{"id":"W6966897427","doi":"10.48448/yf9k-c629","title":"What Makes Sentences Semantically Related? A Textual Relatedness Dataset and Empirical Study","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trillium Health Centre","funders":"","keywords":"Annotation; Sentence; Intuition; Semantic similarity; Empirical research; Semantic role labeling","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":[0.002560819,0.0005878463,0.0003413954,0.003930199,0.001261051,0.0008899329,0.001114883,0.001131891,0.004562758],"category_scores_gemma":[0.01397197,0.0001788971,0.0004977795,0.003601087,0.0007728987,0.001813511,0.001743203,0.001004545,0.003699738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008799956,"about_ca_system_score_gemma":0.0008209371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005921282,"about_ca_topic_score_gemma":0.01223454,"domain_scores_codex":[0.9971154,0.001111659,0.0003327637,0.0005900266,0.0007030581,0.0001471731],"domain_scores_gemma":[0.9895604,0.005178098,0.00124562,0.001567119,0.001552385,0.0008964259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002064413,0.003322512,0.1082251,0.004249593,0.0002895782,0.001952253,0.007042475,0.004275795,0.01359619,0.01254714,0.6748978,0.1675372],"study_design_scores_gemma":[0.0009471506,0.0009351051,0.3767612,0.0006379785,0.0002192496,0.00497541,0.009494078,0.03103495,0.01199901,0.01166344,0.5510398,0.0002926053],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5774844,0.002350376,0.008024881,0.001684166,0.0002083869,0.0007840985,0.3810666,0.00198353,0.02641366],"genre_scores_gemma":[0.2253868,0.0004157676,0.0175263,0.0004562004,0.0001250905,0.000891013,0.7496943,0.0002403044,0.005264267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005921282,"threshold_uncertainty_score":0.01526397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08375234969394411,"score_gpt":0.3971551972583773,"score_spread":0.3134028475644332,"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."}}