{"id":"W4387120355","doi":"10.5539/ijel.v13n5p122","title":"A Corpus-Based Approach to Investigate the Cohesive Features Across Different Levels of CEFR","year":2023,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cohesion (chemistry); Sentence; Natural language processing; Artificial intelligence; Competence (human resources); Computer science; Psychology; Empirical research; Linguistics; Mathematics; Social psychology; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005511746,0.000123703,0.0002130695,0.0001965121,0.00005694306,0.00006540571,0.0005983667,0.00007690712,0.0006388282],"category_scores_gemma":[0.03214749,0.00008678614,0.0001437137,0.0002012155,0.00009797511,0.00001676382,0.00006776922,0.0003996541,0.00001994172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004831904,"about_ca_system_score_gemma":0.00005962923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001568775,"about_ca_topic_score_gemma":0.000002856068,"domain_scores_codex":[0.9985713,0.0001431881,0.0004691235,0.0001307723,0.0004922721,0.0001933878],"domain_scores_gemma":[0.9916056,0.0006455091,0.0004469788,0.0001708005,0.00701992,0.0001111483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003223801,0.002118226,0.02119596,0.0001744046,0.004575436,0.00171764,0.2758822,0.07820415,0.0025433,0.1607654,0.4267601,0.02283941],"study_design_scores_gemma":[0.005906416,0.0007477448,0.3871323,0.0004075114,0.0001851423,0.00006355147,0.0347693,0.0008403917,0.007641682,0.002311485,0.5593272,0.0006672657],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9100878,0.001097337,0.002403287,0.0004692335,0.03531813,0.0002885569,0.0005445087,0.00009838024,0.04969278],"genre_scores_gemma":[0.9896472,0.000003619012,0.0004091248,0.003142104,0.006150375,0.000005153663,0.0000228153,0.00002085874,0.0005987922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3659363,"threshold_uncertainty_score":0.9760051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04182362343096035,"score_gpt":0.3563005532451752,"score_spread":0.3144769298142149,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}