{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007198732,0.0001243416,0.0001721466,0.00004095702,0.001317256,0.001722072,0.002908025,0.00004565535,0.00001290763],"category_scores_gemma":[0.0001980604,0.00004227275,0.00007270428,0.0003224034,0.0004681118,0.0003270481,0.0009109274,0.0002532133,0.000001090304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000301645,"about_ca_system_score_gemma":0.00001491465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006550974,"about_ca_topic_score_gemma":0.001612912,"domain_scores_codex":[0.9988775,0.0001499858,0.0001774433,0.0002754608,0.0003007817,0.0002188106],"domain_scores_gemma":[0.9979057,0.0005346998,0.0001472605,0.001341172,0.00003878179,0.00003235126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001306824,0.000006927526,0.002735791,0.000002320103,0.00007293487,0.000003064303,0.0006807704,0.000001968702,0.00003361268,0.9561516,0.0002650045,0.04003293],"study_design_scores_gemma":[0.001060054,0.00003719495,0.1605828,0.00001336656,0.0001506892,0.00002021842,0.00025829,0.1135164,0.0003712368,0.7194406,0.004216015,0.0003330831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08467011,0.0112454,0.7022924,0.1848416,0.0009904464,0.001825397,0.00001865908,0.0007332428,0.01338276],"genre_scores_gemma":[0.9838836,0.00003883265,0.01532788,0.0004321615,0.00004949668,0.000009886935,9.811116e-7,0.000003582451,0.0002536417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8992134,"threshold_uncertainty_score":0.9999829,"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."}}