{"id":"W4283802141","doi":"10.1609/aaai.v36i9.21219","title":"Planning to Avoid Side Effects","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Computer science; Side effect (computer science); Context (archaeology); Agency (philosophy); Risk analysis (engineering); Lead (geology); Relation (database); Management science; Business; Engineering; Epistemology; Data mining","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":[0.0006833955,0.0002267634,0.0002701383,0.0001773558,0.0005987402,0.0002329525,0.00311924,0.00004670087,0.0000565644],"category_scores_gemma":[0.0006451838,0.000179215,0.0001278661,0.001011414,0.0001032444,0.0002529581,0.001569106,0.0004418939,0.0001569505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009417702,"about_ca_system_score_gemma":0.0001185166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002873482,"about_ca_topic_score_gemma":0.000003361897,"domain_scores_codex":[0.9979076,0.00003997348,0.0003916665,0.0005817323,0.0006266989,0.000452331],"domain_scores_gemma":[0.998745,0.0001933885,0.0002596101,0.0003446438,0.0003125078,0.0001448366],"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":[0.00004954798,0.000144568,0.0002673134,0.00004358568,0.00001243671,0.000003050945,0.005638419,0.0004174586,0.04578751,0.9047647,0.0007283454,0.04214305],"study_design_scores_gemma":[0.00004837507,0.0008663458,0.0005646265,0.0002219978,0.00001439173,0.0000205294,0.001232935,0.03464479,0.738449,0.2218897,0.001578184,0.0004691084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6317731,0.0002298001,0.1227409,0.01077383,0.004643054,0.002317399,0.00001133775,0.0007015337,0.2268091],"genre_scores_gemma":[0.9963027,0.000003500033,0.002086682,0.0007075074,0.00008476611,0.0001070431,2.741948e-7,0.00001311118,0.0006944222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6926615,"threshold_uncertainty_score":0.7308175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0592639208155509,"score_gpt":0.2916186804392807,"score_spread":0.2323547596237298,"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."}}