{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9689913,0.00010868218,0.021232134,0.00016990954,0.000018329172,0.000027938337,0.00023136738,0.000058024612,0.009162258],"genre_scores_gemma":[0.99637187,0.000026967782,0.0029790238,0.000013770458,0.000016491269,0.000022076554,0.000094040035,0.000033955752,0.00044168084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970349,0.0018152245,0.00020575809,0.00036760696,0.00046511594,0.0001114766],"domain_scores_gemma":[0.967098,0.027019655,0.0020102644,0.002601432,0.0009482528,0.00032246156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027705545,0.00019152423,0.00034305218,0.0027891544,0.0006305039,0.0013834528,0.00053487305,0.00042877314,0.0056165517],"category_scores_gemma":[0.023624027,0.0001997036,0.00040555812,0.002287036,0.0023555078,0.0027862298,0.0015341998,0.0006632689,0.00033191912],"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":[0.0008519601,0.0002218624,0.6975921,0.00029927085,0.00031395996,0.0006927004,0.023277497,0.003829469,0.022386624,0.14587958,0.0013992094,0.10325583],"study_design_scores_gemma":[0.0000803433,0.0002978111,0.76940113,0.00007772271,0.0001635643,0.0024004993,0.009844065,0.043893944,0.005464001,0.16128118,0.0069672386,0.00012854407],"about_ca_topic_score_codex":0.0018472845,"about_ca_topic_score_gemma":0.0012832633,"teacher_disagreement_score":0.0056165517,"about_ca_system_score_codex":0.0004886411,"about_ca_system_score_gemma":0.0002938501,"threshold_uncertainty_score":0.018789232},"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":"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":[0.07726739,0.00048611805,0.7227317,0.002970254,0.00020673093,0.00028290946,0.0010074036,0.0027766062,0.19227087],"genre_scores_gemma":[0.86473,0.00024805576,0.12027031,0.00067695166,0.00018749712,0.00047310523,0.000787276,0.0015788202,0.011048045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937152,0.0024976025,0.0006388008,0.0014709068,0.0011434815,0.0005339616],"domain_scores_gemma":[0.9898469,0.0032606972,0.00056745566,0.0053018974,0.00082138926,0.00020162795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005307387,0.0009250081,0.0011502162,0.001887403,0.0023914308,0.005617186,0.0021991136,0.0025755027,0.009292476],"category_scores_gemma":[0.015035832,0.0013454381,0.0023754383,0.0013092315,0.011531003,0.014962102,0.008527667,0.003676304,0.0024978444],"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":[0.000013593268,0.0000074382033,0.00055939663,0.00004195119,0.000012591949,0.00012110973,0.0014153243,0.0004140912,0.0011272875,0.98684144,0.00063568534,0.008810169],"study_design_scores_gemma":[0.00001520649,0.000019398454,0.0005152774,0.0000353305,0.000035562396,0.00030806568,0.00032026035,0.0026446213,0.0021588525,0.9686816,0.025242817,0.00002303551],"about_ca_topic_score_codex":0.0015241615,"about_ca_topic_score_gemma":0.0008776978,"teacher_disagreement_score":0.009292476,"about_ca_system_score_codex":0.0021702668,"about_ca_system_score_gemma":0.0015204058,"threshold_uncertainty_score":0.031086445},"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":"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":[0.9181035,0.0029179726,0.05139967,0.0004191025,0.0005711035,0.0014560235,0.0024283926,0.014192449,0.008511791],"genre_scores_gemma":[0.81279486,0.0006760663,0.16212167,0.00028936,0.00014387324,0.00084903836,0.017255154,0.0011613688,0.0047085406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9811257,0.00801796,0.002326293,0.0035924085,0.004434487,0.000503111],"domain_scores_gemma":[0.94427675,0.035676677,0.0024958993,0.0065814657,0.009808834,0.0011603755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016960854,0.0019211668,0.0020317992,0.0062639993,0.0018303267,0.002919605,0.0047781556,0.0030025297,0.0028031787],"category_scores_gemma":[0.07927291,0.0012107245,0.0013063313,0.0035034418,0.0015674984,0.006720194,0.004292651,0.0021284441,0.0017145445],"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":[0.004110975,0.0028964956,0.031379476,0.0030821317,0.0014641884,0.00091920636,0.0050165844,0.055096872,0.041309565,0.0024837682,0.015895633,0.83634514],"study_design_scores_gemma":[0.001545121,0.006285837,0.11650168,0.0005635111,0.0011501209,0.0027397028,0.0032949895,0.735555,0.08297993,0.0026805375,0.046202723,0.0005008871],"about_ca_topic_score_codex":0.0130294645,"about_ca_topic_score_gemma":0.015795507,"teacher_disagreement_score":0.016960854,"about_ca_system_score_codex":0.0022233275,"about_ca_system_score_gemma":0.0021027715,"threshold_uncertainty_score":0.08969867},"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":"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":[0.37468454,0.00071090966,0.60518044,0.0038065917,0.00009478695,0.00013014948,0.0005450905,0.0011155359,0.0137319425],"genre_scores_gemma":[0.9431992,0.00022070901,0.052466445,0.0003950807,0.00009290828,0.00008893093,0.00066251453,0.00022893882,0.0026453263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993948,0.0026245078,0.00041998213,0.00148922,0.0012651122,0.00025308592],"domain_scores_gemma":[0.9354948,0.05234287,0.0032502175,0.006488163,0.0016670086,0.00075693126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009605183,0.001059961,0.001019058,0.0024295326,0.000968392,0.0044566337,0.002105573,0.0024292031,0.0053613097],"category_scores_gemma":[0.06524683,0.00097004813,0.0017462581,0.0013129101,0.0053976816,0.018442005,0.0057167737,0.0045946594,0.0010397246],"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":[0.001164197,0.00032633697,0.073057875,0.0009188422,0.00056141405,0.00095392106,0.0061327107,0.078785256,0.03605828,0.33161592,0.0057862904,0.46463904],"study_design_scores_gemma":[0.00008965139,0.00020529865,0.020049753,0.00009327454,0.00012047311,0.00076182245,0.00069488236,0.26500732,0.016221246,0.6908274,0.0058080168,0.00012082497],"about_ca_topic_score_codex":0.0012926962,"about_ca_topic_score_gemma":0.0013925366,"teacher_disagreement_score":0.009605183,"about_ca_system_score_codex":0.0017210091,"about_ca_system_score_gemma":0.0007447497,"threshold_uncertainty_score":0.0507977},"labels":[],"label_agreement":null}]}