{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVGIMSWAAPS62CJH427PJIR43C","short_pith_number":"pith:PVGIMSWA","schema_version":"1.0","canonical_sha256":"7d4c864ac003e5ed0927e6bef4a23cd89905bdd2ea2698f8ba089974599c8ebb","source":{"kind":"arxiv","id":"2501.13727","version":2},"attestation_state":"computed","paper":{"title":"Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Fandi Gou, Haikuo Du, Yunze Cai","submitted_at":"2025-01-23T15:01:19Z","abstract_excerpt":"Safety and scalability are two critical challenges faced by practical Multi-Agent Systems (MAS). However, existing Multi-Agent Reinforcement Learning (MARL) algorithms that rely solely on reward shaping are ineffective in ensuring safety, and their scalability is rather limited due to the fixed-size network output. To address these issues, we propose a novel framework, Scalable Safe MARL (SS-MARL), to enhance the safety and scalability of MARL methods. Leveraging the inherent graph structure of MAS, we design a multi-layer message passing network to aggregate local observations and communicati"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.13727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-01-23T15:01:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79f3aa0b335e385373d11903c8376db3e806140b6d1b59f584d765914e337354","abstract_canon_sha256":"196009eaa2fccd75e65c6f259f7110e0d5f42f4eea0ba4064a1f9222c81bd01d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:42.647225Z","signature_b64":"iWVzSfNBGb0QJ0lOx0t7QafNyZ1QEh6Yyl+M9FjMIkEUcd5FGxZ6/J6IpuzSXyLuGM8gs0zU/b+wU/4encmFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d4c864ac003e5ed0927e6bef4a23cd89905bdd2ea2698f8ba089974599c8ebb","last_reissued_at":"2026-07-05T10:42:42.646716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:42.646716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Fandi Gou, Haikuo Du, Yunze Cai","submitted_at":"2025-01-23T15:01:19Z","abstract_excerpt":"Safety and scalability are two critical challenges faced by practical Multi-Agent Systems (MAS). However, existing Multi-Agent Reinforcement Learning (MARL) algorithms that rely solely on reward shaping are ineffective in ensuring safety, and their scalability is rather limited due to the fixed-size network output. To address these issues, we propose a novel framework, Scalable Safe MARL (SS-MARL), to enhance the safety and scalability of MARL methods. Leveraging the inherent graph structure of MAS, we design a multi-layer message passing network to aggregate local observations and communicati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13727","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.13727/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.13727","created_at":"2026-07-05T10:42:42.646773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13727v2","created_at":"2026-07-05T10:42:42.646773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13727","created_at":"2026-07-05T10:42:42.646773+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVGIMSWAAPS6","created_at":"2026-07-05T10:42:42.646773+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVGIMSWAAPS62CJH","created_at":"2026-07-05T10:42:42.646773+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVGIMSWA","created_at":"2026-07-05T10:42:42.646773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C","json":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C.json","graph_json":"https://pith.science/api/pith-number/PVGIMSWAAPS62CJH427PJIR43C/graph.json","events_json":"https://pith.science/api/pith-number/PVGIMSWAAPS62CJH427PJIR43C/events.json","paper":"https://pith.science/paper/PVGIMSWA"},"agent_actions":{"view_html":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C","download_json":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C.json","view_paper":"https://pith.science/paper/PVGIMSWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13727&json=true","fetch_graph":"https://pith.science/api/pith-number/PVGIMSWAAPS62CJH427PJIR43C/graph.json","fetch_events":"https://pith.science/api/pith-number/PVGIMSWAAPS62CJH427PJIR43C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C/action/storage_attestation","attest_author":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C/action/author_attestation","sign_citation":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C/action/citation_signature","submit_replication":"https://pith.science/pith/PVGIMSWAAPS62CJH427PJIR43C/action/replication_record"}},"created_at":"2026-07-05T10:42:42.646773+00:00","updated_at":"2026-07-05T10:42:42.646773+00:00"}