{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Ash Asudeh","is_ca":true},{"name":"Mary Dalrymple","is_ca":false},{"name":"Ida Toivonen","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005307387,0.0009250081,0.001150216,0.001887403,0.002391431,0.005617186,0.002199114,0.002575503,0.009292476],"category_scores_gemma":[0.01503583,0.001345438,0.002375438,0.001309232,0.011531,0.0149621,0.008527667,0.003676304,0.002497844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002170267,"about_ca_system_score_gemma":0.001520406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001524162,"about_ca_topic_score_gemma":0.0008776978,"domain_scores_codex":[0.9937152,0.002497602,0.0006388008,0.001470907,0.001143481,0.0005339616],"domain_scores_gemma":[0.9898469,0.003260697,0.0005674557,0.005301897,0.0008213893,0.0002016279],"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":[0.00001359327,0.000007438203,0.0005593966,0.00004195119,0.00001259195,0.0001211097,0.001415324,0.0004140912,0.001127288,0.9868414,0.0006356853,0.008810169],"study_design_scores_gemma":[0.00001520649,0.00001939845,0.0005152774,0.0000353305,0.0000355624,0.0003080657,0.0003202604,0.002644621,0.002158853,0.9686816,0.02524282,0.00002303551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07726739,0.000486118,0.7227317,0.002970254,0.0002067309,0.0002829095,0.001007404,0.002776606,0.1922709],"genre_scores_gemma":[0.86473,0.0002480558,0.1202703,0.0006769517,0.0001874971,0.0004731052,0.000787276,0.00157882,0.01104805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009292476,"threshold_uncertainty_score":0.03108644,"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","authors":[{"name":"Dunstan Brown","is_ca":false},{"name":"Greville G. Corbett","is_ca":false},{"name":"Sebastian Fedden","is_ca":false},{"name":"Andrew Hippisley","is_ca":false},{"name":"Paul Marriott","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002770555,0.0001915242,0.0003430522,0.002789154,0.0006305039,0.001383453,0.000534873,0.0004287731,0.005616552],"category_scores_gemma":[0.02362403,0.0001997036,0.0004055581,0.002287036,0.002355508,0.00278623,0.0015342,0.0006632689,0.0003319191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004886411,"about_ca_system_score_gemma":0.0002938501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001847284,"about_ca_topic_score_gemma":0.001283263,"domain_scores_codex":[0.9970349,0.001815225,0.0002057581,0.000367607,0.0004651159,0.0001114766],"domain_scores_gemma":[0.967098,0.02701966,0.002010264,0.002601432,0.0009482528,0.0003224616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008519601,0.0002218624,0.6975921,0.0002992708,0.00031396,0.0006927004,0.0232775,0.003829469,0.02238662,0.1458796,0.001399209,0.1032558],"study_design_scores_gemma":[0.0000803433,0.0002978111,0.7694011,0.00007772271,0.0001635643,0.002400499,0.009844065,0.04389394,0.005464001,0.1612812,0.006967239,0.0001285441],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9689913,0.0001086822,0.02123213,0.0001699095,0.00001832917,0.00002793834,0.0002313674,0.00005802461,0.009162258],"genre_scores_gemma":[0.9963719,0.00002696778,0.002979024,0.00001377046,0.00001649127,0.00002207655,0.00009404004,0.00003395575,0.0004416808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005616552,"threshold_uncertainty_score":0.01878923,"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","authors":[{"name":"Alistair Kennedy","is_ca":true},{"name":"Stan Śzpakowicz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01696085,0.001921167,0.002031799,0.006263999,0.001830327,0.002919605,0.004778156,0.00300253,0.002803179],"category_scores_gemma":[0.07927291,0.001210724,0.001306331,0.003503442,0.001567498,0.006720194,0.004292651,0.002128444,0.001714544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002223328,"about_ca_system_score_gemma":0.002102772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01302946,"about_ca_topic_score_gemma":0.01579551,"domain_scores_codex":[0.9811257,0.00801796,0.002326293,0.003592408,0.004434487,0.000503111],"domain_scores_gemma":[0.9442768,0.03567668,0.002495899,0.006581466,0.009808834,0.001160376],"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":[0.004110975,0.002896496,0.03137948,0.003082132,0.001464188,0.0009192064,0.005016584,0.05509687,0.04130957,0.002483768,0.01589563,0.8363451],"study_design_scores_gemma":[0.001545121,0.006285837,0.1165017,0.0005635111,0.001150121,0.002739703,0.003294989,0.735555,0.08297993,0.002680538,0.04620272,0.0005008871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9181035,0.002917973,0.05139967,0.0004191025,0.0005711035,0.001456024,0.002428393,0.01419245,0.008511791],"genre_scores_gemma":[0.8127949,0.0006760663,0.1621217,0.00028936,0.0001438732,0.0008490384,0.01725515,0.001161369,0.004708541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01696085,"threshold_uncertainty_score":0.08969867,"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","authors":[{"name":"Leon Bergen","is_ca":false},{"name":"E. Leigh Gibson","is_ca":false},{"name":"Timothy J. O’Donnell","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009605183,0.001059961,0.001019058,0.002429533,0.000968392,0.004456634,0.002105573,0.002429203,0.00536131],"category_scores_gemma":[0.06524683,0.0009700481,0.001746258,0.00131291,0.005397682,0.018442,0.005716774,0.004594659,0.001039725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001721009,"about_ca_system_score_gemma":0.0007447497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001292696,"about_ca_topic_score_gemma":0.001392537,"domain_scores_codex":[0.993948,0.002624508,0.0004199821,0.00148922,0.001265112,0.0002530859],"domain_scores_gemma":[0.9354948,0.05234287,0.003250218,0.006488163,0.001667009,0.0007569313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001164197,0.000326337,0.07305788,0.0009188422,0.0005614141,0.0009539211,0.006132711,0.07878526,0.03605828,0.3316159,0.00578629,0.464639],"study_design_scores_gemma":[0.00008965139,0.0002052987,0.02004975,0.00009327454,0.0001204731,0.0007618224,0.0006948824,0.2650073,0.01622125,0.6908274,0.005808017,0.000120825],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3746845,0.0007109097,0.6051804,0.003806592,0.00009478695,0.0001301495,0.0005450905,0.001115536,0.01373194],"genre_scores_gemma":[0.9431992,0.000220709,0.05246644,0.0003950807,0.00009290828,0.00008893093,0.0006625145,0.0002289388,0.002645326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009605183,"threshold_uncertainty_score":0.0507977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}