{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002181266,0.0002493244,0.000299469,0.001702779,0.0001424065,0.001543678,0.004028257,0.0001343057,0.00008291951],"category_scores_gemma":[0.0008731652,0.0002140546,0.00005885957,0.00279248,0.0005428291,0.005327479,0.001846915,0.0003067639,0.0002258571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001063794,"about_ca_system_score_gemma":0.0005873765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009105386,"about_ca_topic_score_gemma":0.0008170257,"domain_scores_codex":[0.9967707,0.00007636797,0.0003484568,0.001161524,0.001131002,0.0005119018],"domain_scores_gemma":[0.9975769,0.0002254569,0.000331953,0.001614053,0.0001260688,0.0001255863],"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":[0.000006963988,0.0001002947,0.000008079349,0.0006638191,0.00009072827,0.00004673592,0.0001222533,0.00001926393,0.0003764331,0.1108227,0.8821917,0.005550988],"study_design_scores_gemma":[0.0004006943,0.0002735966,0.00002322415,0.000615109,0.00009640379,0.00002986281,0.0004039743,0.07213169,0.0004718414,0.001709932,0.9233702,0.000473424],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00003006608,0.002518307,0.6371201,0.003060407,0.002052969,0.002361322,0.001691787,0.0008919355,0.3502731],"genre_scores_gemma":[0.006605036,0.00106795,0.07550068,0.0001952534,0.0003508787,0.000132387,0.0007770383,0.0002812938,0.9150895],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5648164,"threshold_uncertainty_score":0.9994928,"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."}}