{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VYGMS24DRDMWWKCRHKUPSFE46R","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":"3acca7bfbfa9a58ed4a70e2d6f9e3e429358ca9958cd28de48984072b4862f81","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T20:34:55Z","title_canon_sha256":"323f35c79f6bc68701868a7589b9c8971224c7eb43a6af5ca923392ff42f4e28"},"schema_version":"1.0","source":{"id":"2504.15425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15425","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15425v1","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15425","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"VYGMS24DRDMW","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"VYGMS24DRDMWWKCR","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"VYGMS24D","created_at":"2026-07-05T10:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:bf98ceebd667b1f1fc4817add26ff90591e63f0d8dbc23693a87777f5a9cc599","target":"graph","created_at":"2026-07-05T10:52:24Z","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/2504.15425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tasks for multi-robot systems often require the robots to collaborate and complete a team goal while maintaining safety. This problem is usually formalized as a constrained Markov decision process (CMDP), which targets minimizing a global cost and bringing the mean of constraint violation below a user-defined threshold. Inspired by real-world robotic applications, we define safety as zero constraint violation. While many safe multi-agent reinforcement learning (MARL) algorithms have been proposed to solve CMDPs, these algorithms suffer from unstable training in this setting. To tackle this, we","authors_text":"Chuchu Fan, Mitchell Black, Oswin So, Songyuan Zhang, Zachary Serlin","cross_cats":["cs.AI","cs.LG","cs.MA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T20:34:55Z","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15425","kind":"arxiv","version":1},"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:b7f6a1a0ec35f1561b2fede1257c7a5023ce8c393338412deaf35fd6a0616079","target":"record","created_at":"2026-07-05T10:52:24Z","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":"3acca7bfbfa9a58ed4a70e2d6f9e3e429358ca9958cd28de48984072b4862f81","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T20:34:55Z","title_canon_sha256":"323f35c79f6bc68701868a7589b9c8971224c7eb43a6af5ca923392ff42f4e28"},"schema_version":"1.0","source":{"id":"2504.15425","kind":"arxiv","version":1}},"canonical_sha256":"ae0cc96b8388d96b28513aa8f9149cf45ea3fabe5a6b861ea53acd50173e9b91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae0cc96b8388d96b28513aa8f9149cf45ea3fabe5a6b861ea53acd50173e9b91","first_computed_at":"2026-07-05T10:52:24.405078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:24.405078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8XI3IAyWGlo8ZO5QLbF5+LtdLobt3Vv4tJvT6PgnxhE+fAJGrUPvqV86TVFt5B9AcZO2MXGowoUIKnpaQWsBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:24.405602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7f6a1a0ec35f1561b2fede1257c7a5023ce8c393338412deaf35fd6a0616079","sha256:bf98ceebd667b1f1fc4817add26ff90591e63f0d8dbc23693a87777f5a9cc599"],"state_sha256":"12352842d764ea429f6629da538aecc882e5d4b7cab67ab3a7233af1e70c0dad"}