{"id":"W2250389127","doi":"","title":"Identifying Sources of Inter-Annotator Variation: Evaluating Two Models of Argument Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Variation (astronomy); Argument (complex analysis); Computer science; Rhetorical question; Domain (mathematical analysis); Natural language processing; Data science; Artificial intelligence; Management science; Linguistics; Mathematics; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005992195,0.0001149739,0.000390335,0.0003261991,0.0001319093,0.00008227785,0.0001948765,0.00001719037,0.008113651],"category_scores_gemma":[0.00006129722,0.00008825938,0.0002918092,0.0001518229,0.0002087232,0.0002697161,0.0001058003,0.00008647966,0.00000748717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008215477,"about_ca_system_score_gemma":0.00001722509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001588989,"about_ca_topic_score_gemma":0.007026488,"domain_scores_codex":[0.9987701,0.00004623718,0.0005177041,0.000184284,0.0003520082,0.0001296447],"domain_scores_gemma":[0.9988363,0.00009393705,0.0003642,0.000303371,0.0003777694,0.00002442522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001349373,0.0002163468,0.002869854,0.00006997554,0.007160147,0.000001521971,0.2218506,0.005090611,0.003550713,0.7542672,0.0001514881,0.004757994],"study_design_scores_gemma":[0.002130838,0.0003629134,0.003060866,0.0002016811,0.02623464,0.00000208138,0.3600491,0.5003985,0.01826975,0.08692139,0.00103276,0.001335543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8892066,0.0001429702,0.01004871,0.00007694118,0.0002397912,0.00008649901,0.00001804643,0.00002815312,0.1001523],"genre_scores_gemma":[0.9937894,0.000003717881,0.002724936,0.00002852004,0.0001856556,0.00001025884,0.000007345539,0.000008340318,0.003241828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6673458,"threshold_uncertainty_score":0.9927931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06126207947042338,"score_gpt":0.3448110371695646,"score_spread":0.2835489576991412,"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."}}