{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":15,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":15,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"a87db38be0a9","filters":{"venue":"Corpus Linguistics and Linguistic Theory"}},"results":[{"id":"W2803450908","doi":"10.1515/cllt-2016-0078","title":"Unifying dimensions in coherence relations: How various annotation frameworks are related","year":2018,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Universiteit Utrecht; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Deutsche Forschungsgemeinschaft","keywords":"Treebank; Computer science; Annotation; Coherence (philosophical gambling strategy); Dimension (graph theory); Set (abstract data type); Representation (politics); Rhetorical question; Natural language processing; Artificial intelligence; Interface (matter); Linguistics; Programming language; Mathematics","authors":[{"name":"Ted Sanders","is_ca":false},{"name":"Vera Demberg","is_ca":false},{"name":"Jet Hoek","is_ca":false},{"name":"Merel Scholman","is_ca":false},{"name":"Fatemeh Torabi Asr","is_ca":true},{"name":"Sandrine Zufferey","is_ca":false},{"name":"Jacqueline Evers-Vermeul","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01066841424052057,"gpt":0.2592416203831324,"spread":0.2485732061426119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000812283,0.0002211942,0.0002457461,0.0002546525,0.0003503434,0.0002742611,0.000486982,0.000343659,0.000008424689],"category_scores_gemma":[0.03281824,0.0002124219,0.000040289,0.0006138242,0.0002834676,0.00005130065,0.0002638514,0.0008408861,0.00001228924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007476048,"about_ca_system_score_gemma":0.0001219258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003296509,"about_ca_topic_score_gemma":0.00002731591,"domain_scores_codex":[0.9984297,0.000163468,0.0003514472,0.0005205051,0.0002067866,0.0003281279],"domain_scores_gemma":[0.9971921,0.001027524,0.0003111438,0.0005297565,0.0008258846,0.0001135716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001376753,0.00003648168,0.001493605,0.0000247467,0.00001152532,0.0001161697,0.002332924,0.000009624879,0.00008570567,0.9895647,0.00009742273,0.006213367],"study_design_scores_gemma":[0.0002364793,0.00009742706,0.0008267665,0.0005376328,0.000026857,0.00002237147,0.0000741176,0.02358327,0.0002500859,0.9709738,0.003044203,0.0003269268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008714328,0.01115993,0.965491,0.0003575131,0.003750036,0.0004798394,0.00001249482,0.001118884,0.008915956],"genre_scores_gemma":[0.8043132,0.00002700503,0.1946913,0.0002088272,0.0003554547,0.00001001006,0.000006150519,0.00001920059,0.0003688103],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7955989,"threshold_uncertainty_score":0.9753287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2315347275","doi":"10.1515/cllt-2014-0020","title":"The meaning of intonation in yes-no questions in American English: A corpus study","year":2014,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Intonation (linguistics); Linguistics; Pitch accent; Utterance; Meaning (existential); Interrogative; Context (archaeology); Sentence; Pitch contour; American English; Stress (linguistics); Phrase; Word order; Psychology; Prosody; History; Philosophy","authors":[{"name":"Nancy Hedberg","is_ca":true},{"name":"Juan Manuel Sosa","is_ca":false},{"name":"Emrah Görgülü","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01725265235915685,"gpt":0.2736270630687182,"spread":0.2563744107095614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001729759,0.0001741416,0.0003035497,0.0001752545,0.0002899662,0.0001787331,0.0003325689,0.0000302544,0.00002360357],"category_scores_gemma":[0.03119314,0.0001360071,0.00003521149,0.0001098993,0.0008386102,0.00001674755,0.0001148683,0.0003029566,0.000004946495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000436775,"about_ca_system_score_gemma":0.00008544978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001638309,"about_ca_topic_score_gemma":0.009936289,"domain_scores_codex":[0.9983208,0.0004892095,0.0005564191,0.0002212748,0.000187222,0.0002250614],"domain_scores_gemma":[0.99576,0.002564699,0.0003250327,0.0004815136,0.0008182634,0.0000504855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004683053,0.0001874576,0.003504359,0.0000187547,0.00001628365,0.00000457029,0.07082974,0.00003112683,0.000003697251,0.9209797,0.00001147701,0.004365951],"study_design_scores_gemma":[0.002100324,0.0008759134,0.01104586,0.0004380518,0.0001487702,0.000001957171,0.1201238,0.004205802,0.00001953997,0.6420239,0.2183569,0.0006591027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3152765,0.001454042,0.0002099546,0.00003763054,0.003114281,0.0006801352,0.00003455713,0.0001261779,0.6790667],"genre_scores_gemma":[0.9979078,0.00009929357,0.0001942805,0.00003572127,0.001105907,0.0000343347,0.00001047868,0.00002477575,0.0005873757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6826314,"threshold_uncertainty_score":0.9769675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756059139","doi":"10.1515/cllt-2016-0052","title":"Common ground across globalized English varieties: A multivariate exploration of mental predicates in World Englishes","year":2017,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"World Englishes; Irish; Focus (optics); Linguistics; Common ground; Varieties of English; Multivariate statistics; American English; Sociology; Computer science; Philosophy","authors":[{"name":"Sandra C. Deshors","is_ca":false},{"name":"Sandra Götz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03693167497631163,"gpt":0.3475377057381498,"spread":0.3106060307618382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002800921,0.0002310022,0.0004798995,0.0001184817,0.001202491,0.0003238306,0.0005566476,0.0001922829,0.00007718678],"category_scores_gemma":[0.1139003,0.0002390541,0.00007352573,0.0001337421,0.001303123,0.00006481478,0.0002456789,0.0002669248,0.000003202485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001050166,"about_ca_system_score_gemma":0.0002241139,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008438894,"about_ca_topic_score_gemma":0.007427241,"domain_scores_codex":[0.9977284,0.0004023468,0.0006605556,0.0004031037,0.0003333194,0.0004722927],"domain_scores_gemma":[0.9965411,0.00121419,0.0006654221,0.0005131936,0.0008737384,0.0001923816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002426451,0.0001618322,0.01014348,0.00004473336,0.0000373518,0.0000315287,0.08527803,0.000006505955,0.0000136314,0.9029628,0.0002436196,0.000833829],"study_design_scores_gemma":[0.002924255,0.000117176,0.01037866,0.0002114004,0.0001111461,0.000001071281,0.009270851,0.0003576468,0.00007910348,0.5092325,0.466806,0.000510196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2311498,0.002251905,0.005325514,0.0006012532,0.08903547,0.00393127,0.009329479,0.0007873023,0.657588],"genre_scores_gemma":[0.995694,0.0001683243,0.000706234,0.00007881143,0.002402588,0.00002526698,0.0001951482,0.00002073427,0.0007089355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7645442,"threshold_uncertainty_score":0.998164,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068619837","doi":"10.1515/cllt-2014-0011","title":"A multivariate analysis of the Old English ACC+DAT double object alternation","year":2014,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Alternation (linguistics); Linguistics; Object (grammar); Variation (astronomy); Verb; Dative case; Semantics (computer science); Psychology; Computer science; Mathematics; Philosophy","authors":[{"name":"Ludovic De Cuypere","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01790267198612642,"gpt":0.2403187402309355,"spread":0.2224160682448091,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00146587,0.000317207,0.0005859711,0.0003407486,0.000491561,0.0002482207,0.0004459921,0.0001086154,0.0002185544],"category_scores_gemma":[0.03689745,0.0002486072,0.0002469434,0.0002213678,0.0004323789,0.00001764309,0.000193033,0.0002644757,0.000009170578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005424589,"about_ca_system_score_gemma":0.00007075665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905557,"about_ca_topic_score_gemma":0.001019821,"domain_scores_codex":[0.9977999,0.000229066,0.0007519273,0.0004700774,0.0004061087,0.000342873],"domain_scores_gemma":[0.9950235,0.001600074,0.0006838979,0.0007386935,0.001843543,0.0001103125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009563101,0.00008514178,0.00215082,0.00006717261,0.0005304982,0.000002132821,0.03391878,0.0002032529,0.0000257018,0.9622929,0.00001656769,0.0006114647],"study_design_scores_gemma":[0.002439497,0.0001840302,0.008580056,0.0002829203,0.00717499,0.000001702188,0.002248306,0.05641645,0.0006418206,0.8172109,0.1038828,0.0009365882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3614446,0.0006031181,0.01980958,0.0005543529,0.06986589,0.001758511,0.0007835536,0.0006810895,0.5444993],"genre_scores_gemma":[0.9897997,0.00001710863,0.0004484601,0.0001747394,0.007487729,0.00001338108,0.00006506636,0.00004806296,0.001945784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6283551,"threshold_uncertainty_score":0.9999966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2898954967","doi":"10.1515/cllt-2018-0033","title":"An information-theoretic view on language complexity and register variation: Compressing naturalistic corpus data","year":2018,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Variation (astronomy); Register (sociolinguistics); Linguistics; Formality; Context (archaeology); Conversation; Sentence; Natural language processing; Artificial intelligence","authors":[{"name":"Katharina Ehret","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0309864596405754,"gpt":0.3110136154834371,"spread":0.2800271558428618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001216151,0.0003311959,0.0003516678,0.000176654,0.0005610811,0.0009320101,0.001450587,0.0001447073,0.00001722256],"category_scores_gemma":[0.01099728,0.0002868888,0.00002515758,0.0002289266,0.0008169664,0.0002137674,0.000759956,0.0003985438,0.00001525213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004191221,"about_ca_system_score_gemma":0.0001031485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007793528,"about_ca_topic_score_gemma":0.00001312971,"domain_scores_codex":[0.99793,0.0002371494,0.0004901536,0.0006482003,0.0003348406,0.0003596619],"domain_scores_gemma":[0.9962308,0.0007868832,0.0003598877,0.001714887,0.0006857817,0.0002217359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005102319,0.00003556044,0.00003230303,0.0001325104,0.0000145536,0.0000342098,0.002961298,6.500607e-7,0.00005628147,0.9707473,0.0001033366,0.02583099],"study_design_scores_gemma":[0.0005525411,0.0004150988,0.0004373761,0.0005123899,0.00009403037,0.0001065915,0.00007372833,0.09118986,0.0003319408,0.8788587,0.0267293,0.0006984137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00342656,0.008459058,0.9663231,0.0001925647,0.004094658,0.0006030222,0.0002608452,0.001296958,0.01534326],"genre_scores_gemma":[0.8274653,0.00004899852,0.1697605,0.001265582,0.001252063,0.000004819646,0.0001314503,0.00002134982,0.00004994979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8240387,"threshold_uncertainty_score":0.9999583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394855929","doi":"10.1515/cllt-2023-0104","title":"Corpus-based discourse analysis: from meta-reflection to accountability","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Australian Research Data Commons; Simon Fraser University; University of Sydney","keywords":"Accountability; Transparency (behavior); Objectivity (philosophy); Reflexivity; Computer science; Corpus linguistics; Consistency (knowledge bases); Subjectivity; Analytics; Data science; Reflection (computer programming); Discourse analysis; Phenomenon; Epistemology; Linguistics; Sociology; Natural language processing; Political science; Artificial intelligence; Social science; Programming language; Philosophy","authors":[{"name":"Monika Bednarek","is_ca":false},{"name":"Martin Schweinberger","is_ca":false},{"name":"Kelvin K. H. Lee","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04261411326796034,"gpt":0.3263412858121069,"spread":0.2837271725441466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009894955,0.0004451928,0.0008636234,0.0005294365,0.0005206843,0.0008524825,0.0002688509,0.00007437427,0.002536039],"category_scores_gemma":[0.005617981,0.0003388257,0.0005654879,0.0003556853,0.0006458539,0.00002673433,0.0001262024,0.0002981088,0.0001086351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000787789,"about_ca_system_score_gemma":0.0001161677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001683378,"about_ca_topic_score_gemma":0.004528697,"domain_scores_codex":[0.9976368,0.0001697561,0.0005781447,0.0008351872,0.0003840354,0.0003961009],"domain_scores_gemma":[0.9969619,0.001481395,0.0001255677,0.0006338585,0.0005980307,0.0001992284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001076194,0.000135059,0.0003332643,0.00008982736,0.0112857,0.00009580814,0.02225286,0.0003752208,0.00001520239,0.9609221,0.0006396343,0.003747671],"study_design_scores_gemma":[0.0002729688,0.0001835666,0.0002227214,0.0001488503,0.07044557,8.926394e-7,0.006098666,0.006710163,0.000105128,0.1997189,0.7150955,0.000997097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1203969,0.1229894,0.07037655,0.0008560695,0.03903935,0.00186195,0.006397379,0.002679638,0.6354027],"genre_scores_gemma":[0.9889687,0.0000562422,0.0005275541,0.0004974596,0.006094821,0.00006919583,0.0001572421,0.00005690494,0.003571925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8685718,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2327588828","doi":"10.1515/cllt.2011.008","title":"Safe harbour: Ethics and accessibility in sociolinguistic corpus building","year":2011,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Globe; Corpus linguistics; Linguistics; Computer science; Applied linguistics; Computational linguistics; Sociology; Data sharing; Natural language processing; Psychology; Philosophy","authors":[{"name":"Becky Childs","is_ca":false},{"name":"Gerard Van Herk","is_ca":true},{"name":"Jennifer Thorburn","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03852763765365219,"gpt":0.3088898463052056,"spread":0.2703622086515534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003722935,0.0004146052,0.0005079851,0.0002870772,0.0004401224,0.0002769927,0.001002565,0.000376092,0.00001313315],"category_scores_gemma":[0.06953516,0.0003923326,0.00006177234,0.0002759593,0.0005526629,0.00005200259,0.0008830013,0.001544759,0.000003557308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009580346,"about_ca_system_score_gemma":0.0002997161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002100445,"about_ca_topic_score_gemma":0.0000356249,"domain_scores_codex":[0.9970224,0.0004096489,0.0006796938,0.0009617337,0.0003228485,0.000603707],"domain_scores_gemma":[0.9955117,0.002400426,0.0003424094,0.0007827642,0.0006833333,0.0002794438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005236905,0.00007320072,0.00393391,0.0002031851,0.00001460854,0.0002585934,0.007835351,3.838753e-7,0.0001173063,0.9769413,0.000006962819,0.01056286],"study_design_scores_gemma":[0.0004029805,0.0001059785,0.002698604,0.0003277442,0.00004245555,0.000038471,0.00005596655,0.003581907,0.001158856,0.9887118,0.002330816,0.0005444175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0440216,0.04465536,0.8581573,0.0001246368,0.007399999,0.001066716,0.0000475862,0.00184211,0.04268473],"genre_scores_gemma":[0.7360911,0.0002185214,0.2627535,0.0003325642,0.000483994,0.00001259571,0.000002414821,0.00003078156,0.00007451147],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6920695,"threshold_uncertainty_score":0.9998528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2332964166","doi":"10.1515/cllt-2013-0014","title":"Topic marking in a Shanghainese corpus: from observation to prediction","year":2013,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Polytomous Rasch model; Computer science; Natural language processing; Logistic regression; Artificial intelligence; Multivariate statistics; Selection (genetic algorithm); Computational linguistics; Machine learning; Statistics; Item response theory; Mathematics; Psychometrics","authors":[{"name":"Weifeng Han","is_ca":false},{"name":"Antti Arppe","is_ca":true},{"name":"John Newman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02289286924627669,"gpt":0.2744754931635357,"spread":0.251582623917259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001063074,0.0001877822,0.0002728918,0.0001907978,0.0003248224,0.0001587412,0.0002216078,0.0001908697,0.0005658868],"category_scores_gemma":[0.0581192,0.0001968875,0.00004101362,0.0002904916,0.000156055,0.0000205057,0.00009209584,0.0002161555,0.00008095481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474784,"about_ca_system_score_gemma":0.000186028,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01306833,"about_ca_topic_score_gemma":0.002140486,"domain_scores_codex":[0.9981308,0.0002864179,0.0004781744,0.0004304127,0.0002603292,0.0004138913],"domain_scores_gemma":[0.9974669,0.00121275,0.0001496171,0.0002571269,0.0006386986,0.0002749652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004520667,0.00006711382,0.06143383,0.00001648189,0.00001768125,0.00003138944,0.01568255,0.00001597955,0.0001352327,0.9117686,0.0003930829,0.01039286],"study_design_scores_gemma":[0.0007503488,0.00008653333,0.126793,0.0001448779,0.0000540501,0.000001269925,0.001672223,0.001515228,0.00001984796,0.6081796,0.2604068,0.0003762263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7398633,0.001288996,0.01722381,0.001006655,0.02291995,0.002202619,0.0001674533,0.0005156207,0.2148115],"genre_scores_gemma":[0.9879003,0.00008918421,0.004261798,0.001112585,0.004843429,0.00007000991,0.00005237212,0.0000252884,0.001645015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.303589,"threshold_uncertainty_score":0.9935037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2563400189","doi":"10.1515/cllt-2015-0047","title":"Mass counts in World Englishes: A corpus linguistic study of noun countability in non-native varieties of English","year":2016,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"York St John University","keywords":"Linguistics; Noun; Syntax; Nominalization; World Englishes; Corpus linguistics; Applied linguistics; Varieties of English; Natural language processing; Computer science; Philosophy","authors":[{"name":"Daniel Schmidtke","is_ca":true},{"name":"Victor Kuperman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01600308910271327,"gpt":0.2859726892322059,"spread":0.2699696001294927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003082171,0.0002401206,0.000641846,0.0004070451,0.0001139849,0.0000280664,0.0003301833,0.000168461,0.0001889082],"category_scores_gemma":[0.1771167,0.0002091524,0.00005707408,0.0004867028,0.0008133995,0.00001306332,0.00008837087,0.0002664455,0.000005018095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001865787,"about_ca_system_score_gemma":0.0004940558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001933674,"about_ca_topic_score_gemma":0.00372302,"domain_scores_codex":[0.9972699,0.0005095105,0.0009360815,0.0004538936,0.0004245089,0.0004061347],"domain_scores_gemma":[0.9923182,0.004112381,0.0004667856,0.0003812392,0.002585615,0.000135803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002191852,0.0005433343,0.07765221,0.00008059808,0.00003459252,0.00004764464,0.08179921,0.000006060511,0.00001696781,0.8389749,0.00003341221,0.0005918958],"study_design_scores_gemma":[0.006771781,0.0008263008,0.03380688,0.0007942454,0.0002617061,9.637841e-7,0.02049153,0.0002169313,0.00009361434,0.781346,0.1543572,0.001032821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.246133,0.0006722658,0.001478543,0.00002166751,0.01871729,0.001684395,0.000225727,0.000118554,0.7309486],"genre_scores_gemma":[0.9967846,0.0001024352,0.0003097388,0.00003375435,0.00160269,0.00002587013,0.000004672866,0.00002657285,0.001109667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7506516,"threshold_uncertainty_score":0.8528987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2807690984","doi":"10.1515/cllt-2017-0031","title":"Dependency profiles in the large-scale analysis of discourse connectives","year":2018,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Brock University","funders":"Turun Yliopisto","keywords":"Dependency (UML); Computer science; Syntax; Natural language processing; Scope (computer science); Artificial intelligence; Linguistics; Cluster analysis; Focus (optics); Annotation","authors":[{"name":"Veronika Laippala","is_ca":false},{"name":"Aki-Juhani Kyröläinen","is_ca":true},{"name":"Jenna Kanerva","is_ca":false},{"name":"Filip Ginter","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00909766402107549,"gpt":0.2919299757573142,"spread":0.2828323117362387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001492473,0.0001660664,0.000317524,0.0003305053,0.0001608396,0.00009942574,0.00089115,0.00007872504,0.00001091374],"category_scores_gemma":[0.009501935,0.0001139119,0.00007580323,0.0009034792,0.0003694422,0.00002124211,0.0002372914,0.0002139225,0.000001529016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001666939,"about_ca_system_score_gemma":0.0000791128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004682712,"about_ca_topic_score_gemma":0.0001326414,"domain_scores_codex":[0.9985777,0.0001964655,0.0003387568,0.000377119,0.0002380456,0.0002719246],"domain_scores_gemma":[0.9977282,0.000931224,0.0002060834,0.0005922937,0.0004916548,0.00005053272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001931686,0.000085678,0.003078181,0.00002643428,0.00005954867,0.000026806,0.009592428,0.00000146185,0.00006619215,0.9840117,0.00001252895,0.003019712],"study_design_scores_gemma":[0.0002634989,0.0002042318,0.003194904,0.0001128853,0.000390102,0.0000076438,0.000977191,0.02266317,0.002030306,0.9684435,0.00139966,0.0003128761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05592057,0.007471159,0.9158127,0.00009160334,0.001373527,0.0004604826,0.00008027069,0.0002714368,0.01851822],"genre_scores_gemma":[0.9420388,0.00002496709,0.05728822,0.0001337012,0.0004336173,0.00001043824,0.000006283097,0.000009197206,0.00005472481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8861183,"threshold_uncertainty_score":0.9988415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3161046106","doi":"10.1515/cllt-2020-0028","title":"Switch-reference and its role in referential choice in Mbyá Guaraní narratives","year":2021,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Connaught Fund","keywords":"Ambiguity; Self-reference; Reference model; Computer science; Function (biology); Narrative; Linguistics; Philosophy","authors":[{"name":"Guillaume Thomas","is_ca":true},{"name":"Gregory Antono","is_ca":true},{"name":"Laurestine Bradford","is_ca":true},{"name":"Angelika Kiss","is_ca":true},{"name":"Darragh Winkelman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02712337624769755,"gpt":0.2525062085082269,"spread":0.2253828322605294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007624318,0.0003523191,0.0005210596,0.0002502086,0.0002712749,0.0002919885,0.0001850978,0.0001674087,0.0003393211],"category_scores_gemma":[0.03048988,0.0003649037,0.00004429302,0.0001054053,0.0002336761,0.00002679161,0.0001754258,0.0005357156,0.00002011144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006323929,"about_ca_system_score_gemma":0.000212008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000875667,"about_ca_topic_score_gemma":0.01229616,"domain_scores_codex":[0.9976746,0.0002208447,0.0007196206,0.0006627531,0.0002635999,0.0004585981],"domain_scores_gemma":[0.9970415,0.001400363,0.0002296025,0.0003150272,0.0008743744,0.000139146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008988033,0.0001352075,0.002286738,0.0001510999,0.00002838228,0.0001322242,0.0394589,0.000007633697,0.0001503908,0.9568182,0.000005271932,0.0007361104],"study_design_scores_gemma":[0.001329768,0.0001089649,0.004576454,0.0005077749,0.00007982682,0.00001123277,0.008520356,0.001495666,0.0002152327,0.9494047,0.03314474,0.0006052977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8095641,0.007676804,0.000227062,0.0005460823,0.007634541,0.0005267218,0.0001809659,0.0001529652,0.1734907],"genre_scores_gemma":[0.9939924,0.0002157017,0.0003309355,0.0001362286,0.003478875,0.00001923289,0.00006539088,0.00004796027,0.001713208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1844283,"threshold_uncertainty_score":0.9998803,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388046533","doi":"10.1515/cllt-2021-0058","title":"Truth be told: a corpus-based study of the cross-linguistic colexification of representational and (inter)subjective meanings","year":2023,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"Jackman Humanities Institute, University of Toronto; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Linguistics; Focus (optics); Meaning (existential); Corpus linguistics; Variation (astronomy); Computer science; Epistemology; Philosophy","authors":[{"name":"Barend Beekhuizen","is_ca":true},{"name":"M Blumenthal","is_ca":true},{"name":"Lee Jiang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03143056356154125,"gpt":0.3366006567825191,"spread":0.3051700932209779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001164326,0.0002561544,0.000427134,0.0002252826,0.0002515985,0.0000503413,0.0002639721,0.0001266984,0.00008574088],"category_scores_gemma":[0.0273432,0.0002114704,0.00009981685,0.0004515403,0.0005283419,0.000007271792,0.0001239625,0.000252988,0.000006192426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002822182,"about_ca_system_score_gemma":0.0001110375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003029087,"about_ca_topic_score_gemma":0.00004617879,"domain_scores_codex":[0.9976723,0.0003998211,0.0007243867,0.0005604957,0.000362922,0.0002800692],"domain_scores_gemma":[0.9948603,0.002700682,0.0006176049,0.0005717909,0.001151409,0.00009822356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001613733,0.0009313961,0.06233685,0.0002781119,0.0003640677,0.00008661116,0.04614919,0.00006170715,0.0004516643,0.8850365,0.00008124034,0.00260895],"study_design_scores_gemma":[0.009945262,0.002395044,0.5203324,0.0005901224,0.001876652,0.00003723914,0.0249003,0.003847663,0.002758599,0.4284253,0.003757844,0.001133606],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756017,0.0004982317,0.0009512156,0.00001115136,0.004121173,0.0007596329,0.0002401919,0.00009420639,0.01772252],"genre_scores_gemma":[0.9980556,0.00001264269,0.0000990002,0.00008097409,0.0006923586,0.00006501598,0.00005566378,0.00004416494,0.000894543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4579955,"threshold_uncertainty_score":0.9808499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405006658","doi":"10.1515/cllt-2024-0015","title":"A multivariate analysis of canonical and non-canonical uses of switch-reference markers in Mbyá narratives","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Canonical form; Computer science; Linguistics; Non canonical; Narrative; Epiphenomenon; Argument (complex analysis); Mathematics; Pure mathematics; Philosophy; Medicine","authors":[{"name":"Guillaume Thomas","is_ca":true},{"name":"Germino Duarte","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02490308447191932,"gpt":0.2710907458460139,"spread":0.2461876613740946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001128387,0.0003040177,0.0008323559,0.0006462056,0.0001228876,0.0001379948,0.0001883236,0.0001343961,0.000208842],"category_scores_gemma":[0.0148414,0.0002724892,0.0001284464,0.0002572711,0.0008477524,0.00001744408,0.0001332344,0.0003169888,0.000002584062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004773345,"about_ca_system_score_gemma":0.000307591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003091977,"about_ca_topic_score_gemma":0.003097545,"domain_scores_codex":[0.9977602,0.0001785691,0.0009603054,0.00052321,0.0002677008,0.0003100087],"domain_scores_gemma":[0.9958156,0.002827311,0.0002935294,0.0003202166,0.0006176849,0.0001256904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001936497,0.0001073731,0.003138436,0.0003858241,0.0006876828,0.00005017553,0.04319553,0.0000376499,0.0001472551,0.9513435,0.000006494733,0.0007064583],"study_design_scores_gemma":[0.001646233,0.0006537895,0.03240704,0.002120022,0.004766061,0.000007333719,0.01354657,0.05572878,0.0002261156,0.8743546,0.01331257,0.001230873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9037361,0.004062783,0.004276551,0.0002874744,0.006256714,0.0006967093,0.0008894504,0.0001412811,0.07965297],"genre_scores_gemma":[0.9974344,0.0001244637,0.001140776,0.00002718422,0.000875044,0.00001085109,0.00004005275,0.00003679108,0.0003104098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09369837,"threshold_uncertainty_score":0.9999727,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4241042034","doi":"10.1515/cllt-2012-masthead1","title":"Masthead","year":2012,"lang":"en","type":"paratext","venue":"Corpus Linguistics and Linguistic Theory","topic":"Marriage and Sexual Relationships","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","authors":[{"name":"Stefan Th","is_ca":false},{"name":"Harald Baayen","is_ca":true},{"name":"Holger Diessel","is_ca":false},{"name":"Michelle Gregory","is_ca":true},{"name":"Stefan Grondelaers","is_ca":false},{"name":"Jen Hay","is_ca":false},{"name":"Frank G. Keller","is_ca":false},{"name":"Adam Kilgarriff","is_ca":false},{"name":"Manfred Krug","is_ca":false},{"name":"Katja Markert","is_ca":false},{"name":"Laura A. Michaelis","is_ca":false},{"name":"Douglas Roland","is_ca":false},{"name":"Anna Theakston","is_ca":false},{"name":"Joe Trotta","is_ca":false},{"name":"Eniko Csomay","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04361840048096364,"gpt":0.3318367090971298,"spread":0.2882183086161661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002368652,0.0003942221,0.0005367406,0.0001867802,0.001173329,0.0002243291,0.0003929035,0.0007217611,0.006348023],"category_scores_gemma":[0.05743038,0.0003963871,0.0001138357,0.0001762853,0.000715295,0.00001058009,0.0001368542,0.0008585393,0.003456804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267494,"about_ca_system_score_gemma":0.0007262166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005124739,"about_ca_topic_score_gemma":0.0001637808,"domain_scores_codex":[0.9972017,0.0006434253,0.00049702,0.0004571708,0.0004521292,0.0007485385],"domain_scores_gemma":[0.9949797,0.003109557,0.0003350515,0.0004310127,0.0006182246,0.0005264623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000316295,0.00004729203,0.00005680997,0.0001125778,0.00005125446,0.00001759068,0.009722944,0.000001414926,0.000001013903,0.9467673,0.03901637,0.004173809],"study_design_scores_gemma":[0.0001118825,0.00003174345,0.00001624252,0.0001748504,0.000182213,0.000001621038,0.0006546032,0.000007060583,0.000001651749,0.07283348,0.9255341,0.0004505528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00004992167,0.01926921,0.00109594,0.00003225725,0.02683729,0.000313911,0.0001703441,0.00007559519,0.9521555],"genre_scores_gemma":[0.3225838,0.002997712,0.0004812402,0.000244188,0.03604879,0.00002390148,0.0001746169,0.00008790362,0.6373579],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8865178,"threshold_uncertainty_score":0.9998488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394842830","doi":"10.1515/cllt-2023-0028","title":"The distributional properties of long nominal compounds in scientific articles: an investigation based on the uniform information density hypothesis","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Constant (computer programming); Scientific literature; Information transmission; Econometrics; Data science; Information retrieval; Mathematics; Biology","authors":[{"name":"John Gamboa","is_ca":false},{"name":"Kristina Braun","is_ca":false},{"name":"Juhani Järvikivi","is_ca":true},{"name":"Shanley Allen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02148689408851192,"gpt":0.2315409293294229,"spread":0.210054035240911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002158883,0.0001337207,0.0001322209,0.0001701995,0.0004678295,0.0006274836,0.0004570065,0.00004361197,0.000001191429],"category_scores_gemma":[0.008099127,0.0000808144,0.00004421234,0.0004756323,0.0006852428,0.00008789635,0.000101356,0.0001908807,0.000003847036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008680188,"about_ca_system_score_gemma":0.0002282792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003218299,"about_ca_topic_score_gemma":0.0000587313,"domain_scores_codex":[0.9987395,0.0001508708,0.0003918876,0.0002233322,0.0003086326,0.0001857777],"domain_scores_gemma":[0.9974768,0.001384372,0.0001353088,0.0004767134,0.0004670336,0.0000598082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003008232,0.00002660479,0.0007765244,0.00004893717,0.000008640644,0.000005562481,0.001000569,0.000219572,0.0002943409,0.9877283,0.00001583083,0.009845027],"study_design_scores_gemma":[0.00008966772,0.0000768133,0.003094169,0.0002685451,0.00002756149,0.000003387,0.0001108546,0.5625045,0.01044495,0.4221849,0.001045912,0.0001486952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.488733,0.0004324335,0.5076927,0.0003275823,0.001136571,0.0004140519,0.00002729543,0.0002355636,0.0010008],"genre_scores_gemma":[0.9964358,0.00000678408,0.003307343,0.00007980612,0.0001133892,0.00001494786,0.00001165532,0.000006215166,0.00002405128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5655434,"threshold_uncertainty_score":0.9695996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}