{"id":"W2331470947","doi":"10.3758/bf03192768","title":"Word frequency effects in high-dimensional co-occurrence models: A new approach","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Word lists by frequency; Computer science; Distributional semantics; Lexical decision task; Natural language processing; Orthographic projection; Hyperspace; Space (punctuation); Semantics (computer science); Artificial intelligence; Linguistics; Semantic similarity; Cognition; Psychology","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":[0.006571629,0.00022451,0.0003395778,0.0006518125,0.0001768369,0.0002237903,0.001688922,0.0001687591,0.00002677656],"category_scores_gemma":[0.0002860095,0.0002132557,0.00008388353,0.001373055,0.0001269244,0.0006714998,0.0005721863,0.001000278,0.00004173307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002456937,"about_ca_system_score_gemma":0.0005755228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004528762,"about_ca_topic_score_gemma":0.00003931982,"domain_scores_codex":[0.9937172,0.002521263,0.0004466168,0.001049729,0.001282321,0.0009828551],"domain_scores_gemma":[0.9973173,0.0009717409,0.00006226815,0.001199318,0.0001726137,0.0002767484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001835903,0.0008564912,0.005378315,0.0000831517,0.000006819416,0.0002835119,0.0005388282,0.008016048,0.0116488,0.193157,0.002581303,0.7774314],"study_design_scores_gemma":[0.001862085,0.0001482121,0.02492579,0.0001386626,0.00001165251,0.00006253878,0.00002608271,0.6700858,0.005812534,0.2957576,0.0004144068,0.0007546355],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0785659,0.0003934283,0.9182045,0.0001632772,0.0002218143,0.0007550533,0.000005568827,0.0001301253,0.001560267],"genre_scores_gemma":[0.1136343,0.000004809711,0.8853924,0.00002547954,0.0001046883,0.0003008505,0.00001745456,0.00001476478,0.0005052157],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7766767,"threshold_uncertainty_score":0.8696316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3032750562130113,"score_gpt":0.5142418890998628,"score_spread":0.2109668328868515,"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."}}