{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W3XUWNNQ7XKGDG66O6DWMFPFZC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"daae61dd1555e96c9da149818196129971b6945a3d51724618fa61eea2f9d68e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2024-10-14T12:52:48Z","title_canon_sha256":"44f205f9f6865de0f6e5ef76c339140c338d403631a309513484cc83bb37792c"},"schema_version":"1.0","source":{"id":"2410.10460","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10460","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10460v2","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10460","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_12","alias_value":"W3XUWNNQ7XKG","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_16","alias_value":"W3XUWNNQ7XKGDG66","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_8","alias_value":"W3XUWNNQ","created_at":"2026-07-05T11:21:37Z"}],"graph_snapshots":[{"event_id":"sha256:80888c236f3e84ed1924d43c4e4e4fc84ae0afcf06eb5344931d66cc38a8fd53","target":"graph","created_at":"2026-07-05T11:21:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.10460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has emerged as a powerful tool for obtaining high-performance policies. However, the safety of these policies has been a long-standing issue. One promising paradigm to guarantee safety is a shield, which shields a policy from making unsafe actions. However, computing a shield scales exponentially in the number of state variables. This is a particular concern in multi-agent systems with many agents. In this work, we propose a novel approach for multi-agent shielding. We address scalability by computing individual shields for each agent. The challenge is that typical ","authors_text":"Asger Horn Brorholt, Christian Schilling, Kim Guldstrand Larsen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2024-10-14T12:52:48Z","title":"Compositional Shielding and Reinforcement Learning for Multi-Agent Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10460","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:717e6b68a19cda3ee0b9980cf3683fdb4fe6efc582278409a154998a9c7ef3ef","target":"record","created_at":"2026-07-05T11:21:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"daae61dd1555e96c9da149818196129971b6945a3d51724618fa61eea2f9d68e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2024-10-14T12:52:48Z","title_canon_sha256":"44f205f9f6865de0f6e5ef76c339140c338d403631a309513484cc83bb37792c"},"schema_version":"1.0","source":{"id":"2410.10460","kind":"arxiv","version":2}},"canonical_sha256":"b6ef4b35b0fdd4619bde77876615e5c8920224153bc78310e0274ddf0ddc4dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6ef4b35b0fdd4619bde77876615e5c8920224153bc78310e0274ddf0ddc4dc0","first_computed_at":"2026-07-05T11:21:37.027096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:37.027096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QuLW8Wqzz9eIVV1Zc8gZcpWGSYvyww5qX0Z3XiYQoBxUcH/35UM0DEIswXHoskH9L45o1k7xZqT2W8vUz7O0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:37.027623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10460","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:717e6b68a19cda3ee0b9980cf3683fdb4fe6efc582278409a154998a9c7ef3ef","sha256:80888c236f3e84ed1924d43c4e4e4fc84ae0afcf06eb5344931d66cc38a8fd53"],"state_sha256":"f7177c904f33f762fa4fdab3dcc61d7ba105dad23ec532e9f13ec0a111416bb9"}