{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SX36ZMBFZI5JAVTFLLMRBITOWK","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":"0f45512950e22d94164f9798b20c14d2c03ebf0f966dca57a2fbbfc842a3c103","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T07:43:18Z","title_canon_sha256":"62d5acdee8a4e170b9b7bcc7a1c26b241d65e773853a81f4ef1571180189f0ad"},"schema_version":"1.0","source":{"id":"2507.14850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14850","created_at":"2026-07-05T11:55:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14850v2","created_at":"2026-07-05T11:55:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14850","created_at":"2026-07-05T11:55:20Z"},{"alias_kind":"pith_short_12","alias_value":"SX36ZMBFZI5J","created_at":"2026-07-05T11:55:20Z"},{"alias_kind":"pith_short_16","alias_value":"SX36ZMBFZI5JAVTF","created_at":"2026-07-05T11:55:20Z"},{"alias_kind":"pith_short_8","alias_value":"SX36ZMBF","created_at":"2026-07-05T11:55:20Z"}],"graph_snapshots":[{"event_id":"sha256:54a589a1c2b790e5d6d92cc4b2df67fd7313457d023085759151f14d0f10557c","target":"graph","created_at":"2026-07-05T11:55:20Z","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/2507.14850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of safe policy learning in multi-agent safety-critical autonomous systems. In such systems, it is necessary for each agent to meet the safety requirements at all times while also cooperating with other agents to accomplish the task. Toward this end, we propose a safe Hierarchical Multi-Agent Reinforcement Learning (HMARL) approach based on Control Barrier Functions (CBFs). Our proposed hierarchical approach decomposes the overall reinforcement learning problem into two levels learning joint cooperative behavior at the higher level and learning safe individual behavior at","authors_text":"Alexander Wasilkoff, Christos Cassandras, Chuchu Fan, Ehsan Sabouni, H. M. Sabbir Ahmad, Param Budhraja, Songyuan Zhang, Wenchao Li, Zijian Guo","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T07:43:18Z","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14850","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:cfcc81f7f10b51b8a4444ebf7b1e56c8722f4f2bf3cee3fe44b5d39a9770f843","target":"record","created_at":"2026-07-05T11:55:20Z","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":"0f45512950e22d94164f9798b20c14d2c03ebf0f966dca57a2fbbfc842a3c103","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T07:43:18Z","title_canon_sha256":"62d5acdee8a4e170b9b7bcc7a1c26b241d65e773853a81f4ef1571180189f0ad"},"schema_version":"1.0","source":{"id":"2507.14850","kind":"arxiv","version":2}},"canonical_sha256":"95f7ecb025ca3a9056655ad910a26eb290b25e602220b4cb354744843b98a649","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f7ecb025ca3a9056655ad910a26eb290b25e602220b4cb354744843b98a649","first_computed_at":"2026-07-05T11:55:20.556929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:20.556929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lF4YQ+WwtcaXA0VYMSGt4Pr7denA2u18hEBMAK16GmR1ymGUAn5G/4yx7+ypUhapy1aEVpBJ/5t0w4+RtqZOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:20.557484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfcc81f7f10b51b8a4444ebf7b1e56c8722f4f2bf3cee3fe44b5d39a9770f843","sha256:54a589a1c2b790e5d6d92cc4b2df67fd7313457d023085759151f14d0f10557c"],"state_sha256":"bca7f39f827f2a7b75a5423b1dc140eaf0b5547e0b1f1894c3dd21a905158b5f"}