{"id":"W6948167585","doi":"10.48448/1myw-6p66","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trillium Health Centre","funders":"","keywords":"Annotation; Sentence; Semantic similarity; Baseline (sea); Semantics (computer science); Data collection; Semantic annotation","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":[0.003905545,0.001651602,0.0007797086,0.007613204,0.002287839,0.001432266,0.002617459,0.002497826,0.007814495],"category_scores_gemma":[0.01766965,0.0004717516,0.001388976,0.007938546,0.001207057,0.003514348,0.003813401,0.001766716,0.008499621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001685145,"about_ca_system_score_gemma":0.003093023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009768744,"about_ca_topic_score_gemma":0.02191306,"domain_scores_codex":[0.9948817,0.001692097,0.0009064302,0.001067891,0.001218465,0.0002333751],"domain_scores_gemma":[0.9889404,0.004017023,0.001287654,0.002318759,0.002473714,0.0009624608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001464035,0.001003699,0.02187552,0.007649254,0.000365257,0.001460228,0.004267087,0.005204316,0.01953417,0.01114199,0.7845318,0.1415026],"study_design_scores_gemma":[0.0005072004,0.0004700447,0.06890884,0.0005902613,0.0001731426,0.001859692,0.004500209,0.01322848,0.01328707,0.01450823,0.8816093,0.0003575535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05059405,0.001373915,0.02044697,0.001602956,0.0003228202,0.001130671,0.9002063,0.008992452,0.01532976],"genre_scores_gemma":[0.01890337,0.0002159167,0.02332481,0.0002692347,0.00004937265,0.001167702,0.9537553,0.0003351033,0.001979108],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.009768744,"threshold_uncertainty_score":0.02614212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05405948883185546,"score_gpt":0.3866247607337149,"score_spread":0.3325652719018595,"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."}}