{"meta":{"query_hash":"ce48bc7d526f","filters":{"venue":"Linguistics Vanguard"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"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/ce48bc7d526f","api":"https://metacan.xera.ac/api/v1/cohort?venue=Linguistics+Vanguard"},"results":[{"id":"W2030992269","doi":"10.1515/lingvan-2014-1008","title":"Language structure and social agency: Confirming polar questions in conversation","year":2015,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Semiotics; Linguistics; Conversation; Agency (philosophy); Repetition (rhetorical device); Function (biology); Conversation analysis; Selection (genetic algorithm); Computer science; Epistemology; Psychology; Artificial intelligence; Philosophy","score_opus":0.04871211242979754,"score_gpt":0.30793624629591115,"score_spread":0.2592241338661136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030992269","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":[0.824407,0.00032966066,0.0672528,0.0037657628,0.00005486226,0.00013153144,0.000056516503,0.000239031,0.103762925],"genre_scores_gemma":[0.99729544,0.000023042834,0.0019090123,0.00006521786,0.000008028803,0.000015110705,0.000007624998,0.000015502157,0.0006609473],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9687845,0.026701901,0.00063268957,0.00130387,0.0015780191,0.0009991266],"domain_scores_gemma":[0.963883,0.02672344,0.0037344773,0.0024182885,0.0026652825,0.0005754526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012697965,0.000446195,0.0004167997,0.0019091815,0.0048344685,0.00604977,0.00094713294,0.002544777,0.0041891965],"category_scores_gemma":[0.029789057,0.0005085238,0.00052517495,0.0010274701,0.01544965,0.007840525,0.0051480616,0.0018863272,0.00058893254],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037968063,0.0000947983,0.012939321,0.00028426773,0.000059336726,0.002352497,0.4928533,0.0014689006,0.021481883,0.44189134,0.0008490581,0.025345588],"study_design_scores_gemma":[0.00012886831,0.0005868487,0.027377527,0.00055049267,0.00018102322,0.0026672217,0.5106375,0.015526805,0.026704188,0.31604648,0.09922816,0.00036488983],"about_ca_topic_score_codex":0.003940444,"about_ca_topic_score_gemma":0.002563887,"teacher_disagreement_score":0.012697965,"about_ca_system_score_codex":0.0023152044,"about_ca_system_score_gemma":0.0012308006,"threshold_uncertainty_score":0.06715405},"labels":[],"label_agreement":null},{"id":"W2335647126","doi":"10.1515/lingvan-2015-0010","title":"An evaluation of noise on LPC-based vowel formant estimates: Implications for sociolinguistic data collection","year":2016,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formant; Spurious relationship; Noise (video); Vowel; Computer science; Speech recognition; Data collection; SIGNAL (programming language); Interference (communication); Acoustics; Telecommunications; Artificial intelligence; Mathematics; Statistics; Physics; Machine learning","score_opus":0.15644486285609407,"score_gpt":0.44929474008707243,"score_spread":0.29284987723097833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335647126","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":[0.94803905,0.00019844543,0.048857186,0.00010174969,0.00005075546,0.00033098581,0.00028311365,0.00024203295,0.0018966737],"genre_scores_gemma":[0.947252,0.00012573089,0.05115393,0.00006947851,0.000042785043,0.00042038996,0.00026954498,0.00015306563,0.0005131041],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9843269,0.010361389,0.00076631445,0.0011240757,0.0031986535,0.00022264419],"domain_scores_gemma":[0.87764764,0.103476085,0.0032123928,0.0049820105,0.010002719,0.00067914097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014020822,0.0007251253,0.00070397713,0.0009049243,0.0009377183,0.0015270159,0.00089525856,0.0008698169,0.0013992005],"category_scores_gemma":[0.07671409,0.00042944402,0.00047440478,0.00082680857,0.0015544987,0.00096062326,0.001264955,0.0004924449,0.00043739323],"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":[0.024566855,0.0020369717,0.11922379,0.0015236046,0.0004958719,0.00067348336,0.013439117,0.020861695,0.543291,0.001503166,0.00073936157,0.27164513],"study_design_scores_gemma":[0.0003472313,0.016724003,0.64840895,0.00020072167,0.00056276744,0.0007719486,0.004747114,0.038240913,0.28486207,0.0015697309,0.0031341834,0.00043044562],"about_ca_topic_score_codex":0.003520458,"about_ca_topic_score_gemma":0.004535027,"teacher_disagreement_score":0.014020822,"about_ca_system_score_codex":0.0005886326,"about_ca_system_score_gemma":0.00045471042,"threshold_uncertainty_score":0.074150026},"labels":[],"label_agreement":null},{"id":"W2565228806","doi":"10.1515/lingvan-2015-0012","title":"Extending ELAN into variationist sociolinguistics","year":2015,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Coding (social sciences); Transcription (linguistics); Linguistics; Natural language processing; Statistics; Mathematics","score_opus":0.056065576894293756,"score_gpt":0.3702220372922769,"score_spread":0.3141564603979831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565228806","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":[0.01092568,0.00021956995,0.93154794,0.0011054715,0.00013152599,0.00030976196,0.0011450145,0.003050483,0.05156449],"genre_scores_gemma":[0.12743491,0.00027576313,0.86049527,0.00034123685,0.000084261315,0.0010305627,0.0014567231,0.001511881,0.007369409],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865116,0.010483048,0.0005425039,0.0011369414,0.0011460808,0.00017993528],"domain_scores_gemma":[0.97684324,0.016816895,0.0006321949,0.0036714226,0.0018118856,0.00022431005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012604666,0.0009592381,0.0006779068,0.004715949,0.0018490296,0.0047364635,0.0021485363,0.0005693791,0.016854692],"category_scores_gemma":[0.021763997,0.0006948814,0.0005856524,0.003165684,0.00388926,0.005703627,0.007214288,0.0028740622,0.0033431514],"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":[0.00012898886,0.00011296679,0.0016746047,0.0006859301,0.000046889098,0.00045178356,0.046003282,0.0032947322,0.0031872182,0.46416909,0.01510969,0.46513477],"study_design_scores_gemma":[0.000036649348,0.00006349389,0.0036289103,0.0008081776,0.000027976546,0.0005295522,0.008195458,0.032427687,0.003753124,0.50628614,0.44413683,0.00010593388],"about_ca_topic_score_codex":0.002561207,"about_ca_topic_score_gemma":0.0052227606,"teacher_disagreement_score":0.016854692,"about_ca_system_score_codex":0.0025056931,"about_ca_system_score_gemma":0.0018731465,"threshold_uncertainty_score":0.06666064},"labels":[],"label_agreement":null},{"id":"W2590027471","doi":"10.1515/lingvan-2016-0025","title":"Individual differences in second language speech perception across tasks and contrasts: The case of English vowel contrasts by Korean learners","year":2017,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Santé, Sciences Biologiques et Chimie du Vivant","keywords":"Psychology; Perception; Vowel; Formant; Weighting; Task (project management); Contrast (vision); Duration (music); Cognitive psychology; Speech perception; Natural (archaeology); Two-alternative forced choice; American English; Linguistics; Speech recognition; Computer science; Artificial intelligence","score_opus":0.028228791811886523,"score_gpt":0.35821914850801334,"score_spread":0.3299903566961268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590027471","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":[0.9997955,0.000011321124,0.00006210061,0.000002584184,6.9138764e-7,0.0000016714527,0.000009837932,0.0000015694748,0.00011466153],"genre_scores_gemma":[0.99966216,0.000013079415,0.000109073895,0.0000050717517,6.8818935e-7,0.0000039790034,0.00002112323,0.000002949942,0.00018190297],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999619,0.00007804642,0.00004657996,0.00010404517,0.00010303198,0.00004924533],"domain_scores_gemma":[0.99692243,0.0013271245,0.00065950723,0.00030700397,0.00045828213,0.00032565722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079583534,0.00032740322,0.00028767105,0.00049707625,0.00022415741,0.00096883264,0.00017424302,0.0003552296,0.0014301131],"category_scores_gemma":[0.0039382083,0.00024707193,0.00023472167,0.0002170927,0.00045951566,0.00053828955,0.0005949399,0.0003820305,0.00034076624],"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":[0.0011762338,0.00045206008,0.7381172,0.00010339606,0.00018994388,0.00071354234,0.017276185,0.0005957854,0.2191431,0.0001684756,0.0001701698,0.021893779],"study_design_scores_gemma":[0.000015603413,0.0006729399,0.97424954,0.000011374306,0.000042334297,0.00092387403,0.006114316,0.0011097469,0.016220303,0.00016247969,0.00043476094,0.00004280351],"about_ca_topic_score_codex":0.0013430958,"about_ca_topic_score_gemma":0.0016489052,"teacher_disagreement_score":0.0014301131,"about_ca_system_score_codex":0.00013739314,"about_ca_system_score_gemma":0.00013535225,"threshold_uncertainty_score":0.0047842264},"labels":[],"label_agreement":null},{"id":"W2609372572","doi":"10.1515/lingvan-2015-0032","title":"Is <i>like</i> like <i>like</i>?: Evaluating the same variant across multiple variables","year":2017,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":35,"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":"Salient; Meaning (existential); Variation (astronomy); Perception; Linguistics; Psychology; Variable (mathematics); Verb; Perspective (graphical); Transitive relation; Cognitive psychology; Social psychology; Mathematics; Computer science","score_opus":0.07200595367626476,"score_gpt":0.39841300019539977,"score_spread":0.326407046519135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609372572","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":[0.98474044,0.000067724824,0.0036083083,0.000076871635,0.000011812201,0.0000128250185,0.000041593183,0.00002013142,0.011420191],"genre_scores_gemma":[0.99908626,0.0000150167125,0.0006788966,0.0000131687,0.000002729931,0.000003717943,0.000025432379,0.000010914051,0.00016374709],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983681,0.0008230313,0.00008300823,0.000292364,0.0003323044,0.00010130073],"domain_scores_gemma":[0.99027866,0.0054930174,0.0015462047,0.0010661804,0.0012770802,0.00033880654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026783082,0.0001822884,0.0002660666,0.0007649915,0.00061433756,0.0027277467,0.00039389858,0.0005687171,0.0023325535],"category_scores_gemma":[0.012859619,0.00013879738,0.00020075058,0.00067549513,0.0021711034,0.002439566,0.0010744004,0.0006633141,0.00025391832],"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":[0.0023859697,0.0002720101,0.46076974,0.0005634681,0.00028609825,0.0012879145,0.15488523,0.0018118613,0.2148962,0.0506091,0.00095412025,0.11127838],"study_design_scores_gemma":[0.00004018796,0.0009296733,0.81031716,0.00013208226,0.00024606352,0.001683649,0.11334726,0.009558477,0.02622245,0.026924167,0.010334971,0.00026384287],"about_ca_topic_score_codex":0.0019113726,"about_ca_topic_score_gemma":0.0020324055,"teacher_disagreement_score":0.0027277467,"about_ca_system_score_codex":0.00050524296,"about_ca_system_score_gemma":0.00022404522,"threshold_uncertainty_score":0.014164388},"labels":[],"label_agreement":null},{"id":"W2800761643","doi":"10.1515/lingvan-2016-0081","title":"The syntax-prosody interface: current theoretical approaches and outstanding questions","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","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":"Prosody; Syntax; Interface (matter); Linguistics; Computer science; Situated; Field (mathematics); Natural language processing; Recursion (computer science); Current (fluid); Artificial intelligence; Programming language; Physics; Mathematics; Speech recognition; Philosophy","score_opus":0.06771065085330953,"score_gpt":0.40110145685154186,"score_spread":0.33339080599823234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800761643","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":[0.044542633,0.5300721,0.11642693,0.18414396,0.0019712858,0.00006319904,0.00024593767,0.000413975,0.12212003],"genre_scores_gemma":[0.7502141,0.19809026,0.03274493,0.00777447,0.006002003,0.00022004388,0.00019724436,0.0001851173,0.004571835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99560636,0.0021850676,0.00026734822,0.00082135404,0.0008127448,0.00030705662],"domain_scores_gemma":[0.9820325,0.013511054,0.0009723061,0.0012607975,0.0016603402,0.0005628674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014062271,0.00092744856,0.0016743188,0.0052879513,0.0023151713,0.017782496,0.004182697,0.0053035123,0.0076885605],"category_scores_gemma":[0.011143252,0.0010395097,0.000657611,0.0042663217,0.033928443,0.028750869,0.005484027,0.00848369,0.0016679515],"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":[0.000037167432,0.000045744106,0.0004685378,0.0003800627,0.000017221886,0.000035913763,0.0012848225,0.0005088118,0.00016186172,0.9628197,0.0011462915,0.033093873],"study_design_scores_gemma":[0.0000064310407,0.000021564607,0.0004074614,0.00048066193,0.000009926594,0.00004982224,0.002000719,0.0020061722,0.00013478458,0.9833875,0.011474497,0.000020500309],"about_ca_topic_score_codex":0.001943418,"about_ca_topic_score_gemma":0.0012285688,"teacher_disagreement_score":0.017782496,"about_ca_system_score_codex":0.00382577,"about_ca_system_score_gemma":0.0038576184,"threshold_uncertainty_score":0.07436931},"labels":[],"label_agreement":null},{"id":"W2885411231","doi":"10.1515/lingvan-2017-0018","title":"Practice makes perfect: the consequences of lexical proficiency for articulation","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Deutsche Forschungsgemeinschaft","keywords":"Coarticulation; Articulation (sociology); Speech recognition; Linguistics; Psychology; Computer science; Speech production; Cognitive psychology; Constraint (computer-aided design); Mathematics; Vowel","score_opus":0.06326567726277735,"score_gpt":0.43677603788864966,"score_spread":0.3735103606258723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885411231","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":[0.99749017,0.000058419933,0.00090452284,0.000051272105,0.0000027067124,0.0000055650216,0.000030803996,0.000008554237,0.0014479212],"genre_scores_gemma":[0.99959046,0.000013873681,0.00027227527,0.000009561175,0.0000016694087,0.0000035438109,0.0000116778765,0.000005187247,0.00009171497],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99882656,0.00041112668,0.00010226064,0.00030159502,0.0002207741,0.00013768786],"domain_scores_gemma":[0.98238695,0.012940118,0.0023421706,0.0010205917,0.00051625195,0.0007939508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014101202,0.00020499261,0.00027785182,0.0003918047,0.00030112982,0.0016787116,0.0003309472,0.0006752895,0.004248402],"category_scores_gemma":[0.02434888,0.00027227635,0.00014447985,0.00032061143,0.001164825,0.0009481388,0.0011800718,0.0004978516,0.00030585908],"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":[0.003022701,0.0010401183,0.55021584,0.00048804257,0.0002466077,0.0022041828,0.010980712,0.0069022393,0.3290694,0.00458603,0.00036517924,0.09087897],"study_design_scores_gemma":[0.000038722825,0.00090086315,0.9780508,0.000053848606,0.000049804952,0.0005027688,0.0029644188,0.004140926,0.008062814,0.0045772903,0.00061959005,0.000038183178],"about_ca_topic_score_codex":0.0009939219,"about_ca_topic_score_gemma":0.0010089393,"teacher_disagreement_score":0.004248402,"about_ca_system_score_codex":0.00027362956,"about_ca_system_score_gemma":0.00025340993,"threshold_uncertainty_score":0.01421237},"labels":[],"label_agreement":null},{"id":"W2892039495","doi":"10.1515/lingvan-2017-0027","title":"The role of predictability in shaping phonological patterns","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":108,"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":"Predictability; Context (archaeology); Computer science; Set (abstract data type); Comprehension; Reduction (mathematics); Cognitive psychology; Linguistics; Natural language processing; Psychology; Mathematics; Statistics; History","score_opus":0.04052652632450414,"score_gpt":0.3620769572044678,"score_spread":0.32155043087996366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892039495","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":[0.8617993,0.003009979,0.105682604,0.0011940541,0.000091275346,0.000031359326,0.00027550786,0.0003884231,0.02752764],"genre_scores_gemma":[0.9966852,0.000303681,0.0026605402,0.00003737034,0.000016817952,0.000004068521,0.00002049871,0.00003301855,0.00023875326],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993755,0.00022644374,0.00004316968,0.00014144658,0.00016025476,0.000053264797],"domain_scores_gemma":[0.99534434,0.002978967,0.00081268884,0.00033477828,0.00041118902,0.000118093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284488,0.00018315321,0.00023408871,0.00088586734,0.00034381324,0.0021996265,0.0003783368,0.0004732226,0.0020316385],"category_scores_gemma":[0.00922686,0.00037257854,0.00023817149,0.0005374508,0.001863825,0.0019226547,0.0009356238,0.00077298185,0.00035072787],"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":[0.00068440655,0.00014140988,0.302263,0.0011224407,0.00047585493,0.0015551002,0.006323581,0.040338892,0.13934994,0.17959112,0.0026604612,0.3254938],"study_design_scores_gemma":[0.00003441499,0.00024379166,0.47220635,0.00026886968,0.00018265388,0.00086484506,0.0015478035,0.05999786,0.016718313,0.43803066,0.009697301,0.0002070863],"about_ca_topic_score_codex":0.0015614659,"about_ca_topic_score_gemma":0.0017713365,"teacher_disagreement_score":0.0021996265,"about_ca_system_score_codex":0.000387519,"about_ca_system_score_gemma":0.00039116057,"threshold_uncertainty_score":0.006796479},"labels":[],"label_agreement":null},{"id":"W3092479361","doi":"10.1515/lingvan-2018-0068","title":"<i>I feel like</i> and <i>it feels like</i>: Two paths to the emergence of epistemic markers","year":2020,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":1,"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":"Complementizer; Preference; Variation (astronomy); Collocation (remote sensing); Vernacular; Persistence (discontinuity); Value (mathematics); Envelope (radar); Psychology; Epistemology; Linguistics; Philosophy; Computer science; Mathematics; Statistics; Syntax; Physics","score_opus":0.02804845608191886,"score_gpt":0.3099939949485337,"score_spread":0.28194553886661483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092479361","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":[0.8280145,0.00045911412,0.015803719,0.0023306345,0.000054350792,0.00004690723,0.000085549764,0.000072484276,0.15313275],"genre_scores_gemma":[0.9973917,0.00004592534,0.0012319966,0.00005189016,0.0000036931071,0.000006226484,0.000016072523,0.000026279757,0.0012262564],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9987877,0.00044802096,0.000032589385,0.00023272698,0.00027054406,0.0002284299],"domain_scores_gemma":[0.9971343,0.0011738337,0.00036285125,0.0003497544,0.0006729613,0.0003062375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001538128,0.00020038856,0.00022463237,0.0010486831,0.0028464578,0.0048594065,0.00061645283,0.0009032514,0.0065862765],"category_scores_gemma":[0.0058734296,0.00038431148,0.0001862858,0.0008424344,0.013246236,0.0052265353,0.0030783857,0.0023464789,0.00041517685],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000259224,0.0000644175,0.020462159,0.00012652307,0.000012915718,0.0008803523,0.5196401,0.00015434662,0.017294237,0.40713906,0.0013116354,0.03265494],"study_design_scores_gemma":[0.000062342144,0.00023246523,0.19514734,0.00045474176,0.00006871305,0.002845757,0.5534746,0.0025949958,0.0067919777,0.14555049,0.09254639,0.00023024771],"about_ca_topic_score_codex":0.04462097,"about_ca_topic_score_gemma":0.06236068,"teacher_disagreement_score":0.04462097,"about_ca_system_score_codex":0.0028898804,"about_ca_system_score_gemma":0.0026099388,"threshold_uncertainty_score":0.08872247},"labels":[],"label_agreement":null},{"id":"W4210262403","doi":"10.1515/lingvan-2020-0013","title":"A socially anchored approach to spatial language in Kalaallisut","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Categorization, perception, and language","field":"Psychology","cited_by":3,"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":"Sociocultural evolution; Affect (linguistics); Encoding (memory); Space (punctuation); Arctic; Geography; Sociology; Frame (networking); Linguistics; Psychology; Computer science; Communication; Ecology; Cognitive psychology; Anthropology; Philosophy","score_opus":0.015967087377721963,"score_gpt":0.3064200608114498,"score_spread":0.29045297343372783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210262403","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":[0.81113386,0.000763728,0.012104307,0.002190831,0.00006136624,0.000021778258,0.000028043045,0.000050211547,0.1736458],"genre_scores_gemma":[0.9976426,0.000061849925,0.00081755,0.00003148209,0.000003115669,0.000003902398,0.0000051065963,0.0000069386615,0.0014274883],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99865913,0.0007231751,0.000044056742,0.0002043331,0.00016427522,0.00020495529],"domain_scores_gemma":[0.99933237,0.00029217036,0.0001307785,0.00006021605,0.00009555667,0.000088854555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010087553,0.0003075272,0.00022361455,0.0013522608,0.0065055112,0.006379105,0.00073005276,0.00058916333,0.002447919],"category_scores_gemma":[0.0013282773,0.00017444833,0.0001513265,0.0008600804,0.014792424,0.0032059802,0.0044678007,0.0013854193,0.00017673637],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000370047,0.000043203338,0.0074775615,0.000050004466,0.000009146718,0.0007482369,0.66927546,0.00030102418,0.0031823064,0.30668178,0.0004075444,0.011786764],"study_design_scores_gemma":[0.0000138739315,0.00008129758,0.028418027,0.00019650471,0.00003818868,0.0012939526,0.73130757,0.004397591,0.0025713497,0.13387124,0.09772044,0.000090048816],"about_ca_topic_score_codex":0.05485366,"about_ca_topic_score_gemma":0.087098286,"teacher_disagreement_score":0.05485366,"about_ca_system_score_codex":0.0062194294,"about_ca_system_score_gemma":0.0021965285,"threshold_uncertainty_score":0.10906875},"labels":[],"label_agreement":null},{"id":"W4210791957","doi":"10.1515/lingvan-2020-0016","title":"Conflation of spatial reference frames in deaf community sign languages","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Modality (human–computer interaction); Conflation; Affordance; Sign language; Modalities; Sign (mathematics); American Sign Language; Frame of reference; Frame (networking); Computer science; Linguistics; Manually coded language; Feature (linguistics); Sociolinguistics of sign languages; Psychology; Artificial intelligence; Sociology; Human–computer interaction; Mathematics","score_opus":0.0589559648813121,"score_gpt":0.3698895156348347,"score_spread":0.3109335507535226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210791957","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":[0.43681026,0.433381,0.041974455,0.0028015233,0.00048250981,0.000065533524,0.00042902178,0.00013163469,0.083924115],"genre_scores_gemma":[0.93049276,0.060335137,0.005711167,0.0002829396,0.00008020245,0.000035424782,0.00012059603,0.000027629396,0.0029140676],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986817,0.0005238194,0.0001862929,0.0001972976,0.00033036212,0.00008043925],"domain_scores_gemma":[0.99755704,0.0012433629,0.00048076187,0.00012274116,0.0005380874,0.000057932717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020067291,0.00027848806,0.00045816787,0.0033584342,0.000497658,0.002997213,0.0006529002,0.0005490598,0.0022588025],"category_scores_gemma":[0.005313483,0.0001673129,0.000250769,0.0027219807,0.0036189232,0.0026965237,0.0015638117,0.0005190307,0.00025254453],"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":[0.0003384083,0.000038383256,0.012348201,0.009599109,0.0001382594,0.002207634,0.043583523,0.0011771404,0.027540695,0.20227985,0.0031052434,0.6976436],"study_design_scores_gemma":[0.00004434253,0.0006412765,0.08934435,0.013506997,0.00047592173,0.015168674,0.081511654,0.002133458,0.045445144,0.16758966,0.5837211,0.00041746048],"about_ca_topic_score_codex":0.0036250595,"about_ca_topic_score_gemma":0.0031835698,"teacher_disagreement_score":0.0036250595,"about_ca_system_score_codex":0.0009424539,"about_ca_system_score_gemma":0.0012212086,"threshold_uncertainty_score":0.010612726},"labels":[],"label_agreement":null},{"id":"W4214853268","doi":"10.1515/lingvan-2021-0057","title":"Disruptions due to COVID-19: using mixed methods to identify factors influencing language maintenance and shift","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Social distance; Recreation; Language shift; Perception; Psychology; Distancing; Affect (linguistics); Coronavirus disease 2019 (COVID-19); Identity (music); Heritage language; Social psychology; Sociology; Pedagogy; Linguistics; Geography; Political science; Medicine; Communication","score_opus":0.10321131260074493,"score_gpt":0.5455870256524398,"score_spread":0.4423757130516949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214853268","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":[0.9829948,0.00076695817,0.0099439025,0.00046661837,0.000044836153,0.0031405813,0.00060808443,0.000027892924,0.0020062828],"genre_scores_gemma":[0.9768574,0.00042362913,0.012590171,0.00029934192,0.00002189221,0.008448438,0.00032385043,0.00002506536,0.0010102387],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9606546,0.02836856,0.0036036551,0.0021587152,0.0034916452,0.0017228004],"domain_scores_gemma":[0.92036563,0.055385377,0.011931298,0.0048829177,0.0060390136,0.001395847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048123684,0.00051570963,0.0010455243,0.0039545805,0.0035742417,0.004285275,0.0019758192,0.0012393638,0.0029828106],"category_scores_gemma":[0.06878462,0.00073932135,0.0012306577,0.00432187,0.0027179876,0.002584277,0.005412763,0.0016465144,0.00026991163],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000748281,0.0011645559,0.4515903,0.002529194,0.0007243437,0.00079605693,0.4510954,0.0006230854,0.0020020064,0.0043859254,0.0016517467,0.08268916],"study_design_scores_gemma":[0.00009096754,0.0019494732,0.41000265,0.0019736383,0.00034591733,0.0002748849,0.56412303,0.0034672355,0.0036696664,0.0038488377,0.010057102,0.0001965673],"about_ca_topic_score_codex":0.015002997,"about_ca_topic_score_gemma":0.025479548,"teacher_disagreement_score":0.048123684,"about_ca_system_score_codex":0.0044833296,"about_ca_system_score_gemma":0.005184607,"threshold_uncertainty_score":0.25450546},"labels":[],"label_agreement":null},{"id":"W4285586648","doi":"10.1515/lingvan-2021-0048","title":"Cross-dialectal synchronic variation of a diachronic conditioned merger in Tlingit","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Variation (astronomy); Sound change; Perception; Linguistics; Indigenous; Set (abstract data type); History; Computer science; Psychology; Biology","score_opus":0.020944653249472533,"score_gpt":0.3604735833782272,"score_spread":0.3395289301287547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285586648","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":[0.99772817,0.000022358534,0.00025539377,0.0000073245224,0.0000034992477,0.0000029579805,0.000042583815,0.0000057053117,0.001932121],"genre_scores_gemma":[0.99960726,0.000007659851,0.00011001259,0.00000429204,9.3530343e-7,0.0000024712567,0.000030171546,0.0000064261353,0.00023079438],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996915,0.00004627499,0.000029987992,0.00011177576,0.000061016086,0.000059439568],"domain_scores_gemma":[0.99888533,0.0003432082,0.00020736046,0.00011527003,0.00033347812,0.00011536418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004414982,0.00012346143,0.0001691125,0.0007776331,0.0007430455,0.0008455729,0.00018562621,0.00019982494,0.0033091356],"category_scores_gemma":[0.0017002828,0.00012837183,0.00006804236,0.0007719881,0.001118321,0.0003395244,0.0011246706,0.0004157743,0.00026791237],"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":[0.00084103737,0.00012450838,0.49836072,0.00014433103,0.00007768875,0.0014517466,0.039133977,0.0005537784,0.42037547,0.0024421248,0.00033858008,0.036156096],"study_design_scores_gemma":[0.0000025012234,0.00006436275,0.9865348,0.000011031538,0.00001564913,0.00036388423,0.006714986,0.0002509335,0.0047510373,0.00027702897,0.0009979574,0.000015858503],"about_ca_topic_score_codex":0.01729225,"about_ca_topic_score_gemma":0.04170005,"teacher_disagreement_score":0.01729225,"about_ca_system_score_codex":0.00074180274,"about_ca_system_score_gemma":0.00035957276,"threshold_uncertainty_score":0.034383237},"labels":[],"label_agreement":null},{"id":"W4294663728","doi":"10.1515/lingvan-2021-0109","title":"Exploring variation and change in a small-scale Indigenous society: the case of (s) in Pirahã","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variation (astronomy); Sound change; Indigenous; Context (archaeology); Scale (ratio); Language change; Social change; Psychology; Demography; Geography; Social psychology; Sociology; Linguistics; Political science; Cartography; Ecology; Biology","score_opus":0.12170473993565635,"score_gpt":0.32382991997494676,"score_spread":0.20212518003929042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294663728","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":[0.99784696,0.000031028692,0.00016828012,0.000066456916,0.000002584525,0.000008405393,0.000016387407,0.0000022009888,0.0018577063],"genre_scores_gemma":[0.9994436,0.000019969604,0.00025624133,0.000012237935,0.000003004755,0.0000075439743,0.000010646891,0.0000024574688,0.00024439063],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9979962,0.0008929958,0.000089471214,0.00033909525,0.00032521927,0.00035703025],"domain_scores_gemma":[0.99730057,0.0014101856,0.0004497357,0.0003024576,0.00037573883,0.00016142643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020325978,0.00021562641,0.00040157788,0.0024479448,0.0042097173,0.0014757611,0.0008276279,0.0004316739,0.0021506974],"category_scores_gemma":[0.0061183637,0.00023794998,0.00019480144,0.0029252518,0.0050289407,0.0010836336,0.0031873656,0.00056833506,0.00016902463],"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":[0.00010158008,0.00007334479,0.13901898,0.00012899129,0.000037487804,0.0028153204,0.8142521,0.00009355658,0.007339367,0.0031097438,0.00028479402,0.032744735],"study_design_scores_gemma":[0.0000044993703,0.00020637334,0.490076,0.000040121045,0.00002593121,0.0015207233,0.49916604,0.00029438562,0.0009886371,0.0009063825,0.0067385896,0.000032309203],"about_ca_topic_score_codex":0.028147528,"about_ca_topic_score_gemma":0.06788137,"teacher_disagreement_score":0.028147528,"about_ca_system_score_codex":0.0012417348,"about_ca_system_score_gemma":0.00071448204,"threshold_uncertainty_score":0.05596739},"labels":[],"label_agreement":null},{"id":"W4306249762","doi":"10.1515/lingvan-2021-0122","title":"Phonetic change over the career: a case study","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":14,"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":"European Commission","keywords":"Flexibility (engineering); Perspective (graphical); Psychology; Linguistics; Longitudinal study; Feature (linguistics); Computer science; Mathematics","score_opus":0.07789135288875891,"score_gpt":0.3521037197557527,"score_spread":0.2742123668669938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306249762","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":[0.9963232,0.00036478232,0.00048817665,0.00060373853,0.00003877679,0.000020764253,0.0000635973,0.000008591819,0.002088351],"genre_scores_gemma":[0.99619114,0.00044476023,0.0004921587,0.00016004086,0.00004005347,0.00001229432,0.00003164824,0.000008816756,0.002619049],"study_design_codex":"case_report","study_design_gemma":"qualitative","domain_scores_codex":[0.999178,0.00023940792,0.000044143617,0.00013362331,0.00014841267,0.00025630498],"domain_scores_gemma":[0.9987465,0.00044883534,0.00019647558,0.000090205634,0.00016276875,0.0003552705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008649828,0.00045688433,0.00037270432,0.0015931755,0.00439943,0.0012465798,0.0006577007,0.0020103487,0.0021009564],"category_scores_gemma":[0.0028626525,0.00026907172,0.00044857207,0.0012789463,0.0016212951,0.00060298597,0.0013210117,0.0013245423,0.00032102494],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002128309,0.0005063215,0.18597534,0.00014459746,0.000032590495,0.59893966,0.16940211,0.0003267354,0.0039253747,0.0020271034,0.0016932415,0.036814094],"study_design_scores_gemma":[0.00001760401,0.0005038285,0.13977064,0.0002095531,0.00006564729,0.6490694,0.18319426,0.0013657662,0.0030673202,0.000974197,0.021645635,0.00011614858],"about_ca_topic_score_codex":0.03222817,"about_ca_topic_score_gemma":0.06346511,"teacher_disagreement_score":0.03222817,"about_ca_system_score_codex":0.0020983417,"about_ca_system_score_gemma":0.001152605,"threshold_uncertainty_score":0.06408119},"labels":[],"label_agreement":null},{"id":"W4312200521","doi":"10.1515/lingvan-2022-0017","title":"The Red Hen Anonymizer and the Red Hen Protocol for de-identifying audiovisual recordings","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fundación Séneca; Google; Alexander von Humboldt-Stiftung","keywords":"JSON; Computer science; Software; Protocol (science); Identification (biology); Face (sociological concept); Multimedia; Human–computer interaction; Speech recognition; World Wide Web; Programming language; Linguistics","score_opus":0.06178125760216429,"score_gpt":0.40706078183376426,"score_spread":0.34527952423159997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312200521","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":[0.010737936,0.00035705874,0.76660925,0.0064543206,0.002933656,0.020333119,0.033387024,0.03223015,0.12695748],"genre_scores_gemma":[0.10215473,0.0011823653,0.50880826,0.0066796984,0.0016479058,0.07537706,0.05200663,0.017019372,0.23512402],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96837795,0.01649209,0.004859952,0.0023129317,0.006569215,0.0013878405],"domain_scores_gemma":[0.91851157,0.025259344,0.003995008,0.035840217,0.014995496,0.0013984492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036264673,0.0010256652,0.00095688447,0.003777514,0.002930224,0.0040910332,0.0022213333,0.002478948,0.1470459],"category_scores_gemma":[0.07201785,0.0014542041,0.00068052125,0.002229728,0.002914648,0.005624579,0.00638518,0.00450379,0.069967404],"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":[0.0020685953,0.00027272938,0.0015087689,0.0010803117,0.00005652736,0.0013859681,0.005955906,0.0015502631,0.01954908,0.13411002,0.6670112,0.16545065],"study_design_scores_gemma":[0.00015090765,0.0001286727,0.0019101537,0.0006810707,0.000025429797,0.00056264614,0.0010324942,0.0037679793,0.02145889,0.027541736,0.9425935,0.00014646615],"about_ca_topic_score_codex":0.001373503,"about_ca_topic_score_gemma":0.0017910319,"teacher_disagreement_score":0.1470459,"about_ca_system_score_codex":0.0015987889,"about_ca_system_score_gemma":0.005599926,"threshold_uncertainty_score":0.49191755},"labels":[],"label_agreement":null},{"id":"W4377224620","doi":"10.1515/lingvan-2021-0143","title":"How did COVID-19 impact the use of Japanese complex words with <i>masuku</i> ‘mask’ in 2020?","year":2023,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Language, Metaphor, and Cognition","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":"York University","funders":"","keywords":"Newspaper; Compounding; Coronavirus disease 2019 (COVID-19); Sentence; Computer science; Advertising; History; Artificial intelligence; Sociology; Media studies; Business","score_opus":0.08374675119605893,"score_gpt":0.3525271364932683,"score_spread":0.2687803852972094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377224620","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":[0.9868172,0.00047167833,0.00048690918,0.00094225665,0.00007349659,0.000013355421,0.00014365594,0.000011083421,0.011040481],"genre_scores_gemma":[0.997875,0.0002445205,0.00030561682,0.00014897101,0.000014784351,0.000009246871,0.00009744225,0.00001510048,0.0012893407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989931,0.000323976,0.00006521235,0.00018805057,0.00017948411,0.00025019317],"domain_scores_gemma":[0.9983134,0.00040950437,0.0005568914,0.00009001977,0.00037654932,0.00025372763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019082723,0.00030251103,0.0002892138,0.00069869135,0.0019135908,0.003435716,0.0003981554,0.0005998399,0.0032563475],"category_scores_gemma":[0.0041327,0.00019711792,0.00028463732,0.0010344214,0.0029511424,0.003309246,0.003120498,0.0009885653,0.00056480686],"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":[0.00063169695,0.00014479453,0.45932728,0.0006700696,0.00010155111,0.0035593645,0.4299242,0.00039773562,0.015819682,0.014111762,0.0049665254,0.07034527],"study_design_scores_gemma":[0.000014699965,0.00026548837,0.47684935,0.00021497616,0.000091513975,0.0006189811,0.46116117,0.00085985294,0.0024353429,0.005375911,0.05199186,0.000120947385],"about_ca_topic_score_codex":0.026591893,"about_ca_topic_score_gemma":0.03660933,"teacher_disagreement_score":0.026591893,"about_ca_system_score_codex":0.0020322101,"about_ca_system_score_gemma":0.0013975438,"threshold_uncertainty_score":0.052874207},"labels":[],"label_agreement":null},{"id":"W4391967989","doi":"10.1515/lingvan-2023-0038","title":"Plains Cree Order as alternation","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Alternation (linguistics); Phenomenon; Lexeme; Linguistics; Computer science; Mathematics; Epistemology; Philosophy","score_opus":0.019250155242884776,"score_gpt":0.2696289642022423,"score_spread":0.25037880895935755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391967989","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":[0.2848885,0.0012102528,0.21332821,0.0042094323,0.0005122224,0.00016991652,0.00039660904,0.0007853646,0.49449947],"genre_scores_gemma":[0.9738178,0.00023635948,0.013700452,0.00020659117,0.00008122053,0.000039209364,0.00011494649,0.00021598722,0.011587306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979844,0.000789096,0.00015599365,0.00034549375,0.0005542171,0.00017085558],"domain_scores_gemma":[0.9972536,0.0012408996,0.0002849447,0.0006920558,0.00045104366,0.00007740434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015074314,0.00026627115,0.00029764726,0.001068743,0.0013117039,0.0027396178,0.00052116835,0.0006087486,0.004865023],"category_scores_gemma":[0.0036054938,0.00025592907,0.00039456377,0.001096118,0.007818437,0.007703538,0.0023536999,0.001670845,0.00063733244],"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":[0.000019971096,0.000007708154,0.00039601402,0.00003401753,0.0000032523785,0.00014345454,0.004291182,0.00013361782,0.0016430527,0.9875392,0.00053276424,0.0052557434],"study_design_scores_gemma":[0.000019669433,0.00005007408,0.0019421052,0.00006320323,0.000014598163,0.0011118514,0.0030289937,0.003157949,0.0044997553,0.8481939,0.13788478,0.000033145683],"about_ca_topic_score_codex":0.00085582485,"about_ca_topic_score_gemma":0.001027895,"teacher_disagreement_score":0.004865023,"about_ca_system_score_codex":0.0011113865,"about_ca_system_score_gemma":0.0005448047,"threshold_uncertainty_score":0.016275108},"labels":[],"label_agreement":null},{"id":"W4392656786","doi":"10.1515/lingvan-2023-0051","title":"The role of syntax in hashtag popularity","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Popularity; Computer science; Syntax; Natural language processing; Semantics (computer science); CLARITY; Artificial intelligence; Linguistics; Information retrieval; Psychology; Programming language; Social psychology","score_opus":0.008434858255253173,"score_gpt":0.26520548807037014,"score_spread":0.25677062981511695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392656786","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":[0.9446638,0.00035035188,0.028467415,0.0013823048,0.000049888444,0.000053456784,0.00035064653,0.00019668211,0.024485542],"genre_scores_gemma":[0.99769044,0.00006143825,0.0016242778,0.000039167033,0.00002182978,0.000012021863,0.00007463452,0.000046141504,0.0004298891],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99626416,0.0022292582,0.00026006094,0.00045695165,0.00057899667,0.00021059132],"domain_scores_gemma":[0.9358897,0.045051794,0.008424304,0.0029447079,0.006134855,0.0015546893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052093877,0.00029297062,0.00043243705,0.002090381,0.0013489157,0.005713111,0.000570661,0.0007019028,0.0055639567],"category_scores_gemma":[0.056841373,0.0005787715,0.00037764636,0.0018794423,0.00341001,0.0127615845,0.002620632,0.001144081,0.0008906251],"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":[0.00173226,0.00034047884,0.4803508,0.00054182607,0.00035409807,0.0009996953,0.02701298,0.007989755,0.03247224,0.31528756,0.0043226634,0.1285957],"study_design_scores_gemma":[0.00023819761,0.000727519,0.47349265,0.00031489017,0.00044207636,0.0019535446,0.019183282,0.08089787,0.012496199,0.3956291,0.014173573,0.00045116714],"about_ca_topic_score_codex":0.0019219997,"about_ca_topic_score_gemma":0.0015773644,"teacher_disagreement_score":0.005713111,"about_ca_system_score_codex":0.0012587041,"about_ca_system_score_gemma":0.0007868107,"threshold_uncertainty_score":0.02755022},"labels":[],"label_agreement":null},{"id":"W4393936388","doi":"10.1515/lingvan-2023-0087","title":"A diachronic consequence of intransitivity: structural underspecification and processing biases in Old French","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Categorization, perception, and language","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":"University of Toronto","funders":"","keywords":"Underspecification; Linguistics; Verb; Grammar; Representation (politics); Object (grammar); Parsing; Corollary; Optimality theory; Computer science; History; Philosophy; Artificial intelligence; Phonology; Mathematics; Political science","score_opus":0.03199731922509109,"score_gpt":0.3445328847187323,"score_spread":0.3125355654936412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393936388","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":[0.9945368,0.00008204853,0.0020726745,0.00008654209,0.0000035023884,0.0000030657877,0.000042956646,0.000021478436,0.0031507644],"genre_scores_gemma":[0.9992855,0.000016841917,0.00033044338,0.000022558479,0.0000042624156,0.0000011037065,0.000021448894,0.000008622247,0.00030924974],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994505,0.0001624629,0.000050678762,0.00013593132,0.00012688075,0.00007360107],"domain_scores_gemma":[0.99658114,0.0017189685,0.0006391541,0.00046928195,0.00049813965,0.00009338879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014206757,0.00017843167,0.0001996937,0.0009396408,0.00050822797,0.0011085576,0.0002239457,0.00034452346,0.0019649446],"category_scores_gemma":[0.0032901121,0.0001405963,0.00012617788,0.00042358058,0.00196331,0.0009118102,0.00047254644,0.00038908888,0.00017124858],"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":[0.00079397176,0.00013718706,0.43692347,0.00026509934,0.00012067339,0.0038677016,0.048433553,0.0011217665,0.34624952,0.048295412,0.00095633866,0.11283529],"study_design_scores_gemma":[0.000034041692,0.00025808293,0.909145,0.000041554038,0.00009181673,0.005068978,0.013255345,0.0028128133,0.03316001,0.021688445,0.014335897,0.000108063745],"about_ca_topic_score_codex":0.006939236,"about_ca_topic_score_gemma":0.0083162505,"teacher_disagreement_score":0.006939236,"about_ca_system_score_codex":0.00070044206,"about_ca_system_score_gemma":0.000258371,"threshold_uncertainty_score":0.0137977},"labels":[],"label_agreement":null},{"id":"W4399982581","doi":"10.1515/lingvan-2023-0148","title":"The syntax of African American English borrowings in the Louisiana Creole tense-mood-aspect system","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","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":"Arts and Humanities Research Council; University of Oxford; Georgetown University; Louisiana State University; McGill University; University of Sussex; University of Pennsylvania","keywords":"Creole language; Linguistics; Syntax; English-based creole languages; History; Mood; American English; Psychology; Philosophy; Language assessment","score_opus":0.011343924825938927,"score_gpt":0.2920378295530314,"score_spread":0.2806939047270925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399982581","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":[0.9876623,0.00008830562,0.0014016534,0.00013581922,0.0000023832038,0.00000884772,0.000089488945,0.00003532361,0.010575913],"genre_scores_gemma":[0.99865216,0.000034019507,0.0005713562,0.000012872021,0.0000014286213,0.000004495406,0.00003392529,0.000015362393,0.0006744052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999841,0.0000618297,0.0000102326585,0.000032795477,0.000026779831,0.000027356187],"domain_scores_gemma":[0.9995927,0.00017584582,0.000087167304,0.000046952384,0.000080467566,0.000016788204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031993084,0.00013297066,0.0001420934,0.00071698806,0.00082892703,0.0011886428,0.0002201802,0.00021964237,0.0023737429],"category_scores_gemma":[0.00077366614,0.00016442107,0.00007621599,0.0008334769,0.0011292434,0.0007937582,0.000949887,0.0003292588,0.00020932152],"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":[0.00061734964,0.000100654506,0.14599358,0.00025486143,0.00011933166,0.0038016946,0.23023248,0.00095898437,0.17732096,0.31099203,0.0024924933,0.1271156],"study_design_scores_gemma":[0.000057497335,0.00021835946,0.6843331,0.00023340825,0.00016370564,0.0035216855,0.09477788,0.0074219345,0.02798687,0.032647725,0.14843361,0.00020420006],"about_ca_topic_score_codex":0.01392738,"about_ca_topic_score_gemma":0.03214463,"teacher_disagreement_score":0.01392738,"about_ca_system_score_codex":0.0012727233,"about_ca_system_score_gemma":0.00040190914,"threshold_uncertainty_score":0.027692616},"labels":[],"label_agreement":null},{"id":"W4402422143","doi":"10.1515/lingvan-2023-0102","title":"Bibliographic bias and information-density sampling","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Marcus och Amalia Wallenbergs minnesfond","keywords":"Sampling bias; Sampling (signal processing); Statistics; Information retrieval; Computer science; Geography; Mathematics; Sample size determination; Telecommunications","score_opus":0.025144856216042854,"score_gpt":0.29749520760234294,"score_spread":0.2723503513863001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402422143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21595514,0.017126357,0.6698187,0.020177852,0.001079099,0.0026210404,0.0038725,0.00091013435,0.06843914],"genre_scores_gemma":[0.87963235,0.0029080939,0.10767119,0.0021333753,0.0008125696,0.0031534715,0.0013417656,0.00014920099,0.0021979462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.61239564,0.2940697,0.023957502,0.01956209,0.04731511,0.0026999216],"domain_scores_gemma":[0.12950107,0.76372534,0.03291723,0.049906857,0.022819914,0.0011295564],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23577125,0.0006860632,0.0027806433,0.024514185,0.0042841868,0.009370446,0.004950193,0.0025444792,0.006182659],"category_scores_gemma":[0.6992773,0.00117837,0.0010063632,0.040740408,0.011577865,0.012066471,0.007245197,0.0022082448,0.0012103791],"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":[0.00060813245,0.00016756891,0.11129969,0.0047150115,0.0010010082,0.0012273652,0.02224816,0.0072406484,0.0010592439,0.5850279,0.013092129,0.25231314],"study_design_scores_gemma":[0.00025433625,0.00018299649,0.04888704,0.0048572505,0.0005624277,0.0022688305,0.012221869,0.029361313,0.0029482103,0.83148074,0.066751465,0.00022343926],"about_ca_topic_score_codex":0.0069225836,"about_ca_topic_score_gemma":0.0059306785,"teacher_disagreement_score":0.9754858,"about_ca_system_score_codex":0.0058763176,"about_ca_system_score_gemma":0.0037091642,"threshold_uncertainty_score":0.9424301},"labels":[],"label_agreement":null},{"id":"W4403221822","doi":"10.1515/lingvan-2024-0091","title":"Using constructed languages to introduce and teach linguistics","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Linguistics; Applied linguistics; Computer science; Quantitative linguistics; Media linguistics; Programming language; Sociology; Philosophy","score_opus":0.037804785940285766,"score_gpt":0.31828005229765444,"score_spread":0.2804752663573687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403221822","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":[0.5343905,0.00037410727,0.31653044,0.0050489022,0.00046501207,0.00056422123,0.00020998128,0.004918296,0.13749848],"genre_scores_gemma":[0.7844381,0.0002551653,0.1772463,0.00066597847,0.000046770045,0.00031890595,0.00023069109,0.0004909575,0.036307227],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961863,0.00280497,0.00009106764,0.00034617732,0.00037291556,0.00019858211],"domain_scores_gemma":[0.9869604,0.009533957,0.00059885834,0.0012598765,0.0005943,0.0010525503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044190916,0.0006256269,0.00018908984,0.0009321545,0.001102796,0.0038970322,0.0012308629,0.00076804846,0.011790998],"category_scores_gemma":[0.008995685,0.00042853822,0.00026237563,0.00038423768,0.003686723,0.0032503402,0.0060019484,0.0022130904,0.002120536],"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":[0.00043986485,0.0035262941,0.018690672,0.0008907654,0.000032305106,0.001622896,0.17943354,0.005986759,0.0687165,0.20969713,0.025997372,0.48496592],"study_design_scores_gemma":[0.0002433546,0.0014205949,0.005213249,0.0007818907,0.000040173945,0.0015187584,0.0521602,0.020086879,0.061220508,0.08970549,0.767428,0.00018094326],"about_ca_topic_score_codex":0.0007130774,"about_ca_topic_score_gemma":0.002041825,"teacher_disagreement_score":0.011790998,"about_ca_system_score_codex":0.0015251015,"about_ca_system_score_gemma":0.0020635251,"threshold_uncertainty_score":0.039444804},"labels":[],"label_agreement":null},{"id":"W4408918469","doi":"10.1515/lingvan-2024-0247","title":"Asymmetry in French speech-in-noise perception: the effects of native dialect and cross-dialectal exposure","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Asymmetry; Speech perception; Perception; Linguistics; Noise (video); Psychology; Speech recognition; Acoustics; Audiology; Computer science; Physics; Artificial intelligence; Philosophy; Medicine","score_opus":0.009096022296645455,"score_gpt":0.34880863823580566,"score_spread":0.3397126159391602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408918469","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":[0.9991314,0.0000454692,0.00009455507,0.0000110402525,0.0000015636411,0.000004400426,0.000034475644,0.0000030918109,0.00067411974],"genre_scores_gemma":[0.9995524,0.000022296645,0.00006825975,0.000011548641,9.699475e-7,0.000005392238,0.000035575475,0.0000024072613,0.00030122642],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995295,0.00012527546,0.000025406658,0.00012594559,0.00011575132,0.000078231984],"domain_scores_gemma":[0.9981421,0.00088665786,0.00027900457,0.00013469282,0.0002948225,0.00026263602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006233681,0.00026266548,0.00019696122,0.0005153168,0.00031349837,0.00070393924,0.00014547948,0.00028414576,0.0034287241],"category_scores_gemma":[0.0026161105,0.00010445419,0.00013226074,0.00015136546,0.0004280311,0.00022755656,0.0005877611,0.0002692154,0.0001951526],"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":[0.0037449326,0.00046403843,0.49592507,0.00015005846,0.00014800248,0.0010841754,0.02166887,0.00020577389,0.43670347,0.00022700867,0.00026550356,0.039413083],"study_design_scores_gemma":[0.0000032716362,0.00014302497,0.9959533,0.000004080449,0.0000071589247,0.000115380746,0.0015352836,0.000056284982,0.0020060374,0.000018676266,0.00015102055,0.00000655618],"about_ca_topic_score_codex":0.028372334,"about_ca_topic_score_gemma":0.041658662,"teacher_disagreement_score":0.028372334,"about_ca_system_score_codex":0.00059511483,"about_ca_system_score_gemma":0.000257154,"threshold_uncertainty_score":0.056414425},"labels":[],"label_agreement":null},{"id":"W4413796994","doi":"10.1515/lingvan-2024-0201","title":"Instance memory models as a general computational framework for exploring language processing: bringing the lexicon to life","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicon; Computer science; Cognitive science; Natural language processing; Linguistics; Artificial intelligence; Psychology; Cognitive psychology; Philosophy","score_opus":0.057039101299999395,"score_gpt":0.32504685551013524,"score_spread":0.26800775421013584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413796994","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":[0.04727067,0.0011416738,0.9266911,0.0055144853,0.000073135154,0.000053917738,0.00026679167,0.000357148,0.01863107],"genre_scores_gemma":[0.788472,0.0011986422,0.20377944,0.0006211465,0.00026447335,0.00024935574,0.00031537248,0.00018344253,0.0049161273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934465,0.00036052015,0.000034101326,0.00012355496,0.00007910669,0.0000580435],"domain_scores_gemma":[0.99731857,0.0018157244,0.00014486891,0.0004057989,0.00013432844,0.0001806358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016455114,0.00049325486,0.0008785061,0.0018496694,0.00085348357,0.0049187867,0.002205178,0.0015912183,0.0047215167],"category_scores_gemma":[0.0061271642,0.00051201746,0.0015628992,0.0012802248,0.0041464763,0.011974021,0.0025865606,0.0023459608,0.0006624325],"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":[0.000013970929,0.000014056651,0.0003587876,0.00003653947,0.000021620775,0.00006628758,0.0005392333,0.015078076,0.00033589796,0.97667843,0.00067166134,0.006185378],"study_design_scores_gemma":[0.0000056033996,0.0000075438957,0.000060083177,0.000011495994,0.0000067984115,0.00003769531,0.00007973708,0.07329762,0.000074486044,0.9247548,0.0016565342,0.00000770458],"about_ca_topic_score_codex":0.0024667566,"about_ca_topic_score_gemma":0.0026333078,"teacher_disagreement_score":0.0049187867,"about_ca_system_score_codex":0.001398093,"about_ca_system_score_gemma":0.0008835655,"threshold_uncertainty_score":0.015795052},"labels":[],"label_agreement":null},{"id":"W4415076690","doi":"10.1515/lingvan-2025-0160","title":"Linguistic approaches to fake news research are growing and maturing: commentary on a special issue","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Misinformation and Its Impacts","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":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Interpretation (philosophy); Sophistication; Context (archaeology); Fake news; Flourishing; Corpus linguistics; Social media; Natural (archaeology)","score_opus":0.17335017976923545,"score_gpt":0.3979844354813963,"score_spread":0.22463425571216084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415076690","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012127397,0.007095202,0.000074478325,0.9288376,0.0629287,0.0000040796804,0.000017829001,0.0000069129187,0.000913948],"genre_scores_gemma":[0.006880221,0.013561999,0.00030986115,0.73237133,0.24296083,0.000053127344,0.00003913097,0.000110094705,0.0037134432],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97465736,0.010806554,0.0025201403,0.0033098704,0.006627479,0.0020785609],"domain_scores_gemma":[0.7453697,0.20562352,0.007963033,0.0034491303,0.031241242,0.0063534086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.033161037,0.0016590204,0.0024160913,0.0054456606,0.015585571,0.016664375,0.006843486,0.059613626,0.0059361258],"category_scores_gemma":[0.12834667,0.0012422161,0.002344748,0.004935324,0.027975067,0.020442968,0.008513766,0.06769149,0.0029170772],"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":[0.000019993913,0.000011426114,0.00010114749,0.0003302325,0.000011627342,0.0002765183,0.0040305434,0.000023151797,0.00006744118,0.009695109,0.9815013,0.00393154],"study_design_scores_gemma":[0.000018466646,0.000020586556,0.0005097178,0.0024315722,0.000030283289,0.00032393672,0.007600461,0.0001083623,0.00014162752,0.00851529,0.98023784,0.000061844694],"about_ca_topic_score_codex":0.02242069,"about_ca_topic_score_gemma":0.03197537,"teacher_disagreement_score":0.96683896,"about_ca_system_score_codex":0.012848999,"about_ca_system_score_gemma":0.018693987,"threshold_uncertainty_score":0.17537439},"labels":[],"label_agreement":null}]}