{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002800641,0.0001000314,0.0004196591,0.0001511818,0.0001524437,0.00006509134,0.0002157623,0.00003240354,0.000003159093],"category_scores_gemma":[0.000217142,0.00006061589,0.0001836062,0.000865191,0.0001379211,0.000204593,0.0001638318,0.0001814874,1.872866e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000152647,"about_ca_system_score_gemma":0.00009877111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001729249,"about_ca_topic_score_gemma":0.00005017167,"domain_scores_codex":[0.9989535,0.0001041639,0.0003908346,0.0001176836,0.0003119165,0.0001219673],"domain_scores_gemma":[0.9984534,0.0002790042,0.0006070658,0.000220349,0.0003823997,0.00005779342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005369758,0.003268456,0.4843884,0.0002775436,0.04609189,0.001970676,0.04859805,0.01692001,0.01688757,0.062119,0.005696412,0.313245],"study_design_scores_gemma":[0.008270719,0.004102048,0.4010865,0.003327665,0.02963896,0.003823606,0.2901322,0.1156203,0.0189594,0.1092403,0.01305129,0.002746954],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8610169,0.006112795,0.1291984,0.002903452,0.0006950008,0.00003030488,0.000004790416,0.00000575454,0.00003250948],"genre_scores_gemma":[0.9781513,0.00134918,0.02010202,0.0002261184,0.0001377496,3.988347e-7,7.071412e-7,0.000003718498,0.00002879058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.310498,"threshold_uncertainty_score":0.2471844,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004074292,0.0002614354,0.0005864958,0.000220192,0.0005641204,0.0005054556,0.0001188012,0.00002907876,0.0001627015],"category_scores_gemma":[0.0001934688,0.0001701143,0.0001979457,0.00008508297,0.0009043409,0.0005881294,0.00009427115,0.0002707916,0.00002522426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004834796,"about_ca_system_score_gemma":0.00007281671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007151073,"about_ca_topic_score_gemma":0.0007099202,"domain_scores_codex":[0.9984198,0.00006477185,0.0006747385,0.0002449917,0.00038648,0.0002092818],"domain_scores_gemma":[0.9979146,0.0008593545,0.0003438116,0.0001081801,0.0006576838,0.0001163878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001454077,0.0003955075,0.006808178,0.0006572554,0.01363465,0.001025059,0.64671,0.0001104569,0.0001839237,0.1260584,0.09687239,0.1060902],"study_design_scores_gemma":[0.0008391807,0.0006597113,0.00368838,0.001302268,0.00115139,0.00009884332,0.3368544,0.00002681537,0.00002040095,0.02641311,0.6284973,0.0004481485],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7544999,0.2111549,0.0001974593,0.01282902,0.013965,0.0001878837,0.0003090331,0.00007194768,0.006784939],"genre_scores_gemma":[0.9873573,0.005283833,0.000183511,0.0002501565,0.004621899,0.000009617413,0.000003996479,0.00002269562,0.002266981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5316249,"threshold_uncertainty_score":0.6937059,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008483375,0.0003395891,0.001485054,0.0005959478,0.0005062516,0.0001309961,0.0003237946,0.00005933052,0.00007128042],"category_scores_gemma":[0.0003048826,0.0001809695,0.0005243575,0.0006085398,0.002195644,0.0003682674,0.0003402379,0.0002407139,0.000001738267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002996078,"about_ca_system_score_gemma":0.00008872781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003285491,"about_ca_topic_score_gemma":0.003149871,"domain_scores_codex":[0.9972603,0.0001640206,0.001085746,0.0002669151,0.000912488,0.0003105746],"domain_scores_gemma":[0.9969359,0.0002081704,0.001518904,0.0003173906,0.0009335061,0.00008609615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001327019,0.001354924,0.0624776,0.001472855,0.07056057,0.0002669781,0.671593,0.0004272812,0.00788599,0.1378882,0.02948352,0.01526205],"study_design_scores_gemma":[0.002460076,0.0008335991,0.1248025,0.002265732,0.02199496,0.00004044935,0.8320719,0.0005006131,0.001271168,0.005950398,0.00685171,0.0009569372],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9667546,0.02912228,0.000009542934,0.00140129,0.0004072898,0.0001538848,0.00007139423,0.00002041887,0.00205929],"genre_scores_gemma":[0.9935281,0.003095194,0.00003669684,0.00009569128,0.0002917661,0.000009846418,0.000002404515,0.00002263923,0.002917633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1604789,"threshold_uncertainty_score":0.8089941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}