{"id":"W4414087786","doi":"10.7152/nasko.v7i1.95650","title":"Cosine Similarity Indexing of Word Embeddings Using Knowledge Organization Systems","year":2025,"lang":"en","type":"article","venue":"NASKO","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Search engine indexing; Vector space model; Cosine similarity; Word (group theory); Similarity (geometry); Latent semantic analysis; Knowledge organization; Context (archaeology); Probabilistic latent semantic analysis","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":[0.002109689,0.0007105735,0.001397379,0.008495568,0.0009829337,0.00347695,0.001477805,0.0009764178,0.002887833],"category_scores_gemma":[0.01501863,0.0003870713,0.001194547,0.01114233,0.001195433,0.00777178,0.00277688,0.001328937,0.001338219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001389854,"about_ca_system_score_gemma":0.001298782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003233017,"about_ca_topic_score_gemma":0.002713016,"domain_scores_codex":[0.9960246,0.001008417,0.0006551981,0.0008940251,0.001227711,0.0001900588],"domain_scores_gemma":[0.9956909,0.001737265,0.000600645,0.001035957,0.0007806822,0.0001546141],"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":[0.0004336037,0.00034925,0.005480519,0.0008025421,0.0002518374,0.0002240304,0.001253875,0.03084445,0.01087338,0.162407,0.01052087,0.7765588],"study_design_scores_gemma":[0.0001041436,0.0003483895,0.005144353,0.000173436,0.0001139952,0.0005177284,0.0009145109,0.622859,0.01040289,0.3300644,0.02919058,0.0001665973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04368873,0.001856302,0.946301,0.0003828095,0.0002579382,0.0002433058,0.001442674,0.001413873,0.004413398],"genre_scores_gemma":[0.3628636,0.001152567,0.6268894,0.0001426325,0.0003158479,0.0004851051,0.004729609,0.0002781384,0.003143174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008495568,"threshold_uncertainty_score":0.01115727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411926126935073,"score_gpt":0.3039590310573438,"score_spread":0.2898397697879931,"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."}}