{"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68332225,0.0014560452,0.011774108,0.036201667,0.0022250311,0.0040303194,0.000037185917,0.00012494836,0.2608284],"genre_scores_gemma":[0.9939147,0.00007418139,0.005550559,0.000100733865,0.00032470035,0.00001290919,0.0000021961296,0.0000038291196,0.00001616323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980908,0.00072846236,0.00029067564,0.00012879161,0.00052029674,0.000240991],"domain_scores_gemma":[0.9980461,0.0013920737,0.0000481381,0.000083523984,0.00034348428,0.00008665765],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004525126,0.00004276361,0.00010363836,0.000095812335,0.0001471961,0.00003301364,0.00019545441,0.00006509823,0.00002026902],"category_scores_gemma":[0.048394892,0.00003527277,0.0000083169325,0.0004176585,0.000277692,0.000007691537,0.000055138946,0.0002562912,0.000010280822],"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":[0.000036581147,0.00010569775,0.032023568,0.00008192099,0.0000045135334,0.00007528356,0.1835893,0.000016231237,0.000057208526,0.7694611,0.00029415684,0.0142544685],"study_design_scores_gemma":[0.0010454666,0.00012892322,0.024369124,0.00008994638,0.000005742145,9.767067e-7,0.028648213,0.0033097144,0.00019932493,0.06940904,0.8725996,0.00019390455],"about_ca_topic_score_codex":0.00092916697,"about_ca_topic_score_gemma":0.0015579406,"teacher_disagreement_score":0.87230545,"about_ca_system_score_codex":0.00006189874,"about_ca_system_score_gemma":0.0005405404,"threshold_uncertainty_score":0.9596209},"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":"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":[0.9762616,0.0023429166,0.00406739,0.0025310684,0.0016631123,0.0017630702,0.0009254528,0.000025713245,0.010419657],"genre_scores_gemma":[0.99760747,0.000022237493,0.00084952486,0.0000768043,0.00047599553,0.000095482865,0.000044772594,0.000018831443,0.0008088862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9971732,0.0008349948,0.00038453803,0.00035471507,0.00065519917,0.00059736375],"domain_scores_gemma":[0.9942239,0.003062174,0.000107887776,0.0008714805,0.0016138861,0.00012066545],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015167798,0.000120225464,0.00036350827,0.00022673425,0.00011213414,0.000042489297,0.00047033565,0.000114433264,0.00006167995],"category_scores_gemma":[0.012020064,0.00007900889,0.00026576596,0.0013022441,0.00034369787,0.000007950621,0.00022969501,0.00033290073,0.000005343205],"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":[0.001206731,0.0026132616,0.07950064,0.0007670871,0.0022567452,0.00020144135,0.008751296,0.0003847883,0.010851062,0.87360287,0.003015085,0.016849028],"study_design_scores_gemma":[0.009084778,0.002501178,0.4094379,0.0010551668,0.0035455876,0.00006243039,0.04907563,0.018711107,0.2580083,0.14263353,0.104359746,0.0015246543],"about_ca_topic_score_codex":0.0011954168,"about_ca_topic_score_gemma":0.0015977737,"teacher_disagreement_score":0.7309693,"about_ca_system_score_codex":0.00013510147,"about_ca_system_score_gemma":0.00027752362,"threshold_uncertainty_score":0.9963021},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046036284,0.111248955,0.0000022143945,0.00044151506,0.06492479,0.0033993584,0.0019176984,0.00016271166,0.77186644],"genre_scores_gemma":[0.5004037,0.2966564,0.0003160231,0.0015358378,0.08099881,0.00020654054,0.0026408297,0.00022795839,0.11701387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957182,0.0006544985,0.0009286386,0.000448702,0.0014597407,0.0007902672],"domain_scores_gemma":[0.98708284,0.0010675511,0.0002988005,0.0008310545,0.010587002,0.00013275405],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043074186,0.00026415565,0.0006096671,0.00079929206,0.00016805636,0.00007756184,0.0009782827,0.00011837938,0.0067836763],"category_scores_gemma":[0.07747334,0.00022732746,0.0001694825,0.0005947111,0.00066770834,0.00005698485,0.000502242,0.0010354227,0.00054712145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100707446,0.0004731779,0.014403579,0.0059903148,0.000075229145,0.000250328,0.06094196,0.000005134329,0.0000041230383,0.011666324,0.9055249,0.0005641909],"study_design_scores_gemma":[0.00057762756,0.00015391449,0.00046281668,0.002121983,0.000052331896,7.080558e-8,0.0074013006,0.00004856495,0.000027871021,0.0005082323,0.9884192,0.00022612103],"about_ca_topic_score_codex":0.0069172718,"about_ca_topic_score_gemma":0.0029005762,"teacher_disagreement_score":0.65485257,"about_ca_system_score_codex":0.0005386408,"about_ca_system_score_gemma":0.00056412246,"threshold_uncertainty_score":0.9996958},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9500299,0.00031716246,0.00004921029,0.000803318,0.0023902028,0.0005404913,0.0002116327,0.00003420886,0.045623854],"genre_scores_gemma":[0.98963153,0.00035168335,0.00040170632,0.000053663596,0.0006349453,0.0000070902333,0.000018623265,0.000010331756,0.008890416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99760187,0.00022185096,0.00051966606,0.00031186367,0.00055746303,0.0007873112],"domain_scores_gemma":[0.99681365,0.00091507286,0.00011639723,0.00024335913,0.0015290513,0.0003824568],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016449286,0.000116802694,0.00041579403,0.0003226342,0.00030804888,0.00012508674,0.00044020353,0.00023268252,0.00006552901],"category_scores_gemma":[0.024465144,0.0001387239,0.000042000655,0.00067406305,0.00091771834,0.000021110754,0.00016474075,0.00048391792,0.0000015852941],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035276582,0.00006758186,0.8905426,0.00010223591,0.000031270945,0.00005949728,0.0054726955,0.000017091717,0.000052812284,0.096657224,0.004306498,0.0026551986],"study_design_scores_gemma":[0.0021540264,0.00015636897,0.64422315,0.00085076975,0.000037610153,0.00000306008,0.0050102556,0.0003818662,0.00044974926,0.08016877,0.26618588,0.00037848766],"about_ca_topic_score_codex":0.81715167,"about_ca_topic_score_gemma":0.9051162,"teacher_disagreement_score":0.26187938,"about_ca_system_score_codex":0.00022839056,"about_ca_system_score_gemma":0.0018341047,"threshold_uncertainty_score":0.9837522},"labels":[],"label_agreement":null}]}