{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001119573,0.0001461602,0.0001874468,0.0003417373,0.002282353,0.001557222,0.000791106,0.0001739118,0.01514004],"category_scores_gemma":[0.0005390117,0.0001404265,0.00006474766,0.0007778861,0.000375043,0.0002690629,0.0006014644,0.000594618,0.01356904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002565153,"about_ca_system_score_gemma":0.00002000441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008639821,"about_ca_topic_score_gemma":0.0004658109,"domain_scores_codex":[0.9978942,0.0006872995,0.0003122323,0.0003603372,0.0004613485,0.000284558],"domain_scores_gemma":[0.9991592,0.00003894715,0.0001017043,0.0003579048,0.0001903122,0.0001519591],"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":[0.000007813687,0.00007236571,0.000001032833,0.0000398278,0.00003957945,0.000005924433,0.000595428,0.000002692277,0.00001215981,0.01714779,0.9736033,0.00847205],"study_design_scores_gemma":[0.00009653605,0.000054175,0.0001247208,0.00007152205,0.0000555493,0.00001215924,0.002686492,0.00002611403,4.684276e-7,0.001342392,0.9953708,0.0001590936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0006332834,0.0007781243,0.00005271183,0.0081973,0.0002053475,0.000644152,0.7190685,0.0003928078,0.2700278],"genre_scores_gemma":[0.01783961,0.001290139,0.00003472689,0.0001090752,0.0003321341,2.092232e-7,0.978546,0.0002621113,0.001586029],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2684418,"threshold_uncertainty_score":0.9994792,"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."}}