{"id":"W2790869732","doi":"10.18653/v1/w17-3602","title":"The Good, the Bad, and the Disagreement: Complex ground truth in rhetorical structure analysis","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Rhetorical question; Annotation; Computer science; Representation (politics); Linguistics; Natural language processing; German; Epistemology; Artificial intelligence; Philosophy; Political science; Law","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03139784,0.001173836,0.001761226,0.008761682,0.006647407,0.01205527,0.003366953,0.005081809,0.0034317],"category_scores_gemma":[0.1010617,0.001169851,0.001807414,0.006787884,0.02127792,0.02864892,0.007903769,0.006602801,0.0006148296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004383622,"about_ca_system_score_gemma":0.002535526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002663769,"about_ca_topic_score_gemma":0.002233375,"domain_scores_codex":[0.9676413,0.01983397,0.00171217,0.003755863,0.005877742,0.00117894],"domain_scores_gemma":[0.9045132,0.07417348,0.006119063,0.008543074,0.00540685,0.001244354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001118932,0.00003760304,0.00213581,0.0001531,0.00004372796,0.0002384411,0.008534163,0.007203705,0.001042648,0.9513758,0.001270081,0.02785298],"study_design_scores_gemma":[0.000008380752,0.000008385013,0.0003522286,0.00006563191,0.00001749758,0.00003947618,0.0007295395,0.0295773,0.0006962161,0.9664249,0.002058118,0.00002227084],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07250638,0.0008678253,0.9079927,0.007250047,0.0001836229,0.0001035091,0.0002757947,0.0003119315,0.01050829],"genre_scores_gemma":[0.8130123,0.0002994951,0.1833192,0.0005541354,0.0002968031,0.0002433069,0.0004266538,0.0002792915,0.001568836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03139784,"threshold_uncertainty_score":0.1660496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0192288870308729,"score_gpt":0.2963445324012137,"score_spread":0.2771156453703408,"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."}}