{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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"},"query_hash":"5828fae01b08","filters":{"venue":"Journal of Language Modelling"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03794886685939878,"gpt":0.2435981288611517,"spread":0.2056492620017529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000169203,0.00008056103,0.0001613653,0.00009776061,0.0001180532,0.0001653341,0.00009258369,0.00003108883,0.001213912],"category_scores_gemma":[0.0000680392,0.00005512121,0.00006095001,0.00002036864,0.00009336879,0.0002277106,0.000009380695,0.0003031848,0.00003652151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003085616,"about_ca_system_score_gemma":0.00004625701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001112334,"about_ca_topic_score_gemma":0.0001438231,"domain_scores_codex":[0.9992853,0.0000271719,0.0003042932,0.00006641822,0.0001994932,0.0001172746],"domain_scores_gemma":[0.9991038,0.00007741096,0.0002366543,0.00008693631,0.0004353101,0.00005992898],"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":[0.00006467279,0.0001889088,0.0008477865,0.000055515,0.0002612667,0.0001120335,0.2356426,0.01561268,0.0003545979,0.7405623,0.0003542727,0.005943367],"study_design_scores_gemma":[0.002373862,0.0006832974,0.000204637,0.0007509831,0.0004975573,0.001036862,0.2504029,0.4328364,0.00113189,0.3054614,0.003792135,0.0008279918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7717448,0.00009108314,0.2153229,0.003108552,0.00072075,0.00007507514,0.00000375635,0.00002280026,0.008910304],"genre_scores_gemma":[0.9726283,0.000004868645,0.0253133,0.00007172619,0.001626529,0.000001147678,0.000001385094,0.00001154527,0.0003412281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4351008,"threshold_uncertainty_score":0.9996991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03382856162492674,"gpt":0.2577247671016593,"spread":0.2238962054767325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003736265,0.0001087974,0.0003095269,0.00008728185,0.0001005426,0.0002614059,0.00006492409,0.00005813039,0.001760953],"category_scores_gemma":[0.0002530206,0.00008505413,0.00008159993,0.00003827861,0.0001334209,0.0003369557,0.00002361151,0.0001872291,0.00004276199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002243571,"about_ca_system_score_gemma":0.00001676625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003432487,"about_ca_topic_score_gemma":0.000456008,"domain_scores_codex":[0.9989964,0.00007980476,0.0004813049,0.0001250333,0.0001631264,0.0001543067],"domain_scores_gemma":[0.9989835,0.000257806,0.0002578091,0.0001268799,0.000282846,0.00009117649],"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":[0.0000497534,0.0002496905,0.1953281,0.0001722953,0.001741622,0.0001365922,0.265049,0.001514916,0.0001841093,0.5336662,0.000186517,0.001721205],"study_design_scores_gemma":[0.001337664,0.0001371792,0.0105389,0.0001442403,0.003173719,0.0003395013,0.04297783,0.3359237,0.00007811482,0.6043525,0.0002656936,0.0007309536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9729728,0.0001068611,0.02429333,0.0009497429,0.0002106568,0.00006936214,0.000004525801,0.00001720409,0.001375558],"genre_scores_gemma":[0.9824971,0.00002370945,0.01661585,0.00008351869,0.0005236739,0.000001354313,0.000002212721,0.00001405789,0.0002385518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3344088,"threshold_uncertainty_score":0.9991516,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02970266816764226,"gpt":0.3008975775526793,"spread":0.271194909385037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004144822,0.00009148331,0.0002773034,0.0002302927,0.00002310152,0.00003259806,0.0007039059,0.00005479737,0.00001269546],"category_scores_gemma":[0.0003057778,0.00006791489,0.0001040762,0.0002186445,0.00002695799,0.0004454048,0.00006780821,0.0001544139,7.454004e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004156646,"about_ca_system_score_gemma":0.0001123734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001995657,"about_ca_topic_score_gemma":0.000001169335,"domain_scores_codex":[0.9980474,0.0002081139,0.0005675658,0.00009923137,0.0009618856,0.0001157818],"domain_scores_gemma":[0.997761,0.0001354671,0.0009190122,0.0002915827,0.0008537243,0.00003920483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001925625,0.0002067925,0.0001321039,0.0003431168,0.0001533864,0.00001905785,0.01854353,0.1246304,0.07830291,0.01673875,0.0000855675,0.7608252],"study_design_scores_gemma":[0.0002010578,0.00007628333,0.000005660032,0.0002428912,0.00005933995,0.00003273358,0.00008395118,0.8357712,0.1318402,0.03162175,0.000004678109,0.00006020657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2639205,0.005059557,0.7306725,0.0000615986,0.00006760855,0.0000506405,4.275842e-7,0.00002974761,0.0001374359],"genre_scores_gemma":[0.602397,0.000009416543,0.3975336,0.00001653571,0.00003466072,5.169632e-7,2.239118e-7,0.000004828696,0.000003242762],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.760765,"threshold_uncertainty_score":0.2769489,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02054387902369851,"gpt":0.2515011090621402,"spread":0.2309572300384417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415008,0.0000636029,0.000128182,0.00008305127,0.0002585919,0.00009580403,0.0003678252,0.0000159204,0.00001265499],"category_scores_gemma":[0.00008895851,0.00006139026,0.00004271481,0.0001456802,0.000008208283,0.0001873189,0.0001941287,0.0003534946,0.000001149385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007342837,"about_ca_system_score_gemma":0.00002618228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001996812,"about_ca_topic_score_gemma":0.000002261011,"domain_scores_codex":[0.9990609,0.0001218272,0.0002463807,0.0001535834,0.0002941018,0.0001231816],"domain_scores_gemma":[0.9993814,0.0001311383,0.0001804888,0.0001551309,0.00005199531,0.00009986571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002063435,0.00004464819,0.0009392351,0.000004739401,0.00001697041,0.0000381685,0.03336633,0.916955,0.003161478,0.0004968457,0.00003633699,0.04491964],"study_design_scores_gemma":[0.0002147328,0.0001233124,0.0005963829,0.00001303255,0.000009897899,0.00004835162,0.002791848,0.9916627,0.0004613942,0.002812495,0.001146625,0.0001192056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5141183,0.0001170613,0.4854442,0.0001725075,0.00006680749,0.00002620285,0.000001675201,0.00001078146,0.00004239912],"genre_scores_gemma":[0.9545731,0.000003196811,0.04513378,0.0001681003,0.00006813731,0.000001776069,0.000001359671,0.000004588021,0.00004596101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4404548,"threshold_uncertainty_score":0.2503422,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}