{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":3,"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":"5f1bc1b48263","filters":{"venue":"Journal of Corpora and Discourse Studies"}},"results":[{"id":"W3157076142","doi":"10.18573/jcads.61","title":"A corpus analysis of online news comments using the Appraisal framework","year":2021,"lang":"en","type":"article","venue":"Journal of Corpora and Discourse Studies","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Judgement; Affect (linguistics); Variety (cybernetics); Appraisal theory; Newspaper; Moderation; Globe; Constructive; Sentiment analysis; Psychology; Computer science; Linguistics; Natural language processing; Social psychology; Artificial intelligence; Sociology; Epistemology; Communication; Process (computing); Media studies","authors":[{"name":"Luca Cavasso","is_ca":true},{"name":"Maite Taboada","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05755865043613934,"gpt":0.3812312372235067,"spread":0.3236725867873673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003249815,0.0005312169,0.0004201985,0.006967308,0.001881874,0.001555747,0.0004985877,0.0005070425,0.002570521],"category_scores_gemma":[0.01938005,0.0002484074,0.0003394857,0.007906023,0.0008777567,0.00115203,0.001043961,0.000798171,0.0009399098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008580819,"about_ca_system_score_gemma":0.001131024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006263672,"about_ca_topic_score_gemma":0.01017361,"domain_scores_codex":[0.9953257,0.002271954,0.0003824256,0.0006803113,0.001156149,0.0001834634],"domain_scores_gemma":[0.9708307,0.01959578,0.001972604,0.001463289,0.005758304,0.0003793999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001801909,0.0007569722,0.08899114,0.004537857,0.0001734679,0.003046792,0.144843,0.002717751,0.1822074,0.009942372,0.03268848,0.5282929],"study_design_scores_gemma":[0.0001736079,0.0009969324,0.5370911,0.001112972,0.0002734021,0.003439648,0.08287644,0.05398107,0.05691796,0.008483779,0.2542209,0.0004321967],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8790129,0.001323106,0.07899019,0.0007941949,0.0002840114,0.002252801,0.01987051,0.001018753,0.0164535],"genre_scores_gemma":[0.7827486,0.0008237325,0.1776066,0.0001480885,0.0002240035,0.003576885,0.0262185,0.0003992795,0.008254272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006967308,"threshold_uncertainty_score":0.01718682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399212702","doi":"10.18573/jcads.117","title":"From cross-linguistic to intersectional corpus-assisted discourse studies","year":2024,"lang":"en","type":"article","venue":"Journal of Corpora and Discourse Studies","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Linguistics; Corpus linguistics; Sociology; Philosophy","authors":[{"name":"Rachelle Vessey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1300079590363563,"gpt":0.4210742496369067,"spread":0.2910662906005504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05434548,0.001084082,0.001412266,0.01923914,0.008482015,0.02083088,0.00487728,0.003075889,0.009775093],"category_scores_gemma":[0.1056217,0.001079312,0.0006767774,0.01893564,0.02645986,0.03580287,0.03178176,0.005136345,0.001508429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007178092,"about_ca_system_score_gemma":0.004771614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003924158,"about_ca_topic_score_gemma":0.005630754,"domain_scores_codex":[0.9370027,0.0501304,0.00244914,0.004279194,0.005293451,0.0008452339],"domain_scores_gemma":[0.8663592,0.1023847,0.003712989,0.0180283,0.008262128,0.001252713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001045822,0.0001135918,0.005865223,0.001456284,0.0001362377,0.000590432,0.300807,0.0006445276,0.0009630212,0.5722702,0.004922958,0.1121259],"study_design_scores_gemma":[0.00005236622,0.00006328969,0.005981588,0.004875858,0.0000888931,0.0006977829,0.2396377,0.004589706,0.003022833,0.4727584,0.2681212,0.0001104691],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2004379,0.03623959,0.4203442,0.02933691,0.001422118,0.001049225,0.003225332,0.0009445717,0.307],"genre_scores_gemma":[0.8415859,0.006324294,0.1389657,0.001670315,0.0004727987,0.00196237,0.002411134,0.0005337146,0.006073763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05434548,"threshold_uncertainty_score":0.2874098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386514035","doi":"10.18573/jcads.90","title":"'Her dreadful plight': A corpus-assisted analysis of the indexical and stance properties of <em>poor thing</em>","year":2023,"lang":"en","type":"article","venue":"Journal of Corpora and Discourse Studies","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Pittsburgh","keywords":"Referent; Linguistics; Expression (computer science); Indexicality; Meaning (existential); Grammaticalization; Psychology; Sociology; Computer science; Philosophy","authors":[{"name":"Sean Nonnenmacher","is_ca":false},{"name":"Ben Naismith","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04979563293252166,"gpt":0.2898047808482827,"spread":0.240009147915761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002941038,0.0003808175,0.0003303168,0.003956151,0.002538859,0.002370909,0.0006810887,0.0005875091,0.003855516],"category_scores_gemma":[0.01122005,0.0002964256,0.0001825439,0.004037589,0.00241155,0.002138699,0.00200031,0.001326252,0.0008554633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001670684,"about_ca_system_score_gemma":0.001401138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01629358,"about_ca_topic_score_gemma":0.03277998,"domain_scores_codex":[0.9985411,0.0008467546,0.0001133611,0.0002440685,0.000185358,0.00006938115],"domain_scores_gemma":[0.9829845,0.01325828,0.0009357652,0.001010884,0.001603147,0.0002073413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006089109,0.0005107064,0.03062274,0.003744282,0.00009006545,0.00277359,0.5848021,0.0008330269,0.06920752,0.05383817,0.0527405,0.2002283],"study_design_scores_gemma":[0.0001369712,0.0001482471,0.1904446,0.001321117,0.0001798988,0.003821743,0.3513606,0.01603621,0.03275067,0.007805161,0.3957937,0.0002009996],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9363723,0.001623256,0.0162713,0.001470906,0.0002034612,0.0004281494,0.01133282,0.0003063501,0.03199146],"genre_scores_gemma":[0.9491389,0.0007795539,0.03281978,0.0002110326,0.00006284525,0.0006694914,0.01049907,0.0003886465,0.00543084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01629358,"threshold_uncertainty_score":0.03239751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}