{"id":"W3021792233","doi":"10.1145/3440755","title":"Evolution of Semantic Similarity—A Survey","year":2021,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Semantic similarity; Similarity (geometry); Semantic computing; Field (mathematics); Natural language; Open research; Semantics (computer science); Strengths and weaknesses; Natural language understanding","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":[0.005090703,0.000132633,0.0002740105,0.00008440202,0.0001112671,0.00007678826,0.00119991,0.00007781045,0.000007742045],"category_scores_gemma":[0.002304249,0.0001469655,0.00007658312,0.0007737709,0.00003285872,0.0001746619,0.001266556,0.0001737113,0.00001833605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006395261,"about_ca_system_score_gemma":0.0002377433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001130927,"about_ca_topic_score_gemma":0.0004116536,"domain_scores_codex":[0.996581,0.001844747,0.0004176054,0.0004949885,0.000347415,0.0003142382],"domain_scores_gemma":[0.9966226,0.001190936,0.0001577552,0.001506829,0.0004562048,0.00006572491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001943894,0.000164865,0.9175183,0.00009513518,0.00005371182,0.00004883579,0.0005524496,0.01595066,0.001976343,0.01374615,0.0004859199,0.04940564],"study_design_scores_gemma":[0.0001627303,0.00001370382,0.6619964,0.00003687417,0.000002998667,0.00001395636,0.00001069901,0.3333192,0.001328113,0.002949742,0.00002669709,0.0001388372],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3489311,0.0001668901,0.6498258,0.0001486961,0.0005948613,0.00003915093,0.000002582109,0.00009729045,0.0001937128],"genre_scores_gemma":[0.9251045,0.000003044035,0.07469271,0.00005470282,0.00005938788,3.905523e-7,0.00001013477,0.000008932812,0.00006621111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5761734,"threshold_uncertainty_score":0.599308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04743587048223354,"score_gpt":0.2804255950414988,"score_spread":0.2329897245592652,"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."}}