{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001392852,0.0001663868,0.0002654542,0.0000511427,0.0001458404,0.0002372604,0.0001325086,0.00007177641,0.00184069],"category_scores_gemma":[0.009224753,0.000154368,0.00004703962,0.00003884019,0.0005060955,0.00001197254,0.0001648053,0.0002491714,0.00003755182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000210694,"about_ca_system_score_gemma":0.00002797405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005026928,"about_ca_topic_score_gemma":0.0005090818,"domain_scores_codex":[0.9990059,0.00003354087,0.0002225682,0.0002771628,0.0001695263,0.0002913736],"domain_scores_gemma":[0.9986469,0.0001801074,0.00004350635,0.0001959304,0.000814552,0.0001189847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003578024,0.0001511979,0.005164518,0.0001101636,0.00002082384,0.000183464,0.03255063,5.790421e-7,0.000007440111,0.9608677,0.0003945385,0.0005131532],"study_design_scores_gemma":[0.01132843,0.0003644725,0.02550818,0.001299883,0.001260703,0.000004458099,0.3114189,0.0003505115,0.0165646,0.5561603,0.0708575,0.00488206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7674292,0.0004317366,0.00003597202,0.00001021571,0.007307477,0.0001348797,0.0001913957,0.000099287,0.2243599],"genre_scores_gemma":[0.9802911,0.00005393945,0.00008324061,0.0002380998,0.01865623,0.000003046558,0.00009911812,0.00001712304,0.0005580757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4047074,"threshold_uncertainty_score":0.999121,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004476845,0.00007880908,0.0002825418,0.0001318709,0.0001266813,0.00002856584,0.0001956795,0.00007021425,0.0002694266],"category_scores_gemma":[0.0007783371,0.00005920258,0.00006310787,0.0008744552,0.001222919,0.000005109668,0.00005698427,0.0001004928,0.000002016161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001928479,"about_ca_system_score_gemma":0.00004035574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00021921,"about_ca_topic_score_gemma":0.0007088418,"domain_scores_codex":[0.9992391,0.0001074569,0.0002089929,0.0001456609,0.0001491658,0.0001495763],"domain_scores_gemma":[0.9992735,0.0003435199,0.00006705887,0.0001685151,0.00009768129,0.00004976582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004158996,0.0001082799,0.002299698,0.000005389617,0.0001021351,0.000001255157,0.0006684901,0.00009534181,0.00007818697,0.9908807,0.00001469306,0.005704233],"study_design_scores_gemma":[0.002547944,0.0001673435,0.04915309,0.0001653938,0.00695228,7.896898e-8,0.1137019,0.01449527,0.001640731,0.7920298,0.01809634,0.001049834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4021178,0.0001479162,0.000362834,0.0006340742,0.00003333099,0.0001401948,0.00002578648,0.00003091799,0.5965071],"genre_scores_gemma":[0.9990621,0.00008463842,0.000425332,0.000169231,0.00005207093,0.000004595579,0.0000563734,0.000002178828,0.0001434445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5969443,"threshold_uncertainty_score":0.4505895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}