{"id":"W3175333484","doi":"10.1609/aaai.v35i13.17368","title":"Agent Incentives: A Causal Perspective","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Soundness; Incentive; Completeness (order theory); Perspective (graphical); Computer science; Value (mathematics); Influence diagram; Control (management); Risk analysis (engineering); Microeconomics; Artificial intelligence; Economics; Machine learning; Mathematics; Business","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":[0.00008272292,0.00007845172,0.00008485124,0.00002781899,0.00007067378,0.0001489446,0.0003108488,0.00003168713,0.0001036476],"category_scores_gemma":[0.00003783769,0.00007037999,0.00004527273,0.0002719935,0.00002387198,0.0002281839,0.0002234387,0.0001009401,0.0001876779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006164387,"about_ca_system_score_gemma":0.0001838846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006348008,"about_ca_topic_score_gemma":0.00002153924,"domain_scores_codex":[0.999164,0.00005002961,0.00009543855,0.0003456827,0.0001601121,0.0001847786],"domain_scores_gemma":[0.9992857,0.00002746112,0.00001978213,0.000342537,0.0002407233,0.00008378159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[7.681964e-7,0.00005469789,0.00006884863,0.000001673799,0.00001222022,0.00004417752,0.001162924,0.00002883624,0.0009113461,0.991344,0.001426127,0.004944403],"study_design_scores_gemma":[0.001172052,0.0002466631,0.006612895,0.0001002492,0.00002652707,0.0003036359,0.006294167,0.3934397,0.05390508,0.5200762,0.01648042,0.001342444],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002917747,0.0002216119,0.9314038,0.002191197,0.000277711,0.00002703724,6.129716e-7,0.0001596287,0.06280062],"genre_scores_gemma":[0.9291146,0.00002975942,0.06646275,0.001020631,0.0000633411,0.00000478221,7.737057e-7,0.000003887311,0.003299494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9261968,"threshold_uncertainty_score":0.2870013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275690468075568,"score_gpt":0.2808606940945524,"score_spread":0.2532916472869956,"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."}}