{"id":"W6929162368","doi":"10.4224/40001819","title":"The Nunavut Hansard Inuktitut–English Parallel Corpus 3.0","year":2020,"lang":"en","type":"dataset","venue":"NRC Digital Repository","topic":"Nuclear Receptors and Signaling","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Scripting language; Preprocessor; Indigenous; Sentence; Arctic; Indigenous language; Baseline (sea)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001107553,0.0004368738,0.0003974649,0.0000561169,0.0006807147,0.002353186,0.001373563,0.0002932471,0.00003880868],"category_scores_gemma":[0.002215426,0.0003233109,0.0003037842,0.0002176036,0.0003964859,0.0004482931,0.000442955,0.0008873307,0.001163151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000166509,"about_ca_system_score_gemma":0.0002661145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003318096,"about_ca_topic_score_gemma":0.00001374214,"domain_scores_codex":[0.9968397,0.0001061945,0.0005356733,0.0008322821,0.001177732,0.000508397],"domain_scores_gemma":[0.9979822,0.0004363344,0.0003496099,0.0008187538,0.0001341474,0.0002789339],"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":[0.00006258315,0.00005358881,0.000005973411,0.00003786647,0.0000176679,0.0002656425,0.00004447,0.000007026958,0.0008334133,0.00009443548,0.9957106,0.002866756],"study_design_scores_gemma":[0.0001701027,0.0001226289,0.000003537032,0.0000676632,0.00002654437,0.00005930091,0.0000345335,0.0000133758,0.002342803,0.00009866596,0.9966721,0.0003887461],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000277593,0.0003055118,0.000008505118,0.00007985242,0.008590985,0.000457467,0.9521109,0.0002822836,0.03788688],"genre_scores_gemma":[0.0215102,0.001818767,0.00005307835,0.004453524,0.01259261,0.0002411624,0.9016083,0.0004927048,0.05722962],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0505026,"threshold_uncertainty_score":0.9999219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01749576237301338,"score_gpt":0.2236101758155757,"score_spread":0.2061144134425623,"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."}}