{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1424769,0.0007749895,0.001527625,0.006226625,0.007245899,0.01883832,0.005607451,0.003746157,0.004833156],"category_scores_gemma":[0.2657806,0.002773871,0.0008714504,0.008291971,0.01968694,0.02232692,0.01001626,0.006166048,0.002256318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003694492,"about_ca_system_score_gemma":0.008129702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004078977,"about_ca_topic_score_gemma":0.006792077,"domain_scores_codex":[0.8779132,0.09782631,0.008085106,0.004842373,0.0104742,0.0008588038],"domain_scores_gemma":[0.7205215,0.1914423,0.008603383,0.05334356,0.0243972,0.001692183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004083286,0.0002453792,0.005731666,0.002350746,0.0000800476,0.0006332102,0.06400127,0.005722499,0.01587197,0.5085958,0.01532016,0.381039],"study_design_scores_gemma":[0.000596511,0.0007827025,0.007143629,0.001933155,0.0001747599,0.002877348,0.02534108,0.02741145,0.03206617,0.3962261,0.5050213,0.0004257999],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01520326,0.001512359,0.9586127,0.009624737,0.0004598721,0.002208022,0.0003391136,0.0008035945,0.01123626],"genre_scores_gemma":[0.04640578,0.0005394591,0.94315,0.001038638,0.0002585664,0.004676658,0.0003814242,0.0006714234,0.002878077],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1424769,"threshold_uncertainty_score":0.7534989,"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."}}