{"id":"W2962852556","doi":"","title":"Testing APSyn against Vector Cosine on Similarity Estimation","year":2016,"lang":"en","type":"preprint","venue":"Waseda University Repository (Waseda University)","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; University of Oxford; University of Wisconsin-Madison","keywords":"Cosine similarity; Similarity (geometry); Relevance (law); Weighting; Context (archaeology); Word (group theory); Metric (unit); Computer science; Measure (data warehouse); Intersection (aeronautics); Similarity measure; Vector space model; Artificial intelligence; Trigonometric functions; Semantic similarity; Estimation; Pattern recognition (psychology); Task (project management); Mathematics; Natural language processing; Data mining; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003087685,0.0007336205,0.0006703116,0.001139908,0.001134442,0.0002732046,0.00326357,0.0007235056,0.00001071502],"category_scores_gemma":[0.0001433789,0.0008660568,0.0003932973,0.000939646,0.0002315207,0.001094355,0.002806019,0.001155723,0.00005751295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002316832,"about_ca_system_score_gemma":0.001109659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002717661,"about_ca_topic_score_gemma":0.00001895092,"domain_scores_codex":[0.9955333,0.0005350213,0.0003960328,0.001988739,0.0008135681,0.0007333555],"domain_scores_gemma":[0.9953331,0.0005192138,0.0007105865,0.002410081,0.0005288603,0.0004981231],"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":[0.002568353,0.004837517,0.01956466,0.003628805,0.002916883,0.07062094,0.004697694,0.3390669,0.05574875,0.3690108,0.01829322,0.1090455],"study_design_scores_gemma":[0.00815467,0.0009741231,0.006075491,0.005755423,0.0007275477,0.0001531491,0.0007637505,0.894594,0.02105192,0.002152754,0.05336339,0.00623375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2011276,0.00004521618,0.6757363,0.001310932,0.002747237,0.001087139,0.0001777202,0.002015182,0.1157527],"genre_scores_gemma":[0.9574667,0.00001803425,0.03468266,0.0002222978,0.0003562304,6.177995e-7,0.00006992875,0.00005066283,0.007132906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7563391,"threshold_uncertainty_score":0.999379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413957227049465,"score_gpt":0.1971345269228654,"score_spread":0.1729949546523707,"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."}}