{"id":"W4366197471","doi":"10.48550/arxiv.2304.06879","title":"Performative Prediction with Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Lipschitz continuity; Resampling; Convexity; Computer science; Artificial neural network; Performative utterance; Minification; Focus (optics); Mathematics; Applied mathematics; Mathematical optimization; Artificial intelligence; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004852524,0.00148373,0.0009843024,0.001364257,0.000773088,0.001763743,0.001699251,0.001673251,0.001899471],"category_scores_gemma":[0.01680265,0.0007093151,0.0009330742,0.001056229,0.002743479,0.003207362,0.002464647,0.00259368,0.0005010947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002189835,"about_ca_system_score_gemma":0.001024493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004341784,"about_ca_topic_score_gemma":0.003853478,"domain_scores_codex":[0.997285,0.001188106,0.000119953,0.0006344199,0.0006018769,0.000170571],"domain_scores_gemma":[0.993008,0.004486431,0.0009360781,0.0008162127,0.0005947482,0.0001584866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001305891,0.00005589499,0.002179953,0.00008112688,0.0001251755,0.0000993845,0.0002118378,0.8343181,0.001452334,0.09556194,0.001379929,0.06440368],"study_design_scores_gemma":[0.000003752339,0.00001285939,0.000178352,0.000009358583,0.000006220757,0.000006800073,0.000007019263,0.9254881,0.0004272319,0.07355946,0.0002930552,0.000007822679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02038054,0.0003379394,0.9754614,0.0005843136,0.00004039125,0.00003935691,0.00007639736,0.0004581652,0.002621406],"genre_scores_gemma":[0.8072045,0.0005060751,0.1860623,0.0003260432,0.0001797116,0.0002168058,0.0003202513,0.0001645384,0.005019651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004852524,"threshold_uncertainty_score":0.0256629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024308090817286,"score_gpt":0.1902680918126301,"score_spread":0.08783728273090152,"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."}}