{"id":"W4416814142","doi":"10.1016/j.chaos.2025.117598","title":"Self-confirming Q-learning on unknown networks","year":2025,"lang":"en","type":"article","venue":"Chaos Solitons & Fractals","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Wuhan University; National Social Science Fund of China; National Natural Science Foundation of China","keywords":"Convergence (economics); Consistency (knowledge bases); Function (biology); Process (computing); Complete information; Social network (sociolinguistics)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002144752,0.0002045481,0.0003387045,0.0003017034,0.0006498818,0.0002996052,0.0008476573,0.0001615045,0.0005908823],"category_scores_gemma":[0.001581868,0.0001669565,0.0001720696,0.001162879,0.0001194144,0.0001887283,0.0001837381,0.0005162447,0.001360712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005097142,"about_ca_system_score_gemma":0.00008944715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007488375,"about_ca_topic_score_gemma":0.000005261327,"domain_scores_codex":[0.9975742,0.000314223,0.0005877067,0.0006035992,0.0004845588,0.0004357735],"domain_scores_gemma":[0.9951646,0.003414218,0.000228032,0.0008650972,0.0001877841,0.0001402233],"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":[0.00007181636,0.0004625076,0.004023546,0.00001502533,0.000111303,0.00001546582,0.001658763,0.01262326,0.001431467,0.7456627,0.0165377,0.2173865],"study_design_scores_gemma":[0.0003022617,0.00005776427,0.002926853,0.00006823292,0.00003223005,0.00000509939,0.001128081,0.0284529,0.00194581,0.08125134,0.8835527,0.0002766867],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5132102,0.0004794289,0.04512167,0.005197499,0.001236137,0.0007029281,0.000008803542,0.0006156564,0.4334277],"genre_scores_gemma":[0.9815196,0.0000244566,0.0003195434,0.001032363,0.0002523693,0.00007312632,0.000005783654,0.00001446669,0.01675826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8670151,"threshold_uncertainty_score":0.9994168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04368944352331026,"score_gpt":0.391468734442258,"score_spread":0.3477792909189477,"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."}}