{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02858884,0.002088263,0.00400763,0.005691034,0.001937159,0.007278269,0.005906907,0.003628356,0.004900067],"category_scores_gemma":[0.08261272,0.00187556,0.004876787,0.007410039,0.003702341,0.008226249,0.00439703,0.006466056,0.001054623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001528297,"about_ca_system_score_gemma":0.002231833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005456197,"about_ca_topic_score_gemma":0.005827234,"domain_scores_codex":[0.9770791,0.01650332,0.001107642,0.003229394,0.001670552,0.0004099393],"domain_scores_gemma":[0.8061897,0.179346,0.002643723,0.008640738,0.002298601,0.0008812522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001260714,0.001760008,0.03452776,0.001138582,0.004927941,0.0008167482,0.006555538,0.1699386,0.005173997,0.4731537,0.004232461,0.2965142],"study_design_scores_gemma":[0.0001341914,0.0002371605,0.004656499,0.00009429385,0.0009220165,0.0002559155,0.000444775,0.7505878,0.0006427091,0.2386599,0.003226627,0.0001380534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01441403,0.0005556943,0.9834929,0.0003876173,0.00005927473,0.00007674738,0.0001745015,0.0002250293,0.0006143037],"genre_scores_gemma":[0.4429207,0.00177089,0.5478525,0.0004375433,0.0008462793,0.001374936,0.0008602508,0.0004003486,0.003536664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02858884,"threshold_uncertainty_score":0.151194,"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."}}