{"id":"W3209416046","doi":"10.1080/15434303.2021.1992629","title":"The Relationship between Word Difficulty and Frequency: A Response to Hashimoto (2021)","year":2021,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Word lists by frequency; Correlation; Vocabulary; Rank (graph theory); Word (group theory); Linguistics; Psychology; Range (aeronautics); Mathematics; Statistics; Sentence; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008984907,0.0001938085,0.0001912975,0.00009390563,0.0004288843,0.0009590951,0.0007568303,0.00009353749,0.00001103087],"category_scores_gemma":[0.0004595777,0.0001418333,0.00005721494,0.0006811222,0.00004796463,0.0004620012,0.0001692929,0.0003622269,0.00002167767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001068833,"about_ca_system_score_gemma":0.00019927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005300479,"about_ca_topic_score_gemma":0.0001576293,"domain_scores_codex":[0.9979206,0.0004893631,0.0002960157,0.000521683,0.0004005971,0.0003717886],"domain_scores_gemma":[0.9969036,0.001762222,0.0001013076,0.0009453963,0.0001204722,0.0001670124],"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":[0.00006691663,0.0001317575,0.07032432,0.00006162352,0.0000910083,0.001077234,0.03220738,5.620614e-7,0.0735165,0.1457214,0.00256396,0.6742374],"study_design_scores_gemma":[0.0009096138,0.000871026,0.8794996,0.0002803844,0.0000504389,0.0001215748,0.004729796,0.0002866516,0.005626216,0.1043072,0.002288206,0.001029369],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6749615,0.002377786,0.3044482,0.0169088,0.0001730063,0.0003476464,0.00001356968,0.0004709179,0.0002985394],"genre_scores_gemma":[0.7433425,0.000001633015,0.255436,0.0002475899,0.00008125598,0.0000525474,0.000009437008,0.00001205259,0.0008169753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8091753,"threshold_uncertainty_score":0.9248577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01621099591469831,"score_gpt":0.3205802786497973,"score_spread":0.304369282735099,"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."}}