{"id":"W4393789404","doi":"10.5281/zenodo.1456564","title":"Corpus Of Occitan Written Traditional Folktales Annotated With Part-Of-Speech (Owt-Tag)","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Medieval European Literature and History","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"European Commission","keywords":"Natural language processing; Linguistics; Computer science; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000463588,0.0002824029,0.0004044289,0.0004200547,0.001150475,0.0003804209,0.001060438,0.0001010651,0.05296944],"category_scores_gemma":[0.0001927546,0.0002503527,0.0001014415,0.0001776176,0.001313132,0.0002138748,0.0003138924,0.0004303021,0.002161325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007551643,"about_ca_system_score_gemma":0.00001788558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004667569,"about_ca_topic_score_gemma":0.00001187757,"domain_scores_codex":[0.9977044,0.0003342651,0.0005243691,0.0004481981,0.000676107,0.0003126649],"domain_scores_gemma":[0.9973118,0.00004333978,0.0004917954,0.0006217808,0.001373594,0.0001576892],"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":[0.0002097735,0.0001936444,9.885014e-8,0.0003861373,0.000148226,0.00004458644,0.002145707,5.542675e-7,0.0000647061,0.004907209,0.9899822,0.001917123],"study_design_scores_gemma":[0.0004707902,0.001085217,0.000009317049,0.0002988422,0.00009688034,0.00006862365,0.0002440538,0.00000281639,0.00004272957,0.00006467359,0.9973419,0.0002741745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0004530555,0.0003112139,0.000007229783,0.00006880539,0.0003799552,0.0003400237,0.9075593,0.0001626091,0.09071775],"genre_scores_gemma":[0.0009459139,0.0001586717,0.00004325598,0.0001100256,0.001346683,6.870556e-8,0.992457,0.00080239,0.00413595],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0865818,"threshold_uncertainty_score":0.9999949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05822606488989326,"score_gpt":0.2203912336234934,"score_spread":0.1621651687336001,"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."}}