{"id":"W2268973493","doi":"","title":"Principles and Practicalities of Corpus Design in Language Retrieval: Issues in the Digitization of the Beynon Corpus of Early Twentieth-Century Sm’algyax Materials","year":2010,"lang":"en","type":"article","venue":"ScholarSpace (University of Hawaii at Manoa)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Council for Canadian Studies","keywords":"Digitization; Computer science; Linguistics; Function (biology); Natural language processing; Corpus linguistics; Artificial intelligence; Ethnography; Sociology; Anthropology; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001210079,0.000107246,0.0002613635,0.0001814068,0.00007099431,0.00004934606,0.0009514476,0.0001280591,0.00000853771],"category_scores_gemma":[0.0003486279,0.00008615736,0.00004194277,0.0005115879,0.0003351831,0.000913693,0.0005521251,0.0002674185,3.777691e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002880631,"about_ca_system_score_gemma":0.00006389181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007689356,"about_ca_topic_score_gemma":0.0003411114,"domain_scores_codex":[0.998704,0.0003593579,0.0001932193,0.0002091893,0.0003901471,0.0001440631],"domain_scores_gemma":[0.998569,0.0002335133,0.0005197528,0.0004967918,0.0001578128,0.00002311031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003117402,0.0001718687,0.02913001,0.0003724495,0.00002428036,0.00003225938,0.0253511,0.000006945293,0.8474245,0.09513252,0.00006019056,0.001982139],"study_design_scores_gemma":[0.0009877736,0.0002835236,0.1401075,0.0005146595,0.00004406617,0.00002834727,0.006567702,0.0001704093,0.8461176,0.004122077,0.0007847178,0.000271613],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949075,0.000989304,0.002280907,0.001195094,0.00009560958,0.0003389736,0.00001551199,0.00002982755,0.0001472552],"genre_scores_gemma":[0.9594882,0.0001848296,0.04008423,0.00001416164,0.000005229531,2.911107e-7,0.000002119999,0.000005953387,0.0002150479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1109775,"threshold_uncertainty_score":0.3513395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01462096669406423,"score_gpt":0.2426616553417466,"score_spread":0.2280406886476824,"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."}}