.011301540709767867,"score_gpt":0.25126442258731396,"score_spread":0.2399628818775461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404534114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30397865,0.00046112624,0.690044,0.0003303658,0.00007045723,0.000060955943,0.00016437964,0.0022442187,0.002645939],"genre_scores_gemma":[0.9241479,0.00007578524,0.07441155,0.00005355646,0.00001982676,0.000035779296,0.00018419545,0.000091146845,0.0009802143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966633,0.00014040997,0.000019769477,0.00009687729,0.000042294432,0.000034305176],"domain_scores_gemma":[0.9976941,0.001381743,0.00021853989,0.00034509954,0.00030260146,0.000057948626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010136898,0.00042753117,0.00034892446,0.00035179898,0.00027442852,0.00038963134,0.0007326315,0.00041641688,0.0006241936],"category_scores_gemma":[0.004698767,0.00035895282,0.00030998717,0.0003281898,0.0005431269,0.0010668234,0.0005416692,0.0009429739,0.00024056213],"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":[0.00026750413,0.000105032675,0.005610714,0.00011884306,0.0001300684,0.00034251894,0.00059962046,0.7366472,0.05130839,0.0143321045,0.0025955967,0.18794248],"study_design_scores_gemma":[0.0000022029485,0.000012860702,0.000335199,0.0000026323282,0.0000043610858,0.000006778898,0.00000710711,0.994451,0.0022309783,0.0028184126,0.00012523866,0.000003211351],"about_ca_topic_score_codex":0.006840246,"about_ca_topic_score_gemma":0.007987703,"teacher_disagreement_score":0.006840246,"about_ca_system_score_codex":0.000676911,"about_ca_system_score_gemma":0.000516836,"threshold_uncertainty_score":0.013600886},"labels":[],"label_agreement":null},{"id":"W4412158322","doi":"10.1162/coli.a.16","title":"🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":142,"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 Waterloo","funders":"","keywords":"Siren (mythology); Computer science; Natural language processing; Linguistics; Art; Literature; Philosophy","score_opus":0.025782207768242967,"score_gpt":0.34966651908309326,"score_spread":0.3238843113148503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412158322","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06632197,0.27676377,0.61890465,0.012932299,0.0006774334,0.00032264012,0.00078516226,0.0038781746,0.019413855],"genre_scores_gemma":[0.6460825,0.16895193,0.17255731,0.0030151396,0.002313291,0.00026809343,0.0022597478,0.0009694088,0.0035826336],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969144,0.0017135331,0.00023647565,0.00032172745,0.00071792473,0.00009593038],"domain_scores_gemma":[0.96860045,0.026398113,0.0008496669,0.0016591229,0.0021124976,0.00038006774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051402086,0.00084928126,0.0010627427,0.0023668173,0.00049342954,0.0031753576,0.0015975077,0.0011483572,0.0015866387],"category_scores_gemma":[0.027835816,0.0005104649,0.00079319224,0.0020564054,0.0013669515,0.00486848,0.002398461,0.0022182062,0.00069715624],"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":[0.0002802013,0.00024147377,0.013776349,0.0036675723,0.00043076737,0.0005135548,0.00196258,0.06499913,0.00274424,0.038214847,0.018154247,0.85501504],"study_design_scores_gemma":[0.000060289483,0.00047750163,0.0062487605,0.0025051564,0.00026598354,0.0013887327,0.0023711717,0.6917969,0.0066585494,0.15583736,0.13218834,0.00020126511],"about_ca_topic_score_codex":0.003482481,"about_ca_topic_score_gemma":0.0028080186,"teacher_disagreement_score":0.0051402086,"about_ca_system_score_codex":0.00077392685,"about_ca_system_score_gemma":0.0013348407,"threshold_uncertainty_score":0.027184367},"labels":[],"label_agreement":null},{"id":"W4414596705","doi":"10.1162/coli.a.24","title":"Are Formal and Functional Linguistic Mechanisms Dissociated in Language Models?","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","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":"Azrieli Foundation; Universiteit van Amsterdam; European Commission; Open Philanthropy Project","keywords":"Set (abstract data type); Formal language; Task (project management); Formal system; Theory; Formal methods; Functional approach","score_opus":0.021967691500343927,"score_gpt":0.2635182464301234,"score_spread":0.24155055492977948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414596705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6523574,0.00057418476,0.3280158,0.002760065,0.00003727314,0.0000704815,0.00022878153,0.0009901022,0.014965886],"genre_scores_gemma":[0.9872378,0.000077751654,0.011771262,0.00011281749,0.000013472778,0.000040096475,0.00011900502,0.000089129455,0.0005388161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985482,0.0007133334,0.00007650834,0.00032345275,0.00019863897,0.00013976771],"domain_scores_gemma":[0.9933427,0.0032976368,0.00087588717,0.0016784531,0.00040667655,0.0003986343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026526998,0.00044504722,0.0007367321,0.00087459857,0.00045826443,0.0034455915,0.0015527968,0.0010387276,0.003628073],"category_scores_gemma":[0.014960797,0.0006263213,0.00074595184,0.0005182076,0.003406756,0.009005756,0.0028599696,0.0018080496,0.0005069661],"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":[0.0007810328,0.00040134552,0.033328976,0.0006706572,0.00059678534,0.0002973386,0.0053968877,0.1093069,0.05453371,0.6447084,0.0019530532,0.14802492],"study_design_scores_gemma":[0.00006951888,0.0001260648,0.014178028,0.000052354335,0.00008999861,0.0001745281,0.00067222473,0.2524191,0.0058903047,0.7246602,0.0016060346,0.0000616939],"about_ca_topic_score_codex":0.0012547192,"about_ca_topic_score_gemma":0.0010854929,"teacher_disagreement_score":0.003628073,"about_ca_system_score_codex":0.0009596312,"about_ca_system_score_gemma":0.000721395,"threshold_uncertainty_score":0.014029026},"labels":[],"label_agreement":null},{"id":"W4416872671","doi":"10.1162/coli.a.583","title":"LLMs and Cultural Values: The Impact of Prompt Language and Explicit Cultural Framing","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","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":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Canada First Research Excellence Fund","keywords":"Framing (construction); Cultural diversity; Cultural values; Cultural bias; Hofstede's cultural dimensions theory; Perspective (graphical); Set (abstract data type); Cultural issues; Cultural psychology","score_opus":0.031044744766767877,"score_gpt":0.43185472382640566,"score_spread":0.4008099790596378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416872671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97961557,0.0003008916,0.013299672,0.000660287,0.00007517185,0.00013816978,0.0004281821,0.00013749678,0.0053445566],"genre_scores_gemma":[0.9951663,0.00005831769,0.0040115905,0.00012947676,0.0000132526175,0.00011206124,0.00024873353,0.00004131433,0.0002188903],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93296975,0.05893893,0.0017244201,0.0032027417,0.0024518094,0.00071227876],"domain_scores_gemma":[0.5311048,0.43486682,0.012752186,0.014744449,0.0049765413,0.0015551586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047098335,0.0010331642,0.00067696284,0.00097174227,0.000883093,0.0054226955,0.0007642927,0.0010843591,0.0046834447],"category_scores_gemma":[0.2376297,0.00046757222,0.00090062723,0.0015994976,0.0022112792,0.0039369273,0.0038940108,0.0025836308,0.0006597272],"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":[0.0044373414,0.00084534584,0.72667855,0.0019504082,0.00084685,0.0005828952,0.06991451,0.018698268,0.0077138115,0.011062684,0.00339927,0.15387008],"study_design_scores_gemma":[0.0005302024,0.0037109863,0.6349207,0.003283108,0.0016884592,0.00071803865,0.13157317,0.12818293,0.017091097,0.04536349,0.032278832,0.00065891695],"about_ca_topic_score_codex":0.0024654896,"about_ca_topic_score_gemma":0.0021955476,"teacher_disagreement_score":0.047098335,"about_ca_system_score_codex":0.0015451293,"about_ca_system_score_gemma":0.0013824411,"threshold_uncertainty_score":0.2490828},"labels":[],"label_agreement":null}]}