{"id":"W2988314392","doi":"10.22148/16.049","title":"A Shared Task for the Digital Humanities Chapter 2: Evaluating Annotation Guidelines","year":2019,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Guideline; Annotation; Task (project management); Section (typography); Computer science; Data science; Artificial intelligence; Political science; Engineering; Systems engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04692203,0.001505454,0.001767347,0.006084652,0.004477749,0.007984232,0.003374399,0.004248032,0.01162917],"category_scores_gemma":[0.1885483,0.0007979593,0.001106921,0.004650766,0.002310216,0.01145882,0.009599663,0.003629172,0.004654831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00458913,"about_ca_system_score_gemma":0.008193662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01144683,"about_ca_topic_score_gemma":0.01780963,"domain_scores_codex":[0.9087276,0.06026801,0.006812132,0.005144856,0.0174338,0.001613664],"domain_scores_gemma":[0.8523111,0.08454446,0.005347255,0.01903677,0.03456369,0.004196706],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001678711,0.0029275,0.02198892,0.005334939,0.0004857744,0.0006118375,0.02512304,0.01411222,0.01761865,0.04582936,0.1777117,0.6865774],"study_design_scores_gemma":[0.00121907,0.002410392,0.03278251,0.006029101,0.0006928158,0.000903485,0.0440766,0.1782044,0.05867124,0.1627481,0.5114981,0.0007642117],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.336787,0.004490403,0.455254,0.0152191,0.001557852,0.02218469,0.01641939,0.01601109,0.1320764],"genre_scores_gemma":[0.3657272,0.0008203166,0.5883886,0.001606955,0.0001973393,0.006673206,0.02141812,0.001743746,0.01342464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.953078,"threshold_uncertainty_score":0.2481503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018420387922206,"score_gpt":0.3715093349101505,"score_spread":0.2696672961179299,"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."}}