{"id":"W2806372986","doi":"10.1609/aaai.v32i1.11353","title":"Building More Explainable Artificial Intelligence With Argumentation","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Research Foundation","keywords":"Argumentation theory; Artificial intelligence; Black box; Computer science; Order (exchange); Data science; Management science; Epistemology; Engineering; Philosophy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001258171,0.000648593,0.0005695422,0.0004793571,0.0009819557,0.0009464029,0.004399784,0.0002198048,0.0002304902],"category_scores_gemma":[0.0006545499,0.0004969788,0.0002094829,0.002852066,0.001539699,0.001959248,0.0008136844,0.0006265243,0.0004472836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002275509,"about_ca_system_score_gemma":0.0003044782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002095782,"about_ca_topic_score_gemma":0.00007232613,"domain_scores_codex":[0.9945506,0.00006187656,0.001365419,0.001417046,0.001433006,0.001172011],"domain_scores_gemma":[0.995389,0.0002437904,0.0009409674,0.0009781204,0.002211656,0.0002365056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001949768,0.0002554425,0.00006705917,0.00004858022,0.00003172478,0.000003339394,0.003192188,0.0002469138,0.07466657,0.8231274,0.00007474635,0.09809104],"study_design_scores_gemma":[0.00001459112,0.0006523155,0.00003748903,0.0003185234,0.00002066317,0.00001702903,0.002847396,0.05874887,0.6422604,0.2944962,0.0001655631,0.0004209362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2763785,0.00004853748,0.6973296,0.008403928,0.001345698,0.001661925,0.00001016752,0.0005173464,0.01430426],"genre_scores_gemma":[0.9632074,0.00002546927,0.03552154,0.0005305604,0.0002789693,0.0001181918,0.00000107732,0.00004973976,0.0002670144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6868289,"threshold_uncertainty_score":0.9997482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07023473309506409,"score_gpt":0.3177145133934403,"score_spread":0.2474797802983762,"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."}}