{"id":"W4225383538","doi":"10.32473/flairs.v35i.130643","title":"Learning to Rank with BERT for Argument Quality Evaluation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Argument (complex analysis); Leverage (statistics); Ranking (information retrieval); Rank (graph theory); Computer science; Learning to rank; Pairwise comparison; Artificial intelligence; Quality (philosophy); Machine learning; Representation (politics); Task (project management); Mathematics; Epistemology; Political science; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01070053,0.000161822,0.0001929893,0.0001919284,0.0008429987,0.0004419312,0.003850947,0.00004507584,0.0001292876],"category_scores_gemma":[0.004979629,0.0001346914,0.0001800458,0.001418039,0.000178859,0.0004222614,0.002017629,0.0008378072,0.00001204803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008449698,"about_ca_system_score_gemma":0.0005887208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001424329,"about_ca_topic_score_gemma":0.000008892461,"domain_scores_codex":[0.9937664,0.00009144918,0.000474417,0.0006544385,0.004441972,0.0005712755],"domain_scores_gemma":[0.9927074,0.001428033,0.0001683558,0.0002881402,0.005266827,0.0001412031],"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":[0.0006095431,0.0004200523,0.009612994,0.0001988931,0.000314855,7.003683e-7,0.02631562,0.04691332,0.1375668,0.670898,0.006011865,0.1011373],"study_design_scores_gemma":[0.0002323584,0.001057488,0.002247653,0.0001383416,0.00001435323,0.000008590004,0.0129781,0.7026005,0.2128633,0.06035595,0.007051974,0.0004513247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6925938,0.00003934548,0.2813055,0.0203471,0.001201408,0.002986661,0.00002853369,0.0001751283,0.001322605],"genre_scores_gemma":[0.9849531,0.00001195313,0.0128946,0.00008088593,0.0001609482,0.001322938,0.000004408199,0.00001749992,0.0005536423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6556872,"threshold_uncertainty_score":0.7156082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1733581635769031,"score_gpt":0.4124483342358819,"score_spread":0.2390901706589788,"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."}}