{"meta":{"query_hash":"5828fae01b08","filters":{"venue":"Journal of Language Modelling"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/5828fae01b08","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Language+Modelling"},"results":[{"id":"W1973560518","doi":"10.15398/jlm.v1i2.69","title":"Grammatical typology and frequency analysis: number availability and number use","year":2013,"lang":"en","type":"article","venue":"Journal of Language Modelling","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Economic and Social Research Council","keywords":"Animacy; Plural; Hierarchy; Typology; Noun; Linguistics; Preference; Mathematics; Noun phrase; Linguistic typology; Correspondence analysis; Computer science; Statistics; Geography; Economics; Philosophy","score_opus":0.033828561624926735,"score_gpt":0.25772476710165926,"score_spread":0.22389620547673253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973560518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97297275,0.000106861065,0.02429333,0.00094974285,0.00021065683,0.00006936214,0.0000045258007,0.000017204085,0.0013755584],"genre_scores_gemma":[0.9824971,0.00002370945,0.016615853,0.000083518695,0.0005236739,0.0000013543134,0.0000022127215,0.000014057886,0.00023855177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899644,0.00007980476,0.00048130486,0.00012503332,0.00016312643,0.00015430672],"domain_scores_gemma":[0.9989835,0.000257806,0.00025780906,0.00012687988,0.00028284604,0.00009117649],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037362648,0.00010879742,0.0003095269,0.00008728185,0.000100542595,0.00026140595,0.00006492409,0.00005813039,0.0017609531],"category_scores_gemma":[0.00025302058,0.00008505413,0.00008159993,0.000038278606,0.00013342086,0.00033695574,0.00002361151,0.00018722907,0.000042761985],"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":[0.0000497534,0.0002496905,0.19532806,0.00017229535,0.0017416218,0.00013659218,0.26504904,0.0015149163,0.0001841093,0.5336662,0.00018651698,0.0017212053],"study_design_scores_gemma":[0.0013376641,0.00013717925,0.010538896,0.00014424032,0.0031737192,0.00033950128,0.04297783,0.33592367,0.00007811482,0.60435253,0.0002656936,0.00073095364],"about_ca_topic_score_codex":0.0034324871,"about_ca_topic_score_gemma":0.00045600798,"teacher_disagreement_score":0.33440876,"about_ca_system_score_codex":0.000022435714,"about_ca_system_score_gemma":0.000016766251,"threshold_uncertainty_score":0.9991516},"labels":[],"label_agreement":null},{"id":"W2001579541","doi":"10.15398/jlm.v1i1.56","title":"Constructions with Lexical Integrity","year":2013,"lang":"en","type":"article","venue":"Journal of Language Modelling","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Leverhulme Trust","keywords":"Lexicon; Phrase; Linguistics; Syntax; Computer science; Phrase structure rules; Grammar; Natural language processing; Generalized phrase structure grammar; Word grammar; Lexical functional grammar; Artificial intelligence; Word (group theory); Lexical item; Generalization; Emergent grammar; Relational grammar; Mathematics; Philosophy","score_opus":0.03794886685939878,"score_gpt":0.24359812886115167,"score_spread":0.2056492620017529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001579541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7717448,0.00009108314,0.21532287,0.0031085522,0.00072075,0.000075075135,0.0000037563505,0.000022800265,0.008910304],"genre_scores_gemma":[0.9726283,0.000004868645,0.025313295,0.00007172619,0.0016265287,0.0000011476778,0.0000013850942,0.000011545268,0.0003412281],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928534,0.0000271719,0.00030429318,0.000066418215,0.00019949318,0.000117274634],"domain_scores_gemma":[0.9991038,0.000077410965,0.00023665429,0.00008693631,0.00043531007,0.00005992898],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016920299,0.00008056103,0.00016136526,0.00009776061,0.000118053154,0.00016533409,0.00009258369,0.00003108883,0.0012139123],"category_scores_gemma":[0.0000680392,0.00005512121,0.000060950013,0.000020368643,0.00009336879,0.00022771055,0.000009380695,0.00030318485,0.00003652151],"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":[0.000064672786,0.00018890876,0.00084778655,0.000055514996,0.00026126672,0.00011203349,0.23564264,0.01561268,0.0003545979,0.74056226,0.0003542727,0.0059433673],"study_design_scores_gemma":[0.0023738616,0.0006832974,0.00020463698,0.00075098313,0.00049755734,0.0010368624,0.25040293,0.4328364,0.0011318905,0.30546144,0.003792135,0.0008279918],"about_ca_topic_score_codex":0.0011123337,"about_ca_topic_score_gemma":0.00014382313,"teacher_disagreement_score":0.43510082,"about_ca_system_score_codex":0.000030856158,"about_ca_system_score_gemma":0.00004625701,"threshold_uncertainty_score":0.9996991},"labels":[],"label_agreement":null},{"id":"W2154726829","doi":"10.15398/jlm.v2i1.78","title":"Evaluation of automatic updates of Roget’s Thesaurus","year":2014,"lang":"en","type":"article","venue":"Journal of Language Modelling","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Thesaurus; Computer science; Information retrieval; Natural language processing; WordNet; Vocabulary; Artificial intelligence; Word (group theory); Linguistics","score_opus":0.029702668167642263,"score_gpt":0.3008975775526793,"score_spread":0.27119490938503704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154726829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26392055,0.0050595566,0.7306725,0.0000615986,0.000067608555,0.0000506405,4.2758418e-7,0.000029747613,0.00013743585],"genre_scores_gemma":[0.602397,0.000009416543,0.39753357,0.000016535707,0.00003466072,5.169632e-7,2.2391183e-7,0.0000048286956,0.0000032427617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980474,0.00020811388,0.0005675658,0.00009923137,0.00096188555,0.00011578179],"domain_scores_gemma":[0.997761,0.00013546705,0.00091901224,0.0002915827,0.00085372425,0.000039204828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041448222,0.00009148331,0.0002773034,0.00023029269,0.000023101524,0.00003259806,0.0007039059,0.000054797372,0.000012695464],"category_scores_gemma":[0.00030577782,0.00006791489,0.0001040762,0.0002186445,0.000026957989,0.0004454048,0.000067808214,0.00015441392,7.454004e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019256246,0.00020679252,0.00013210395,0.00034311676,0.00015338635,0.000019057848,0.01854353,0.12463038,0.07830291,0.016738754,0.000085567495,0.76082516],"study_design_scores_gemma":[0.00020105785,0.00007628333,0.0000056600315,0.0002428912,0.000059339945,0.000032733577,0.00008395118,0.8357712,0.13184024,0.03162175,0.0000046781092,0.000060206567],"about_ca_topic_score_codex":0.000019956567,"about_ca_topic_score_gemma":0.0000011693346,"teacher_disagreement_score":0.76076496,"about_ca_system_score_codex":0.00004156646,"about_ca_system_score_gemma":0.00011237341,"threshold_uncertainty_score":0.27694887},"labels":[],"label_agreement":null},{"id":"W4365139124","doi":"10.15398/jlm.v10i2.263","title":"Simplicity and learning to distinguish arguments from modifiers","year":2022,"lang":"en","type":"article","venue":"Journal of Language Modelling","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Argument (complex analysis); Lexicon; Simplicity; Learnability; Computer science; Simple (philosophy); Argument map; Artificial intelligence; Natural language processing; Linguistics; Epistemology; Philosophy","score_opus":0.020543879023698513,"score_gpt":0.2515011090621402,"score_spread":0.23095723003844168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365139124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5141183,0.00011706129,0.48544425,0.00017250754,0.000066807486,0.000026202853,0.0000016752006,0.000010781462,0.00004239912],"genre_scores_gemma":[0.9545731,0.000003196811,0.045133784,0.00016810032,0.00006813731,0.0000017760691,0.0000013596707,0.0000045880206,0.00004596101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990609,0.00012182719,0.00024638075,0.0001535834,0.00029410177,0.00012318157],"domain_scores_gemma":[0.99938136,0.0001311383,0.00018048885,0.00015513087,0.000051995306,0.00009986571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415008,0.0000636029,0.00012818204,0.00008305127,0.00025859187,0.00009580403,0.00036782518,0.000015920403,0.000012654994],"category_scores_gemma":[0.000088958506,0.00006139026,0.000042714808,0.00014568023,0.000008208283,0.00018731895,0.00019412873,0.00035349457,0.0000011493853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020634354,0.000044648194,0.00093923515,0.0000047394014,0.000016970413,0.000038168502,0.03336633,0.916955,0.0031614779,0.0004968457,0.000036336995,0.044919636],"study_design_scores_gemma":[0.00021473276,0.0001233124,0.0005963829,0.000013032547,0.000009897899,0.000048351623,0.002791848,0.99166274,0.0004613942,0.0028124948,0.0011466254,0.00011920562],"about_ca_topic_score_codex":0.0001996812,"about_ca_topic_score_gemma":0.0000022610106,"teacher_disagreement_score":0.44045478,"about_ca_system_score_codex":0.000073428375,"about_ca_system_score_gemma":0.000026182284,"threshold_uncertainty_score":0.25034222},"labels":[],"label_agreement":null}]}