{"id":"W4411948807","doi":"10.1109/jiot.2025.3584811","title":"Permutation-Invariant and Equivariant Multiagent Reinforcement Learning for Flexible Manufacturing in Industrial IoT","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Digital Transformation in Industry","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Invariant (physics); Equivariant map; Computer science; Permutation (music); Reinforcement learning; Internet of Things; Distributed computing; Artificial intelligence; Theoretical computer science; Mathematics; Computer security; Pure mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004590522,0.0001393845,0.0001999931,0.0003403297,0.0000441852,0.0001599543,0.0001621191,0.0001305969,0.00004363276],"category_scores_gemma":[0.00008140672,0.0001394845,0.00006698502,0.00007774398,0.00002693435,0.0004435203,0.0000240647,0.0006032375,0.000001928836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001714855,"about_ca_system_score_gemma":0.00004280251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003237308,"about_ca_topic_score_gemma":0.000001541054,"domain_scores_codex":[0.9988437,0.00001769064,0.0006501463,0.00009955189,0.0001648394,0.0002241315],"domain_scores_gemma":[0.9995955,0.0001197551,0.0001142164,0.00006270213,0.00004611513,0.00006177728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001326787,0.00002750184,0.000481463,0.0002760718,0.0001923389,0.00001306267,0.004155775,0.9652469,0.003439056,0.001338389,0.001617795,0.02307893],"study_design_scores_gemma":[0.004662937,0.000213963,0.0003920486,0.002165713,0.0000554555,0.0001168308,0.001534201,0.596212,0.3855041,0.001610927,0.007154176,0.0003775978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5705701,0.00009548831,0.4144106,0.0002060517,0.00193647,0.0003681169,0.000002553951,0.00009727725,0.01231341],"genre_scores_gemma":[0.9979566,0.00002277104,0.0009519227,0.0000463118,0.00008326879,0.00001428442,0.000003075721,0.00001563682,0.0009060916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4273866,"threshold_uncertainty_score":0.5688012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02886827858804082,"score_gpt":0.2615844009393472,"score_spread":0.2327161223513063,"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."}}