{"id":"W6931940799","doi":"10.5683/sp2/h4bhlt","title":"Replication Data for: Empirically Evaluating the Semantic Qualities of Language Vocabularies","year":2021,"lang":"en","type":"dataset","venue":"Borealis","topic":"Quality and Supply Management","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina; University of Toronto; York University","funders":"","keywords":"Replication (statistics); Semantics (computer science); Vocabulary; Semantic data model; Natural language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005276694,0.001300412,0.0008658399,0.002368768,0.001339749,0.001706312,0.002944811,0.002079409,0.01586351],"category_scores_gemma":[0.02375235,0.0004917171,0.00148592,0.003766088,0.001012069,0.002202542,0.002770826,0.002323317,0.01813742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001705454,"about_ca_system_score_gemma":0.002435766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04414738,"about_ca_topic_score_gemma":0.06682122,"domain_scores_codex":[0.9956651,0.001292765,0.0004061567,0.0008859374,0.001378938,0.0003710608],"domain_scores_gemma":[0.9865065,0.004078761,0.0008849064,0.004749689,0.003242457,0.0005376376],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0009685159,0.0004407878,0.008168551,0.001133203,0.0001690125,0.0001365703,0.0005095633,0.002740668,0.001328514,0.004296022,0.9646579,0.01545066],"study_design_scores_gemma":[0.002736325,0.000334911,0.04724227,0.0004895916,0.0001916002,0.0005555898,0.002479431,0.01608913,0.005576332,0.006643644,0.9174528,0.0002085166],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01776127,0.0001908252,0.001230146,0.0007254233,0.0001075787,0.000185579,0.9739161,0.001882542,0.004000546],"genre_scores_gemma":[0.01050051,0.00004091987,0.002611723,0.000133901,0.00001576317,0.0003301579,0.9845437,0.0001667167,0.001656576],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9947233,"threshold_uncertainty_score":0.08778083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1284139831006391,"score_gpt":0.3833308250037853,"score_spread":0.2549168419031462,"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."}}