{"meta":{"query_hash":"e06f5461f2f9","filters":{"venue":"Linguistic Variation"},"cohort_total":18,"direct_labels_cover":0,"predictions_cover":18,"exported":18,"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/e06f5461f2f9","api":"https://metacan.xera.ac/api/v1/cohort?venue=Linguistic+Variation"},"results":[{"id":"W161760220","doi":"10.1075/lv.15.2.01fru","title":"I’m done my homework—Case assignment in a stative passive","year":2015,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":19,"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":"Participle; Adjective; Complement (music); Linguistics; Variation (astronomy); Argument (complex analysis); Verb; Head (geology); Computer science; Noun; History; Philosophy; Physics","score_opus":0.04409870292138081,"score_gpt":0.26767301966793844,"score_spread":0.22357431674655764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W161760220","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":[0.8345873,0.00020527914,0.030478522,0.0003948769,0.000019947014,0.000059147347,0.0003915974,0.00021596138,0.13364747],"genre_scores_gemma":[0.99442035,0.000033446413,0.00239149,0.000017361206,0.0000045619686,0.000009224829,0.00009301069,0.00005952542,0.0029710291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985776,0.00044581338,0.000054760854,0.00032514377,0.00033543812,0.00026120906],"domain_scores_gemma":[0.9986076,0.0006104245,0.00014458838,0.00029120073,0.00028102286,0.000065102635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012880806,0.0003988333,0.00031825464,0.0013662246,0.0041312873,0.003461622,0.0009029649,0.0005634425,0.003410592],"category_scores_gemma":[0.0016652293,0.000450175,0.0003177556,0.0019401513,0.00715892,0.0024393143,0.0019642015,0.0009668017,0.00040603548],"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":[0.00014003695,0.000045153185,0.0153755555,0.0000763812,0.00001513061,0.0010701298,0.090300776,0.00065929757,0.018548768,0.85425997,0.0011336531,0.018375246],"study_design_scores_gemma":[0.00018371076,0.00032331602,0.1605997,0.00033887167,0.0003323468,0.007383806,0.18767917,0.02078479,0.046675183,0.23660974,0.33877918,0.00031018243],"about_ca_topic_score_codex":0.16807936,"about_ca_topic_score_gemma":0.2308164,"teacher_disagreement_score":0.16807936,"about_ca_system_score_codex":0.0062094815,"about_ca_system_score_gemma":0.0032703173,"threshold_uncertainty_score":0.3342021},"labels":[],"label_agreement":null},{"id":"W2012534933","doi":"10.1075/lv.12.2.03gil","title":"Evidence for mass and count in Inuttut","year":2012,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":7,"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":"Numeral system; Noun; Linguistics; Semantics (computer science); Mathematics; Interpretation (philosophy); Computer science; Arithmetic; Philosophy; Programming language","score_opus":0.07885239937651277,"score_gpt":0.29160673093643075,"score_spread":0.21275433155991796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012534933","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":[0.9134784,0.00052655046,0.0049715703,0.0010882701,0.00008504344,0.00002972422,0.00035393093,0.00010253248,0.07936391],"genre_scores_gemma":[0.9964503,0.00006209805,0.0013835217,0.0000877096,0.0000217781,0.000011513668,0.00018268802,0.000043589298,0.0017568466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9979564,0.00060804444,0.00015758375,0.00050034997,0.0005576609,0.00021989392],"domain_scores_gemma":[0.99485356,0.002396634,0.001060711,0.00066529785,0.00081238034,0.00021140915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023209122,0.00033001803,0.0004644835,0.0020357266,0.0027077817,0.0038382334,0.00076739845,0.0006068164,0.0065468033],"category_scores_gemma":[0.006776446,0.00026359243,0.00022556965,0.002973798,0.0035845952,0.0035881873,0.0031577265,0.0010322065,0.00064002903],"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":[0.0010129543,0.0001790041,0.25798303,0.00055688,0.00015659287,0.0009615529,0.07526595,0.00074392534,0.016670676,0.47188956,0.009900187,0.16467969],"study_design_scores_gemma":[0.00007936013,0.00028298737,0.6423937,0.00042235787,0.00020103087,0.002768129,0.051214118,0.006982413,0.0136848185,0.14649394,0.13530047,0.00017674665],"about_ca_topic_score_codex":0.0058543384,"about_ca_topic_score_gemma":0.012453511,"teacher_disagreement_score":0.0065468033,"about_ca_system_score_codex":0.0019956469,"about_ca_system_score_gemma":0.0005852255,"threshold_uncertainty_score":0.02190119},"labels":[],"label_agreement":null},{"id":"W2172729879","doi":"10.1075/lv.16.2.02com","title":"An extension of the comparative sociolinguistics approach for sociosyntax","year":2016,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":8,"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 Ottawa","keywords":"Sociolinguistics; Linguistics; Focus (optics); Generative grammar; Constraint (computer-aided design); Polarity (international relations); Extension (predicate logic); Sociology; Computer science; Mathematics; Philosophy; Biology; Physics","score_opus":0.06659404555741713,"score_gpt":0.36080460767221084,"score_spread":0.2942105621147937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172729879","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":[0.047155812,0.0013145837,0.75712883,0.003294482,0.00022837636,0.00013767045,0.00023485339,0.00015396818,0.1903515],"genre_scores_gemma":[0.8516611,0.0007218783,0.13917838,0.0006250343,0.0003157844,0.00040602306,0.00019349018,0.00023072299,0.0066677225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979761,0.0012266655,0.00007226973,0.00033268752,0.00030288912,0.00008939454],"domain_scores_gemma":[0.9978283,0.0012519012,0.00022794923,0.0004366967,0.0002042595,0.000050955714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002831805,0.00049364805,0.00053303875,0.0024581568,0.0015060488,0.0020188533,0.0013669162,0.00066222483,0.008282914],"category_scores_gemma":[0.0040948098,0.00027564415,0.0009847662,0.001512262,0.008331172,0.004166155,0.0024727713,0.0018212178,0.0004197397],"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":[0.000006501343,0.000008220953,0.0003420414,0.000031565083,0.000010512853,0.00006699851,0.0019368886,0.0004678376,0.00038772044,0.9872736,0.00021781238,0.009250319],"study_design_scores_gemma":[0.00001528361,0.000049429247,0.0031407955,0.000044871147,0.000016151826,0.00038835945,0.0010143752,0.0030203538,0.0004977625,0.9456046,0.046187434,0.000020635263],"about_ca_topic_score_codex":0.0029373765,"about_ca_topic_score_gemma":0.003297095,"teacher_disagreement_score":0.008282914,"about_ca_system_score_codex":0.002523567,"about_ca_system_score_gemma":0.0010828869,"threshold_uncertainty_score":0.027709067},"labels":[],"label_agreement":null},{"id":"W2575795807","doi":"10.1075/lv.16.2.05bur","title":"Variation as a testing ground for grammatical theory","year":2016,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":2,"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":"Negation; Linguistics; Variation (astronomy); Word order; Psychology; Philosophy; Physics; Astrophysics","score_opus":0.04298550062241268,"score_gpt":0.333124112651169,"score_spread":0.2901386120287563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575795807","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":[0.37207645,0.0018168276,0.50783384,0.010329625,0.0004139444,0.00016320695,0.0008539289,0.00058961904,0.105922475],"genre_scores_gemma":[0.9759187,0.00018724603,0.022302525,0.00036149353,0.00014831562,0.00010923621,0.000323717,0.00016266495,0.00048610233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97280145,0.017339032,0.0008958806,0.004442438,0.0038145238,0.00070668093],"domain_scores_gemma":[0.90231967,0.07585212,0.0032038197,0.014969868,0.0029191065,0.0007354021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020191824,0.00074515044,0.0014832923,0.004406867,0.0024368104,0.0046227863,0.0038483709,0.0018584267,0.0060881833],"category_scores_gemma":[0.0565183,0.00071368075,0.0013686559,0.0024984218,0.028351886,0.0151493,0.007212812,0.0041917753,0.0004223943],"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":[0.00009223851,0.000023570725,0.0045953323,0.0001373599,0.000067798705,0.00014343763,0.0026105896,0.0018941996,0.00087872153,0.96915853,0.0004974597,0.019900702],"study_design_scores_gemma":[0.000025316933,0.000060147704,0.0027453427,0.00006994851,0.000022030626,0.00013263062,0.000841991,0.008520226,0.0007599696,0.98130643,0.005485062,0.000030888863],"about_ca_topic_score_codex":0.0014970368,"about_ca_topic_score_gemma":0.0009592377,"teacher_disagreement_score":0.020191824,"about_ca_system_score_codex":0.003001819,"about_ca_system_score_gemma":0.0013327573,"threshold_uncertainty_score":0.106785834},"labels":[],"label_agreement":null},{"id":"W2577090158","doi":"10.1075/lv.14018.pau","title":"Reduced structure in Malagasy headlines","year":2017,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Word order; Linguistics; Syntactic structure; History; Syntax; Philosophy","score_opus":0.029849262287239876,"score_gpt":0.2678179236343418,"score_spread":0.23796866134710193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577090158","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":[0.9905552,0.00017438465,0.00048709378,0.0001793571,0.000010458669,0.000007629036,0.0004375246,0.000034045588,0.0081141805],"genre_scores_gemma":[0.99895406,0.000045866298,0.00019185575,0.000015976571,0.000006752053,0.000003877175,0.00017440133,0.000017805925,0.0005894058],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997241,0.000074334625,0.00002515237,0.00006496983,0.00005707206,0.00005440383],"domain_scores_gemma":[0.99865663,0.0003806827,0.0005692471,0.00015416862,0.00019284354,0.00004633142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023390086,0.00014442351,0.00018874994,0.0011827997,0.00089503516,0.0010852644,0.00020465828,0.00022904872,0.008154818],"category_scores_gemma":[0.0017870672,0.00014565173,0.00007124589,0.0022499731,0.0013573646,0.0007150443,0.0010151317,0.00025310327,0.00035169735],"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":[0.001547928,0.00009930059,0.4132007,0.001146533,0.00016565628,0.0060339468,0.15390117,0.0012777459,0.10659491,0.11736483,0.007164054,0.19150323],"study_design_scores_gemma":[0.000031475272,0.00014277092,0.8776474,0.00014240974,0.000071393326,0.001628965,0.030226134,0.0010613331,0.008924554,0.00772747,0.07233411,0.000061959254],"about_ca_topic_score_codex":0.013132372,"about_ca_topic_score_gemma":0.012319873,"teacher_disagreement_score":0.013132372,"about_ca_system_score_codex":0.00095582247,"about_ca_system_score_gemma":0.00029803885,"threshold_uncertainty_score":0.02728057},"labels":[],"label_agreement":null},{"id":"W2624792854","doi":"10.1075/lv.17.1.04cow","title":"The rise of contrastive modality in English","year":2017,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Grammaticalization; Modal verb; Modality (human–computer interaction); Linguistics; Feature (linguistics); Grammatical category; Modal; Psychology; Epistemic modality; Computer science; Verb; Artificial intelligence; Philosophy; Noun; Chemistry","score_opus":0.024689875792338997,"score_gpt":0.256821200888708,"score_spread":0.23213132509636902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624792854","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":[0.9166725,0.0004779697,0.016277347,0.0006794991,0.00004045283,0.000014252389,0.00009791952,0.00007121018,0.065668754],"genre_scores_gemma":[0.9989808,0.000035320183,0.00049763505,0.000019795525,0.00000834422,0.000001593557,0.000008426692,0.000011017702,0.00043710644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99970824,0.00009553529,0.000016141132,0.00007262932,0.000069463305,0.00003801041],"domain_scores_gemma":[0.99909866,0.00047933726,0.000100720725,0.00010999646,0.0001809672,0.000030311028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060745206,0.00010102198,0.00013528786,0.0005791305,0.00058546796,0.0012194302,0.00029053702,0.0002275095,0.0017124857],"category_scores_gemma":[0.0014188664,0.00014919996,0.00013135305,0.00031153104,0.0022263941,0.0017719091,0.00097385637,0.00063773745,0.00009110422],"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":[0.00021315027,0.000045058703,0.016412491,0.0001972243,0.000038138478,0.002093309,0.03461978,0.0006814294,0.09654331,0.81153417,0.00074486,0.036877044],"study_design_scores_gemma":[0.0001327418,0.0004953479,0.23388791,0.00020751928,0.00021060598,0.008794465,0.023191955,0.012698594,0.06466887,0.51101184,0.14447942,0.00022073486],"about_ca_topic_score_codex":0.0014513045,"about_ca_topic_score_gemma":0.0016859208,"teacher_disagreement_score":0.0017124857,"about_ca_system_score_codex":0.0009903258,"about_ca_system_score_gemma":0.0001752683,"threshold_uncertainty_score":0.0071853995},"labels":[],"label_agreement":null},{"id":"W2626008218","doi":"10.1075/lv.17.1.05oxf","title":"Variation and change in the Degree Phrase","year":2017,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","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 Manitoba","funders":"","keywords":"Variation (astronomy); Degree (music); Generative grammar; Phrase; Linguistics; Computer science; Artificial intelligence; Natural language processing; Philosophy","score_opus":0.10554998700493665,"score_gpt":0.28554876747740027,"score_spread":0.17999878047246362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626008218","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":[0.9235783,0.00037425148,0.008742444,0.0004888772,0.000030268078,0.000022587607,0.00015739807,0.000051886756,0.066553906],"genre_scores_gemma":[0.9985556,0.00003511114,0.0005662075,0.000025147612,0.000007955709,0.0000033532865,0.000029897583,0.000012654121,0.00076401175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9990421,0.00039862786,0.000048178736,0.00016652961,0.0002587754,0.00008566898],"domain_scores_gemma":[0.99808216,0.0011807822,0.00023040733,0.00022751265,0.000220961,0.000058117865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092153414,0.00017008552,0.00019582848,0.001093306,0.0008217882,0.0015846118,0.00029954952,0.0003645152,0.0033389567],"category_scores_gemma":[0.0035377047,0.00012404626,0.00016860306,0.0012266045,0.0030700485,0.0022544372,0.0012883523,0.00059385697,0.00019065385],"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":[0.00051173306,0.000087517736,0.060990553,0.00032985627,0.000103802595,0.0015997867,0.06285508,0.0014971562,0.06327527,0.7111385,0.002024098,0.095586725],"study_design_scores_gemma":[0.00013839883,0.00053044735,0.385775,0.00023920403,0.0001982984,0.005513298,0.046675175,0.008424653,0.036553744,0.34173995,0.17398106,0.0002306822],"about_ca_topic_score_codex":0.003004513,"about_ca_topic_score_gemma":0.0029613657,"teacher_disagreement_score":0.0033389567,"about_ca_system_score_codex":0.0013366198,"about_ca_system_score_gemma":0.00029176395,"threshold_uncertainty_score":0.01116997},"labels":[],"label_agreement":null},{"id":"W2792060362","doi":"10.1075/lv.15017.mas","title":"Obligatorily null pronouns in the instructional register and beyond","year":2017,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Null (SQL); Linguistics; Focus (optics); Subject pronoun; Computer science; Register (sociolinguistics); Reflexive pronoun; Natural language processing; Psychology; Mathematics; Physics; Philosophy","score_opus":0.029418305989876263,"score_gpt":0.25183078120283725,"score_spread":0.22241247521296098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792060362","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":[0.7753863,0.00088593096,0.052148342,0.0014458867,0.00011803105,0.000045427845,0.0003167074,0.00028158558,0.16937183],"genre_scores_gemma":[0.9936745,0.00010266121,0.0026126807,0.0000598576,0.000023784405,0.000012399289,0.0000674756,0.00008112454,0.0033653772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99883527,0.00035827252,0.00013262988,0.0002670629,0.0002643659,0.00014242007],"domain_scores_gemma":[0.99810696,0.00074943656,0.00025006355,0.00039317075,0.00042579003,0.000074443065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013809556,0.00039878997,0.00043847295,0.0010539271,0.0020211653,0.002442347,0.00076245045,0.00052744674,0.0036507812],"category_scores_gemma":[0.0023655386,0.00033534662,0.00032499712,0.0008547971,0.005989274,0.0041452614,0.0021540965,0.001115451,0.00042608133],"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":[0.000044572582,0.000019229443,0.0051939385,0.00007713815,0.000011025504,0.00036100333,0.010264447,0.00008992659,0.0039062407,0.96827984,0.0006632557,0.011089318],"study_design_scores_gemma":[0.000077225486,0.00016146399,0.026269713,0.00020285582,0.00016073546,0.0019788898,0.020289771,0.003690687,0.020756286,0.774046,0.15220323,0.00016319273],"about_ca_topic_score_codex":0.003221212,"about_ca_topic_score_gemma":0.0038023784,"teacher_disagreement_score":0.0036507812,"about_ca_system_score_codex":0.001123603,"about_ca_system_score_gemma":0.0009535258,"threshold_uncertainty_score":0.012213111},"labels":[],"label_agreement":null},{"id":"W2793112483","doi":"10.1075/lv.00001.mas","title":"Introducing register variation and syntactic theory","year":2017,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","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":"Register (sociolinguistics); Variation (astronomy); Computer science; Linguistics; Natural language processing; Artificial intelligence; Philosophy; Physics","score_opus":0.02521093705739471,"score_gpt":0.25312988876043313,"score_spread":0.2279189517030384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793112483","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":[0.016256092,0.011235289,0.41420987,0.024099823,0.0025353797,0.000078205274,0.0005859151,0.0007220717,0.5302774],"genre_scores_gemma":[0.77680534,0.0073870393,0.11938964,0.0038950634,0.004577725,0.00026057992,0.0007123727,0.0010028098,0.0859695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99716115,0.0016730188,0.00011879154,0.00037255447,0.0005058909,0.00016864434],"domain_scores_gemma":[0.9988601,0.0006872626,0.000057754416,0.00015919033,0.00019276256,0.00004290233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025659266,0.00072244555,0.00064791803,0.0031096484,0.002181377,0.0036664214,0.0012033783,0.0016425491,0.011684769],"category_scores_gemma":[0.0038533607,0.0004728139,0.0010849496,0.0021705034,0.010457578,0.011734388,0.0032151942,0.0038920932,0.002002322],"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":[0.00000239136,0.0000017288897,0.000025783645,0.000009197485,0.0000021523872,0.00001732479,0.00027260254,0.00011586469,0.000051616717,0.99495935,0.0015735666,0.0029683367],"study_design_scores_gemma":[0.0000029991347,0.0000064212295,0.000071802424,0.000022200331,0.000004565761,0.000054281194,0.00014291891,0.00055390876,0.00011023767,0.9621927,0.036830276,0.0000075826138],"about_ca_topic_score_codex":0.0029327786,"about_ca_topic_score_gemma":0.002462631,"teacher_disagreement_score":0.011684769,"about_ca_system_score_codex":0.0028915657,"about_ca_system_score_gemma":0.001200707,"threshold_uncertainty_score":0.03908944},"labels":[],"label_agreement":null},{"id":"W2884639244","doi":"10.1075/lv.00003.duf","title":"The variable use of determiners in Old French and the argument DP hypothesis","year":2018,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of British Columbia; Queen's University","funders":"","keywords":"Definiteness; Determiner; Argument (complex analysis); Covert; Linguistics; Noun; Subject (documents); Object (grammar); Class (philosophy); Philosophy; Mathematics; Computer science; Epistemology","score_opus":0.029135167445405306,"score_gpt":0.22217917106696036,"score_spread":0.19304400362155505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884639244","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":[0.982942,0.00071761536,0.0013992587,0.00032328482,0.0000104134415,0.0000045706215,0.000089253575,0.000020519692,0.014493139],"genre_scores_gemma":[0.9991615,0.000054216318,0.00024886453,0.000024572051,0.000009048402,0.000001368167,0.000015466541,0.000006787754,0.0004781807],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798113,0.0009559046,0.00010015773,0.0004224305,0.00036137874,0.00017899903],"domain_scores_gemma":[0.9933161,0.003968227,0.0009050025,0.00039642557,0.0011988021,0.0002154718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027605323,0.00025370053,0.0002567603,0.0017383338,0.00093551766,0.0017512809,0.00040837817,0.0004309842,0.001844853],"category_scores_gemma":[0.004565314,0.00017256103,0.00014270266,0.0009512346,0.0038323451,0.0012159906,0.00054176187,0.00052484544,0.00015384468],"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":[0.0015227007,0.00019156186,0.35489738,0.000491681,0.0002730535,0.0025476676,0.09930272,0.0019723459,0.11717565,0.23975359,0.0018653744,0.18000633],"study_design_scores_gemma":[0.00007587479,0.00045644294,0.893468,0.0001127526,0.00012417402,0.0015737622,0.0129471375,0.0024988863,0.016331406,0.029944014,0.042280823,0.00018667342],"about_ca_topic_score_codex":0.021723147,"about_ca_topic_score_gemma":0.024269236,"teacher_disagreement_score":0.021723147,"about_ca_system_score_codex":0.0023942967,"about_ca_system_score_gemma":0.00057907857,"threshold_uncertainty_score":0.0431934},"labels":[],"label_agreement":null},{"id":"W3089527804","doi":"10.1075/lv.00015.lim","title":"A typology of the mass/count distinction in Brazil and its relevance for mass/count theories","year":2020,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":13,"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":"Numeral system; Countable set; Linguistics; Noun; Indigenous; Typology; Mathematics; Geography; Pure mathematics; Philosophy; Arithmetic; Archaeology","score_opus":0.020623825848762767,"score_gpt":0.24407383037608105,"score_spread":0.22345000452731828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089527804","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":[0.8251767,0.0012200292,0.05533128,0.00367938,0.00006118872,0.000095781965,0.00030086364,0.00006474568,0.11407001],"genre_scores_gemma":[0.99751675,0.00007993096,0.0018353054,0.0000717252,0.000007803012,0.00002213388,0.000025822004,0.000011036316,0.000429536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99684745,0.0014640477,0.00020177949,0.00057040557,0.00069945824,0.00021686441],"domain_scores_gemma":[0.99296796,0.0041832943,0.001163613,0.00091743295,0.000585141,0.00018268557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003979944,0.0002258313,0.0005689161,0.0031472624,0.0027073633,0.0029719297,0.0008965787,0.00063501875,0.0026631749],"category_scores_gemma":[0.008746174,0.00022504225,0.00027211753,0.004706246,0.013713855,0.004104482,0.0033446501,0.0011048355,0.00012606665],"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":[0.00003595094,0.000016668368,0.015328839,0.00014024606,0.000012590863,0.00023751485,0.060850848,0.00017355096,0.0024917682,0.9049107,0.0005186668,0.015282619],"study_design_scores_gemma":[0.0000425664,0.00006752318,0.075493306,0.00060574914,0.00006112953,0.0013343295,0.09799362,0.0049077994,0.0026572852,0.7520009,0.06475645,0.00007923373],"about_ca_topic_score_codex":0.011364805,"about_ca_topic_score_gemma":0.016443595,"teacher_disagreement_score":0.011364805,"about_ca_system_score_codex":0.0026881734,"about_ca_system_score_gemma":0.0011674422,"threshold_uncertainty_score":0.022597313},"labels":[],"label_agreement":null},{"id":"W3089545972","doi":"10.1075/lv.00022.sal","title":"Counting and measuring in Mẽbengokre and the count/mass distinction","year":2020,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coercion (linguistics); Numeral system; Noun; Noun phrase; Linguistics; Phrase; Type (biology); Contrast (vision); Computer science; Mathematics; Natural language processing; Artificial intelligence; Philosophy","score_opus":0.029727383632731676,"score_gpt":0.2115073354473907,"score_spread":0.18177995181465903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089545972","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":[0.6781344,0.002474434,0.101347774,0.005798598,0.00014489825,0.000085760505,0.00038091722,0.00026905077,0.21136414],"genre_scores_gemma":[0.994201,0.00007826049,0.0040829554,0.00009971273,0.000012005939,0.000013237805,0.00002147311,0.000041770385,0.0014495649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99792236,0.000853965,0.00014652162,0.0004460661,0.00044062815,0.00019041963],"domain_scores_gemma":[0.9969476,0.0016073528,0.00045143682,0.00050414156,0.00038453235,0.00010480581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024429706,0.00035137127,0.0005137006,0.0015994841,0.001844185,0.0028311831,0.0006107317,0.0005277807,0.002405869],"category_scores_gemma":[0.00606308,0.00034521223,0.0002990504,0.0020711294,0.014993444,0.0047610886,0.0027991815,0.0014748324,0.0001904422],"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":[0.000023045075,0.000004309969,0.0016550053,0.000056717134,0.0000065271465,0.00009243497,0.011701303,0.00012531465,0.0020244895,0.9777169,0.00021338867,0.006380511],"study_design_scores_gemma":[0.000028606033,0.000057046902,0.02561943,0.000263978,0.00005844748,0.000822569,0.014803786,0.002704393,0.005077991,0.8730563,0.077422425,0.00008503532],"about_ca_topic_score_codex":0.013334092,"about_ca_topic_score_gemma":0.022039298,"teacher_disagreement_score":0.013334092,"about_ca_system_score_codex":0.0030812216,"about_ca_system_score_gemma":0.00094305794,"threshold_uncertainty_score":0.02651298},"labels":[],"label_agreement":null},{"id":"W3090211777","doi":"10.1075/lv.00024.bom","title":"Count and mass nouns in Patxohã","year":2020,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","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 Toronto","funders":"","keywords":"Plural; Numeral system; Noun; Linguistics; Quantifier (linguistics); Literal (mathematical logic); Computer science; Natural language processing; Noun phrase; Mathematics; Artificial intelligence; Philosophy","score_opus":0.027154424541389645,"score_gpt":0.22728857663610674,"score_spread":0.2001341520947171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090211777","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":[0.9333382,0.00073815306,0.0071095987,0.0010468088,0.000051943724,0.00005263497,0.0001614267,0.000089228575,0.05741195],"genre_scores_gemma":[0.9982591,0.000062702755,0.00076288846,0.000033071923,0.000008483962,0.00001091491,0.000016461796,0.000015299047,0.00083115767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936765,0.00020200951,0.0000412162,0.00015655915,0.00016131766,0.000071240895],"domain_scores_gemma":[0.9987897,0.00063553837,0.0002588393,0.00011580328,0.00015218456,0.000047996997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089154707,0.00024718174,0.0003340218,0.0010008839,0.0018317447,0.0018265487,0.00036343516,0.00029341172,0.0029452022],"category_scores_gemma":[0.0027495774,0.00021736424,0.00013703595,0.0016709588,0.0043445225,0.0018603622,0.0021218916,0.00069213985,0.00010277976],"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":[0.00027863085,0.00003844671,0.038656157,0.0005913394,0.00003860845,0.0023429708,0.29908824,0.00026395626,0.049215827,0.53735304,0.0012921111,0.07084068],"study_design_scores_gemma":[0.0000689789,0.00030888515,0.3152496,0.0006721183,0.00017892053,0.006980728,0.13819498,0.004269063,0.016060567,0.10369456,0.41414806,0.00017349712],"about_ca_topic_score_codex":0.009693955,"about_ca_topic_score_gemma":0.01749116,"teacher_disagreement_score":0.009693955,"about_ca_system_score_codex":0.0019297237,"about_ca_system_score_gemma":0.0006644812,"threshold_uncertainty_score":0.01927507},"labels":[],"label_agreement":null},{"id":"W3090851909","doi":"10.1075/lv.00021.tho","title":"Countability in Mbyá","year":2020,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","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 Toronto","funders":"","keywords":"Noun; Plural; Numeral system; Linguistics; Proper noun; Countable set; Mathematics; Class (philosophy); Computer science; Philosophy; Artificial intelligence; Arithmetic; Combinatorics","score_opus":0.037965042727887845,"score_gpt":0.24586784229264375,"score_spread":0.2079027995647559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090851909","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":[0.989179,0.00048197462,0.00051848026,0.0001555529,0.00000815573,0.000007945907,0.00009677123,0.000014775966,0.009537358],"genre_scores_gemma":[0.9992767,0.00004570538,0.00015671084,0.000009766158,0.0000037121854,0.0000056961194,0.000034936482,0.000007272599,0.0004594546],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986406,0.00041660524,0.00009327137,0.000331375,0.00029274824,0.00022551072],"domain_scores_gemma":[0.9978661,0.00088457554,0.00057352835,0.00022545145,0.00031360114,0.00013688649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011706828,0.000234022,0.0006967145,0.0030063703,0.002071493,0.002239877,0.00055965415,0.00031309514,0.006031695],"category_scores_gemma":[0.0050459765,0.00026165816,0.00013175509,0.0037903176,0.004156609,0.0013530873,0.0024584292,0.00057251984,0.00029893356],"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":[0.0014790478,0.000098204386,0.3438047,0.00080703455,0.00021100653,0.0026259262,0.23125817,0.00077963306,0.07187775,0.18926175,0.0020450586,0.15575176],"study_design_scores_gemma":[0.00004834123,0.0001601968,0.8992932,0.0002263234,0.000077869336,0.00200593,0.036366228,0.0009311114,0.0037905604,0.018769968,0.03826359,0.00006668106],"about_ca_topic_score_codex":0.020015877,"about_ca_topic_score_gemma":0.024014847,"teacher_disagreement_score":0.020015877,"about_ca_system_score_codex":0.0023102039,"about_ca_system_score_gemma":0.00045762642,"threshold_uncertainty_score":0.039798737},"labels":[],"label_agreement":null},{"id":"W4390790986","doi":"10.1075/lv.22012.dun","title":"Indeterminate pronouns in Kaqchikel","year":2024,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","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 Toronto","funders":"","keywords":"Interrogative word; Linguistics; Syntax; Interrogative; Relative clause; Focus (optics); Existentialism; Semantics (computer science); Indeterminate; Computer science; Mathematics; Philosophy; Pure mathematics; Programming language; Epistemology","score_opus":0.021468695546150753,"score_gpt":0.25096181454376326,"score_spread":0.22949311899761252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390790986","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":[0.9772593,0.00017334038,0.0029986459,0.00039693492,0.000009156048,0.000020091591,0.00012345385,0.00012838615,0.01889053],"genre_scores_gemma":[0.9991304,0.000021221,0.00032881254,0.000017646631,0.0000016346065,0.0000029796702,0.000015904136,0.000021338581,0.0004599498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994357,0.00018532969,0.00003446665,0.000110010275,0.000109637724,0.00012482202],"domain_scores_gemma":[0.9988285,0.0005544705,0.00020755758,0.00016803363,0.0002015794,0.000039865838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070990407,0.00024896272,0.00025283123,0.0010155961,0.0016676711,0.0018846923,0.00048986694,0.0003507817,0.0027206878],"category_scores_gemma":[0.001717715,0.00026194373,0.00014420788,0.0020588348,0.004453436,0.0017823126,0.0015647418,0.00060153316,0.00019763508],"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":[0.0004570385,0.000037946433,0.03955229,0.0006118721,0.000074328105,0.0042141797,0.3458124,0.0009158662,0.0838449,0.48275864,0.001438982,0.040281605],"study_design_scores_gemma":[0.00017591342,0.00026758172,0.31329322,0.00036264447,0.0004494913,0.0075488924,0.2571477,0.014491458,0.07606017,0.12671232,0.20300125,0.00048937195],"about_ca_topic_score_codex":0.021407558,"about_ca_topic_score_gemma":0.03195547,"teacher_disagreement_score":0.021407558,"about_ca_system_score_codex":0.0029025436,"about_ca_system_score_gemma":0.00092374324,"threshold_uncertainty_score":0.042565882},"labels":[],"label_agreement":null},{"id":"W4401420887","doi":"10.1075/lv.23057.ueg","title":"Cross-linguistic dataset of force-flavor combinations in modal elements","year":2024,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","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":"UK Research and Innovation","keywords":"Modal verb; Modal; Lexicalization; Modality (human–computer interaction); Linguistics; Typology; Computer science; Semantics (computer science); Natural language processing; Artificial intelligence; Geography; Philosophy; Archaeology; Verb","score_opus":0.029239731869712612,"score_gpt":0.2993828384759613,"score_spread":0.2701431066062487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401420887","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41911414,0.0015353794,0.014141604,0.001321805,0.0003973376,0.000580385,0.5111947,0.0015126867,0.050201915],"genre_scores_gemma":[0.32940963,0.00037986744,0.023681149,0.0007343389,0.00012694846,0.0018066767,0.6343911,0.0006123813,0.008857877],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971148,0.00095007924,0.0003636943,0.00064559985,0.0007417753,0.00018414983],"domain_scores_gemma":[0.98893636,0.0056666424,0.00091004214,0.0022140073,0.001751262,0.0005217733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002124224,0.0005384348,0.0004394148,0.0052013407,0.0018578651,0.0020444908,0.0012298931,0.0015392371,0.012258226],"category_scores_gemma":[0.012843202,0.00028959234,0.00053653127,0.0056654285,0.0014777327,0.0021354437,0.0039036255,0.001669576,0.0061174794],"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":[0.002187998,0.0011505039,0.10445048,0.0059496798,0.00032565446,0.004334325,0.027339218,0.0035669815,0.041830957,0.049055755,0.5224115,0.23739696],"study_design_scores_gemma":[0.00015667743,0.00016163796,0.1697468,0.0006574191,0.00006142584,0.0020732025,0.012942141,0.0029122275,0.008255534,0.012897336,0.7899213,0.000214366],"about_ca_topic_score_codex":0.005620156,"about_ca_topic_score_gemma":0.012171713,"teacher_disagreement_score":0.012258226,"about_ca_system_score_codex":0.0010281056,"about_ca_system_score_gemma":0.001042984,"threshold_uncertainty_score":0.041007876},"labels":[],"label_agreement":null},{"id":"W4401924416","doi":"10.1075/lv.23049.hop","title":"The emergence of vowel harmony in Armenian dialects","year":2024,"lang":"en","type":"article","venue":"Linguistic Variation","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":"Vowel harmony; Armenian; Vowel; Linguistics; Harmony (color); Mid vowel; Relative articulation; Art; Philosophy; Visual arts","score_opus":0.01987667911206416,"score_gpt":0.3258058903800464,"score_spread":0.3059292112679823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401924416","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":[0.9965738,0.00008947014,0.00013761256,0.000015733776,0.0000034333343,0.0000025442016,0.000029407629,0.0000026010232,0.0031454142],"genre_scores_gemma":[0.99957913,0.000030220659,0.000111504276,0.0000059932136,0.0000011118539,0.0000019390911,0.000024670206,0.0000018989325,0.00024359582],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99978715,0.000045648034,0.000021571776,0.000066169596,0.000033940018,0.000045525692],"domain_scores_gemma":[0.99983406,0.000053976048,0.000032770113,0.000029513909,0.00003659876,0.000013004394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042735247,0.00021165115,0.00023886422,0.0009748339,0.000775336,0.00084787223,0.00021322965,0.00019504417,0.0017839762],"category_scores_gemma":[0.00076076156,0.0001320576,0.000119671706,0.0007464432,0.0008385801,0.0003536774,0.00082649896,0.00025647305,0.00020377019],"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":[0.0026823292,0.00012829447,0.38838083,0.00048671212,0.0002860908,0.0040200036,0.1596328,0.0012281704,0.22922778,0.016755478,0.0011212247,0.19605035],"study_design_scores_gemma":[0.000019342688,0.00012730504,0.9802713,0.000049342485,0.000032750777,0.00085798535,0.010347828,0.0003445431,0.0022575948,0.0010520089,0.004615021,0.000024908875],"about_ca_topic_score_codex":0.0054466263,"about_ca_topic_score_gemma":0.011614991,"teacher_disagreement_score":0.0054466263,"about_ca_system_score_codex":0.0006100554,"about_ca_system_score_gemma":0.00019442031,"threshold_uncertainty_score":0.010829806},"labels":[],"label_agreement":null},{"id":"W4407898264","doi":"10.1075/lv.24010.mye","title":"The form and force of Kirundi exclamatives","year":2025,"lang":"en","type":"article","venue":"Linguistic Variation","topic":"Syntax, Semantics, Linguistic Variation","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":"McGill University","funders":"","keywords":"Physics","score_opus":0.015853954244831964,"score_gpt":0.24754557911260572,"score_spread":0.23169162486777375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407898264","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":[0.7683837,0.0008661074,0.0842615,0.0016884153,0.00008635017,0.00006321232,0.00025198556,0.00035327175,0.14404543],"genre_scores_gemma":[0.9956457,0.000083661405,0.0028942225,0.0000549014,0.00001552491,0.000018243165,0.00004837077,0.00006250003,0.0011768028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986173,0.0005316334,0.00015996862,0.00025276231,0.00031178095,0.00012656009],"domain_scores_gemma":[0.99666226,0.0018136558,0.00037788658,0.00044660136,0.0006178241,0.00008176635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023260445,0.0002903244,0.0003567289,0.0019029975,0.0013467721,0.0035798126,0.00076381984,0.0005636716,0.00280314],"category_scores_gemma":[0.005315671,0.00040421746,0.00030864394,0.0010249629,0.005887925,0.0062922686,0.003002457,0.00097087334,0.00027699114],"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":[0.00009590796,0.000024971674,0.008085855,0.00012712213,0.000025091153,0.00055650226,0.02235751,0.0004178588,0.010887953,0.9347459,0.00060506596,0.022070285],"study_design_scores_gemma":[0.000049238235,0.00011473318,0.023038879,0.00026703574,0.00010944628,0.003084168,0.021734837,0.009410749,0.021773677,0.8537313,0.066534825,0.00015124686],"about_ca_topic_score_codex":0.000691887,"about_ca_topic_score_gemma":0.0006039355,"teacher_disagreement_score":0.0035798126,"about_ca_system_score_codex":0.0012735,"about_ca_system_score_gemma":0.0003563255,"threshold_uncertainty_score":0.012301445},"labels":[],"label_agreement":null}]}