{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3X2LP3LPKDQY2OS55OYSMZNVHW","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":"3da80ddb0cc285821fae8ba9987fc808d852c782f2f4115ec656c30a61d6631e","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T04:27:06Z","title_canon_sha256":"384be0531d394a6048e9a37a680ec6bb41a4bfe7932be8868c2a9c1e14711a10"},"schema_version":"1.0","source":{"id":"2101.11196","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11196","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11196v2","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11196","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"3X2LP3LPKDQY","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"3X2LP3LPKDQY2OS5","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"3X2LP3LP","created_at":"2026-07-05T02:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:5f9c0ae97a769f0f4ff03152d61297aaecf79d7de12602bf38839c0e67ea9d8b","target":"graph","created_at":"2026-07-05T02:11:26Z","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/2101.11196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.Unfortunately, current MARL methods do not have safety guarantees. Therefore, we present two shielding approaches for safe MARL. In centralized shielding, we synthesize a single shield to monitor all agents' joint actions and correct any unsafe action if necessary. In factored shielding, we synthesize multiple shields based on a factorization of the joint state space observed b","authors_text":"Christopher Amato, Ingy Elsayed-Aly, Lu Feng, R\\\"udiger Ehlers, Suda Bharadwaj, Ufuk Topcu","cross_cats":["cs.FL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T04:27:06Z","title":"Safe Multi-Agent Reinforcement Learning via Shielding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11196","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:b00e0e15d98058d4f43911c87b254339a541de9843c2848d9e0798197a036f37","target":"record","created_at":"2026-07-05T02:11:26Z","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":"3da80ddb0cc285821fae8ba9987fc808d852c782f2f4115ec656c30a61d6631e","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T04:27:06Z","title_canon_sha256":"384be0531d394a6048e9a37a680ec6bb41a4bfe7932be8868c2a9c1e14711a10"},"schema_version":"1.0","source":{"id":"2101.11196","kind":"arxiv","version":2}},"canonical_sha256":"ddf4b7ed6f50e18d3a5debb12665b53da9dc502324fce4aa7fb5d78ae62eba3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf4b7ed6f50e18d3a5debb12665b53da9dc502324fce4aa7fb5d78ae62eba3f","first_computed_at":"2026-07-05T02:11:26.293274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:26.293274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q8gx3bVR6sQdhc1MPeBtucKISapZu0t3JYH4wn2DbFFhGDtUVT1MZ8eR7D1165hRROUxyiPsmh3bdjgYJjB3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:26.293775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.11196","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b00e0e15d98058d4f43911c87b254339a541de9843c2848d9e0798197a036f37","sha256:5f9c0ae97a769f0f4ff03152d61297aaecf79d7de12602bf38839c0e67ea9d8b"],"state_sha256":"63c8708cad111d6e1ad64437d1f4c4e03e1abc71c27d61ebe614430df26e0248"}