{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002662455,0.00009536187,0.0001674023,0.0002082495,0.00009599948,0.0001261859,0.0005777723,0.0001059209,0.000002071978],"category_scores_gemma":[0.0002408353,0.00009076996,0.00002116321,0.001611563,0.00002955481,0.000351991,0.0003211064,0.0001407561,0.000001571749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112104,"about_ca_system_score_gemma":0.000139677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006248503,"about_ca_topic_score_gemma":0.000003192689,"domain_scores_codex":[0.999235,0.00004442598,0.0002260561,0.0002198827,0.0001357687,0.0001388049],"domain_scores_gemma":[0.9990776,0.00005675641,0.0001272057,0.0002954749,0.0004209252,0.00002209897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001797854,0.0003556114,0.01479755,0.002041444,0.00009946255,0.00002390435,0.005348078,0.0005198666,0.3463681,0.5596744,0.004863151,0.06589033],"study_design_scores_gemma":[0.0005041492,0.00003906162,0.0006704797,0.002204649,0.00003650264,0.00002565179,0.00009721571,0.3282265,0.6516194,0.01480791,0.001299707,0.0004687265],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04221854,0.002701828,0.9534113,0.0001082629,0.0003148933,0.0001424596,0.000001089115,0.0004438285,0.0006578207],"genre_scores_gemma":[0.8670645,0.000003462162,0.1326599,0.00005432051,0.00002749038,0.000001543959,0.000001658057,0.000006761282,0.0001804066],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.824846,"threshold_uncertainty_score":0.3701491,"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."}}