{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"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":"bcdf9eba7291","filters":{"venue":"Theoretical and Applied Linguistics"}},"results":[{"id":"W3179142225","doi":"10.22250/2410-7190_2021_7_2_160_168","title":"ENGLISH WORD STRESS IN LONG-TERM LANGUAGE CONTACT","year":2021,"lang":"en","type":"article","venue":"Theoretical and Applied Linguistics","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Linguistics; Language contact; Stress (linguistics); Variety (cybernetics); Syllable; Assimilation (phonology); Lexicon; Term (time); Varieties of English; History; Perspective (graphical); Psychology; Computer science; Artificial intelligence","authors":[{"name":"TATIANA SHEVCHENKO","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008880693194363251,"gpt":0.2225417419911253,"spread":0.2136610487967621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003295857,0.0001608081,0.000184088,0.0008492052,0.0007699336,0.001295867,0.0002040546,0.000267274,0.003100221],"category_scores_gemma":[0.001903607,0.00007663834,0.0001186016,0.001647219,0.0008175973,0.0007858977,0.0009781744,0.0002859399,0.0003125351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001020964,"about_ca_system_score_gemma":0.0005858037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.020041,"about_ca_topic_score_gemma":0.02655007,"domain_scores_codex":[0.9996953,0.00005559871,0.00002487194,0.00005181564,0.0001047631,0.00006764713],"domain_scores_gemma":[0.9984272,0.0005070841,0.0004538971,0.00005062407,0.0003395524,0.0002216683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009898564,0.0001741252,0.8398413,0.0002524152,0.00005382216,0.001836948,0.07975623,0.0001559909,0.02258149,0.002158737,0.0005059461,0.05169307],"study_design_scores_gemma":[0.000002058521,0.00006867486,0.9838188,0.00001698655,0.000009341878,0.0001988735,0.01389685,0.00003723266,0.0004842594,0.0002485988,0.001208884,0.000009333962],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972378,0.0003588269,0.000061865,0.00003374806,0.000004026237,0.000002100312,0.00005300842,0.000001530789,0.002247098],"genre_scores_gemma":[0.999177,0.0001352905,0.00002501306,0.000009707818,0.000005247738,0.000002544448,0.00005625754,0.000002192836,0.0005867215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.020041,"threshold_uncertainty_score":0.03984869,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414739115","doi":"10.22250/24107190-2025-11-3-87","title":"Corpus-based discourse analysis of connected speech phenomena in typologically diverse languages","year":2025,"lang":"en","type":"article","venue":"Theoretical and Applied Linguistics","topic":"Discourse Analysis and Cultural Communication","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Scripting language; Annotation; Python (programming language); Computational linguistics; Speech corpus; Corpus linguistics; Natural language; Text corpus","authors":[{"name":"Veronika G. Karavaeva","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01298485957063372,"gpt":0.339433345069315,"spread":0.3264484854986813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003958081,0.0006649788,0.0005468841,0.009439089,0.001864484,0.002665513,0.001042133,0.0006854267,0.004317331],"category_scores_gemma":[0.009181015,0.0003511913,0.0006216606,0.005862522,0.001423952,0.002107766,0.002501993,0.0009147793,0.0009520021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268752,"about_ca_system_score_gemma":0.002123036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002981964,"about_ca_topic_score_gemma":0.003888549,"domain_scores_codex":[0.9949636,0.002538141,0.0004479245,0.001191559,0.0007429597,0.0001157882],"domain_scores_gemma":[0.9903122,0.006313483,0.0005035007,0.001147773,0.001524683,0.000198333],"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":[0.0005913936,0.0006759804,0.02016732,0.003283543,0.0003282557,0.00190183,0.06608295,0.009232857,0.1407667,0.09172229,0.0103007,0.6549463],"study_design_scores_gemma":[0.0001918333,0.0006861563,0.1216224,0.001612313,0.0005681681,0.003503358,0.07108557,0.193423,0.1630396,0.09912545,0.3446185,0.0005237925],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1948187,0.001289778,0.7713728,0.0003657627,0.0002042421,0.002693627,0.01054613,0.002064516,0.01664446],"genre_scores_gemma":[0.2874033,0.0004594429,0.6919478,0.00005792571,0.00006196276,0.004240481,0.01198652,0.0004255957,0.003416979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009439089,"threshold_uncertainty_score":0.02093256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}