{"id":"W4409361388","doi":"10.1609/aaai.v39i26.34944","title":"Joint Scoring Rules: Competition Between Agents Avoids Performative Prediction","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Performative utterance; Joint (building); Competition (biology); Computer science; Artificial intelligence; Epistemology; Engineering; Philosophy; Structural engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0106483,0.001440135,0.001971206,0.0005947531,0.001167271,0.002573037,0.003701452,0.001957353,0.004384713],"category_scores_gemma":[0.0310204,0.0007301192,0.0006516442,0.0006436752,0.002957524,0.003647744,0.003879498,0.002778601,0.001157642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001071759,"about_ca_system_score_gemma":0.002253889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002037501,"about_ca_topic_score_gemma":0.002296171,"domain_scores_codex":[0.9900643,0.004663251,0.0004986718,0.001745773,0.002016519,0.001011412],"domain_scores_gemma":[0.9795068,0.01020795,0.002168537,0.004718424,0.001847578,0.00155068],"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":[0.001001095,0.000782724,0.007447303,0.0002468982,0.0002818841,0.0004698329,0.0008081296,0.5452967,0.01099114,0.2551211,0.004594916,0.1729582],"study_design_scores_gemma":[0.00009380344,0.0001786868,0.0004869075,0.00001598301,0.00003287185,0.00007052613,0.00003696375,0.9049538,0.00207877,0.09117959,0.0008424303,0.0000295969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1832486,0.0001390113,0.7989988,0.000941415,0.00007696641,0.0002612114,0.0001005388,0.000743578,0.01548995],"genre_scores_gemma":[0.9413502,0.00003318724,0.05519649,0.0001915079,0.00002950187,0.0001904047,0.0000701296,0.00006417626,0.002874298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0106483,"threshold_uncertainty_score":0.05631423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.107909667531006,"score_gpt":0.3036342043271588,"score_spread":0.1957245367961528,"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."}}