{"meta":{"query_hash":"1db3f6171fff","filters":{"venue":"Research in Corpus Linguistics"},"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/1db3f6171fff","api":"https://metacan.xera.ac/api/v1/cohort?venue=Research+in+Corpus+Linguistics"},"results":[{"id":"W3095271408","doi":"10.32714/ricl.08.02.04","title":"Grammaticalisation paths in the rise and development of aside","year":2020,"lang":"en","type":"article","venue":"Research in Corpus Linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"College of Pharmacy, University of Michigan; Department of Environment and Conservation, Government of Newfoundland and Labrador; University of Toronto; University of Oxford; University of Michigan; U.S. Department of Energy","keywords":"Grammaticalization; Aside; Linguistics; Variation (astronomy); Adverbial; Semantic change; History; Coalescence (physics); Philosophy; Physics","score_opus":0.2719444070045588,"score_gpt":0.44945176755662614,"score_spread":0.17750736055206734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095271408","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":[0.8853383,0.0007937615,0.0218853,0.0009385086,0.00008879043,0.000059346403,0.00012040644,0.00007847865,0.09069715],"genre_scores_gemma":[0.98950714,0.00020582364,0.0034808863,0.000059207996,0.000020004825,0.000012096996,0.00007056616,0.0000958775,0.00654833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820435,0.0006616867,0.00007570826,0.0003948829,0.00041423013,0.00024920082],"domain_scores_gemma":[0.9971675,0.0016253777,0.00026122085,0.0002877252,0.0004966147,0.00016143906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018380912,0.0002953387,0.00027597995,0.0014087973,0.0015094437,0.0023183422,0.0005331092,0.000568224,0.004695722],"category_scores_gemma":[0.0047710636,0.0004539231,0.0003701568,0.00081191387,0.0068702362,0.0045050387,0.0033375334,0.002327728,0.0007527479],"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":[0.0002798205,0.00007275937,0.033313464,0.0002931107,0.000033147324,0.002937067,0.16474135,0.00070601015,0.049907725,0.66843456,0.000762918,0.07851805],"study_design_scores_gemma":[0.00005083243,0.00043084205,0.20158514,0.0002995582,0.00008352964,0.0068237674,0.08223963,0.0026980839,0.031024374,0.43860692,0.23592134,0.0002360588],"about_ca_topic_score_codex":0.0017082504,"about_ca_topic_score_gemma":0.0025518043,"teacher_disagreement_score":0.004695722,"about_ca_system_score_codex":0.00150598,"about_ca_system_score_gemma":0.0007392601,"threshold_uncertainty_score":0.015708745},"labels":[],"label_agreement":null},{"id":"W3177588564","doi":"10.32714/ricl.09.01.08","title":"How to prepare the video component of the Diachronic Corpus of Political Speeches for multimodal analysis","year":2021,"lang":"en","type":"article","venue":"Research in Corpus Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gesture; Corpus linguistics; Linguistics; Computer science; Politics; Annotation; Multimodality; Component (thermodynamics); Metadata; Representativeness heuristic; Natural language processing; Meaning (existential); Artificial intelligence; Variation (astronomy); World Wide Web; Political science; Psychology","score_opus":0.1005764603258395,"score_gpt":0.41644334395863747,"score_spread":0.31586688363279797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177588564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061902832,0.0021766732,0.59878564,0.013886918,0.0047034705,0.015957652,0.16163728,0.030446956,0.11050259],"genre_scores_gemma":[0.06095545,0.00091528567,0.8226535,0.0013368928,0.0007588947,0.014034219,0.07284447,0.006994911,0.019506365],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979755,0.00058385904,0.00025612157,0.00050072424,0.00050963694,0.00017406941],"domain_scores_gemma":[0.9905165,0.0031598778,0.00035959997,0.0017915948,0.0036137442,0.00055861473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045514856,0.00095635356,0.0010046638,0.004667415,0.002138371,0.0037001283,0.0011467432,0.0015692808,0.059931267],"category_scores_gemma":[0.023544934,0.0010028993,0.00075401895,0.0027183301,0.0014286913,0.005053264,0.0026946575,0.002626841,0.04957677],"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":[0.0008120293,0.00027333255,0.004302203,0.0023026804,0.000052135896,0.0010995729,0.010601659,0.0015199755,0.09342032,0.02394053,0.2941804,0.5674951],"study_design_scores_gemma":[0.00018791917,0.00022453026,0.02474553,0.0006641578,0.00006370536,0.00084229244,0.009858776,0.0066076675,0.040961727,0.015588869,0.8999332,0.00032165876],"about_ca_topic_score_codex":0.008757359,"about_ca_topic_score_gemma":0.015088132,"teacher_disagreement_score":0.059931267,"about_ca_system_score_codex":0.001342835,"about_ca_system_score_gemma":0.0030304915,"threshold_uncertainty_score":0.20049006},"labels":[],"label_agreement":null},{"id":"W4380484631","doi":"10.32714/ricl.11.01.10","title":"Review of Bouzada-Jabois, Carla. 2021. Nonfinite Supplements in the Recent History of English. Bern: Peter Lang. ISBN: 978-3-034-34226-1. DOI: https://doi.org/10.3726/b19142","year":2023,"lang":"en","type":"article","venue":"Research in Corpus Linguistics","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","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":"Université Laval","funders":"","keywords":"History; Sociology; Media studies; Humanities; Art","score_opus":0.16083799585899738,"score_gpt":0.35438457380403277,"score_spread":0.19354657794503538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380484631","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006479752,0.99552506,0.000085976724,0.0014062722,0.00076728285,0.0000023760995,0.000058577716,0.000005701766,0.00208388],"genre_scores_gemma":[0.00070667674,0.9958246,0.00014341253,0.00072022725,0.0007252578,0.00000643373,0.00011172249,0.0000074896743,0.0017542337],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994797,0.0000953099,0.000085460095,0.00011472889,0.00018592205,0.00003894957],"domain_scores_gemma":[0.99789435,0.0012855086,0.00018847898,0.000052817526,0.00044622947,0.00013273487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012128333,0.00095955766,0.0014474088,0.005654769,0.0006841284,0.0023451007,0.0011811903,0.0017854382,0.016024966],"category_scores_gemma":[0.0030072066,0.0005505877,0.0004908499,0.008736006,0.0012478022,0.0038239749,0.0012992498,0.0019435375,0.0095038265],"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":[0.000056912595,0.00003221569,0.0003627097,0.022989322,0.000057230947,0.00020435135,0.0009170943,0.00014257006,0.0003413206,0.0107363975,0.28652015,0.6776398],"study_design_scores_gemma":[0.0000016628236,0.000008959365,0.0006552024,0.004741082,0.00001909034,0.00025428648,0.00017669128,0.000009969209,0.000040210416,0.00056232786,0.99352384,0.000006620153],"about_ca_topic_score_codex":0.0061439243,"about_ca_topic_score_gemma":0.010565273,"teacher_disagreement_score":0.016024966,"about_ca_system_score_codex":0.0014579721,"about_ca_system_score_gemma":0.0029682498,"threshold_uncertainty_score":0.053608894},"labels":[],"label_agreement":null},{"id":"W4408687949","doi":"10.32714/ricl.13.02.04","title":"Same, same, but erm sort of different? Comparing three kinds of fluencemes across Australian, British, Canadian, and New Zealand English","year":2025,"lang":"en","type":"article","venue":"Research in Corpus Linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"sort; Genealogy; History; Computer science; Information retrieval","score_opus":0.12172470002866462,"score_gpt":0.4163803788728151,"score_spread":0.29465567884415045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408687949","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":[0.9947837,0.00022218678,0.0005615102,0.0000568627,0.0000073118126,0.000014561522,0.00016124584,0.000007876213,0.0041846815],"genre_scores_gemma":[0.9983689,0.00013992423,0.00047252316,0.000023066317,0.0000032932833,0.000016622698,0.00020034144,0.000013717369,0.0007615668],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99920636,0.00022691359,0.00005492006,0.00017668138,0.00018839285,0.00014667264],"domain_scores_gemma":[0.99726033,0.001373394,0.0003127411,0.00016372754,0.0006499574,0.0002398164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013751803,0.00021514298,0.00026836665,0.0011564756,0.00086904934,0.001716935,0.0002792578,0.00032083556,0.0016441646],"category_scores_gemma":[0.007025358,0.00017699828,0.00017709688,0.00083001266,0.0015412971,0.0012063915,0.0009605455,0.0004574677,0.00023689939],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011018299,0.000059126698,0.30487913,0.0007809538,0.00018360582,0.0010124071,0.5100878,0.000260575,0.06478278,0.0028604856,0.0012534534,0.11273788],"study_design_scores_gemma":[0.000008268739,0.00007808824,0.9070707,0.00009468722,0.00005510493,0.00047128552,0.08403172,0.00039821607,0.0017055741,0.00036786016,0.0056671156,0.000051354134],"about_ca_topic_score_codex":0.13391422,"about_ca_topic_score_gemma":0.2287407,"teacher_disagreement_score":0.86608577,"about_ca_system_score_codex":0.0010357102,"about_ca_system_score_gemma":0.00087864464,"threshold_uncertainty_score":0.2662695},"labels":[],"label_agreement":null}]}