{"id":"W6891776892","doi":"10.48448/66tx-q829","title":"UAlberta at SemEval-2024 Task 1: A Potpourri of Methods for Quantifying Multilingual Semantic Textual Relatedness and Similarity","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Semantic similarity; Task (project management); Variety (cybernetics); Similarity (geometry); Semantic computing; Semantics (computer science); Semantic memory; Point (geometry); Test (biology)","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":[0.00559325,0.002889964,0.001640941,0.004932775,0.002599746,0.005725155,0.002997185,0.003251719,0.04875744],"category_scores_gemma":[0.01785228,0.0007424983,0.001586843,0.00335959,0.00101127,0.008467213,0.006750845,0.003068091,0.04575404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001905186,"about_ca_system_score_gemma":0.002645281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01886019,"about_ca_topic_score_gemma":0.02571075,"domain_scores_codex":[0.9943694,0.002057162,0.000274894,0.001783809,0.001230982,0.0002836893],"domain_scores_gemma":[0.9923245,0.00191086,0.0003167193,0.002919908,0.001933127,0.0005948796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006697915,0.0004872925,0.004093661,0.0007060046,0.0003257169,0.0003822289,0.0005176886,0.004132692,0.005476599,0.008997915,0.4154358,0.5587746],"study_design_scores_gemma":[0.0004020724,0.0004210721,0.01227519,0.0005524536,0.0003045092,0.001290863,0.001432326,0.1919253,0.02953662,0.04483741,0.7166819,0.0003403991],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08802476,0.01117743,0.3430375,0.01142347,0.00648693,0.001514001,0.08861835,0.2030092,0.2467083],"genre_scores_gemma":[0.2596276,0.001936606,0.3485987,0.002621924,0.001138555,0.001112424,0.2306886,0.01327503,0.1410005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04875744,"threshold_uncertainty_score":0.1631098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.090822860149071,"score_gpt":0.4431904847437317,"score_spread":0.3523676245946608,"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."}}