{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003547023,0.0002482302,0.0004323309,0.0001360956,0.0002500699,0.0004457868,0.001734056,0.0001375555,0.0001566498],"category_scores_gemma":[0.004015204,0.000188026,0.0001251129,0.00026316,0.000127491,0.0004386163,0.00132609,0.000176215,0.00001103448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002073493,"about_ca_system_score_gemma":0.00008606239,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06221561,"about_ca_topic_score_gemma":0.02715576,"domain_scores_codex":[0.9977202,0.00009323161,0.000673228,0.0006433051,0.0006118124,0.0002582112],"domain_scores_gemma":[0.9936679,0.0004526991,0.0006901327,0.004884056,0.0002969892,0.000008223512],"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":[0.00003012852,0.00005959862,0.00001130529,0.002263496,0.0001312815,0.000003262018,0.0001149141,0.00001162915,0.000005744626,0.003539676,0.9917671,0.002061837],"study_design_scores_gemma":[0.0002046041,0.00001565866,0.0001342574,0.0001671849,0.0005452176,6.898958e-7,0.002104099,0.001438423,0.000004129215,0.001429613,0.9937278,0.0002283183],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007744757,0.0004765241,0.0005093181,0.005039801,0.0001829364,0.0007063643,0.9925333,0.00004137386,0.0004329622],"genre_scores_gemma":[0.00007836027,0.00006755671,0.0002170793,0.00291157,0.001167192,0.0001190218,0.9951318,0.00002482242,0.0002826128],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03505985,"threshold_uncertainty_score":0.9905961,"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."}}