{"id":"W4400310896","doi":"10.1016/j.erss.2024.103653","title":"Addressing machine learning bias to foster energy justice","year":2024,"lang":"en","type":"article","venue":"Energy Research & Social Science","topic":"Energy, Environment, and Transportation Policies","field":"Energy","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Building Technologies Office; Wellcome Trust; U.S. Department of Energy; Office of Energy Efficiency and Renewable Energy; National Science Foundation","keywords":"Economic Justice; Psychology; Energy (signal processing); Computer science; Artificial intelligence; Cognitive psychology; Applied psychology; Political science; Law; Mathematics; Statistics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002081821,0.0002325011,0.0002168079,0.0007352113,0.002220843,0.0006773173,0.0007650406,0.0001252758,0.0005107752],"category_scores_gemma":[0.0003687566,0.0002129146,0.0001138188,0.003162911,0.001148341,0.0005976929,0.0002625492,0.0004968055,0.0001466946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003275407,"about_ca_system_score_gemma":0.0003153032,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008864441,"about_ca_topic_score_gemma":0.003528358,"domain_scores_codex":[0.9951902,0.0003866474,0.0003299391,0.0008101162,0.002010485,0.001272618],"domain_scores_gemma":[0.9986527,0.0004074706,0.00004370475,0.0002710488,0.0001652904,0.0004597844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003048854,0.0000593005,0.0001612032,0.00004012579,0.00002978864,0.00008574362,0.004871957,0.008130883,0.03709931,0.8577079,0.002614787,0.08916859],"study_design_scores_gemma":[0.0001691844,0.0001119203,0.001531892,0.00008159428,0.00002476463,0.000005097536,0.001008849,0.004572562,0.02007114,0.004758538,0.9672955,0.0003689304],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1116735,0.004502373,0.01086335,0.01355906,0.002316455,0.0002072403,0.00005005238,0.00119508,0.8556328],"genre_scores_gemma":[0.9738381,0.0003532901,0.0002023928,0.001021641,0.0008750922,0.00007189253,0.00002723633,0.00005630742,0.02355408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646807,"threshold_uncertainty_score":0.9990782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.165999478308115,"score_gpt":0.4109796090870745,"score_spread":0.2449801307789596,"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."}}