{"id":"W4393676644","doi":"10.5281/zenodo.10463346","title":"Grammatical functions, inflectional class and textual frequency in Russian nominals","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Discourse Analysis and Cultural Communication","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Economic and Social Research Council","keywords":"Linguistics; Class (philosophy); Natural language processing; Computer science; Artificial intelligence; Mathematics; Philosophy","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":[0.0009972963,0.0007044257,0.0008151628,0.004345479,0.0006610054,0.001408441,0.0007821553,0.0008600303,0.01380519],"category_scores_gemma":[0.004663325,0.0003610928,0.000647885,0.004688713,0.0004511122,0.000738285,0.001325441,0.0008189529,0.01854895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008035853,"about_ca_system_score_gemma":0.0007209304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009166231,"about_ca_topic_score_gemma":0.01041871,"domain_scores_codex":[0.9988802,0.0003105065,0.0001925515,0.0002880899,0.000213949,0.0001146868],"domain_scores_gemma":[0.99751,0.0009947689,0.0003931267,0.0005338005,0.000445677,0.0001226935],"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":[0.001131346,0.0004990089,0.08427086,0.00462058,0.0003165073,0.0007223318,0.004628078,0.003951504,0.004847904,0.007438136,0.8207561,0.06681754],"study_design_scores_gemma":[0.0001891516,0.0001454828,0.298113,0.0007086458,0.0001073077,0.0006939103,0.00293319,0.002289498,0.002470507,0.002184198,0.6900545,0.0001107735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03940145,0.0002445111,0.0003075517,0.00008985156,0.00003550706,0.00002918397,0.957249,0.0002043547,0.002438518],"genre_scores_gemma":[0.01568903,0.00009955581,0.0006697238,0.00001392871,0.000009709192,0.0001414506,0.9818403,0.0000583627,0.001477915],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01380519,"threshold_uncertainty_score":0.04618293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04329444214906199,"score_gpt":0.3171631349385529,"score_spread":0.2738686927894909,"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."}}