{"id":"W4387344795","doi":"10.1145/3610206","title":"Selective Explanations: Leveraging Human Input to Align Explainable AI","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Universitas Brawijaya; National Science Foundation","keywords":"Task (project management); Computer science; Space (punctuation); Perception; Artificial intelligence; Property (philosophy); Ask price; Machine learning; Data science; Psychology; Epistemology; Management","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":[0.0007410359,0.0003088559,0.0003030673,0.0009010208,0.0008769627,0.0005903839,0.003858783,0.00009459078,0.00001868324],"category_scores_gemma":[0.0004135631,0.0002747402,0.0001719258,0.00205076,0.000050714,0.002148109,0.001981223,0.0004422259,0.0003246274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003824608,"about_ca_system_score_gemma":0.00003473028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001876564,"about_ca_topic_score_gemma":0.00002231672,"domain_scores_codex":[0.9973205,0.00003874787,0.0006093498,0.0008082468,0.0006540682,0.0005690298],"domain_scores_gemma":[0.9976461,0.0001979591,0.000380404,0.00087076,0.0007881636,0.0001166061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001009377,0.0006450389,0.002528667,0.0002783943,0.0002483563,0.00001484414,0.04061325,0.01316627,0.332945,0.298465,0.2825172,0.028477],"study_design_scores_gemma":[0.0002847744,0.000718366,0.004122139,0.000595391,0.00001915096,0.00002804264,0.001649648,0.03483916,0.8200338,0.1304704,0.006605526,0.0006335196],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9520858,0.000006449266,0.02811209,0.01033392,0.001902397,0.001091801,0.000002669223,0.0009754936,0.005489381],"genre_scores_gemma":[0.9906024,0.000002682652,0.006146828,0.001655092,0.0003883984,0.0001596288,0.000003580633,0.00003567406,0.001005701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4870888,"threshold_uncertainty_score":0.9999705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08774926588927132,"score_gpt":0.3596719010079191,"score_spread":0.2719226351186478,"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."}}