{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007266994,0.001252558,0.0007999605,0.002164484,0.001414266,0.004536455,0.002643357,0.003135605,0.006958624],"category_scores_gemma":[0.02183339,0.0008455197,0.002915394,0.00100995,0.005008283,0.01058657,0.00859774,0.005265146,0.0009298305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001766791,"about_ca_system_score_gemma":0.001718342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001331705,"about_ca_topic_score_gemma":0.002708223,"domain_scores_codex":[0.9940568,0.003766442,0.0002928278,0.0006516068,0.001024772,0.0002075288],"domain_scores_gemma":[0.9868401,0.008460272,0.0007465333,0.002783418,0.0008521013,0.0003175785],"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":[0.00002046965,0.00008297518,0.0006054385,0.0002641726,0.0001242096,0.0002769323,0.001826125,0.02444956,0.0009702748,0.9389105,0.002665722,0.02980358],"study_design_scores_gemma":[0.00003021282,0.00002181342,0.0001796974,0.0001369876,0.00004171736,0.00007976866,0.0003062026,0.06202248,0.0006926678,0.9124502,0.02401078,0.00002751507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01418707,0.000812306,0.9555358,0.008345047,0.0001889006,0.0002256157,0.0001925031,0.0008276142,0.01968513],"genre_scores_gemma":[0.2146238,0.0008662916,0.7779268,0.001174982,0.0001835231,0.0003894284,0.0006406356,0.0002340981,0.003960523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007266994,"threshold_uncertainty_score":0.038432,"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."}}