{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GKVDOKOUP6RWT766464E3INAZD","short_pith_number":"pith:GKVDOKOU","schema_version":"1.0","canonical_sha256":"32aa3729d47fa369ffdee7b84da1a0c8d0aeb9ca46c8ad4d54d1ed99709e4c2a","source":{"kind":"arxiv","id":"2309.11057","version":2},"attestation_state":"computed","paper":{"title":"Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Ehsan Sabouni, Fei Miao, Furong Huang, H M Sabbir Ahmad, Wenchao Li, Yanchao Sun, Zhili Zhang","submitted_at":"2023-09-20T04:34:09Z","abstract_excerpt":"We address the problem of coordination and control of Connected and Automated Vehicles (CAVs) in the presence of imperfect observations in mixed traffic environment. A commonly used approach is learning-based decision-making, such as reinforcement learning (RL). However, most existing safe RL methods suffer from two limitations: (i) they assume accurate state information, and (ii) safety is generally defined over the expectation of the trajectories. It remains challenging to design optimal coordination between multi-agents while ensuring hard safety constraints under system state uncertainties"},"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":"2309.11057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-09-20T04:34:09Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"91a1213d53fddf59120033ba153f9476a7ea94cdcfcd99981411b79add6bde9a","abstract_canon_sha256":"65ea6311dc6190e4b6805851197c0669c66f6cf250814fbec16efa62b7081ae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:42.465152Z","signature_b64":"zUbtSF+I6s1yKi2P09tXfATu7QnBTa1sfdi1ThidLKOGgphyqp6X45jdUp+7zmvCI1Oh6hOGaDRIcbqnz2W1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32aa3729d47fa369ffdee7b84da1a0c8d0aeb9ca46c8ad4d54d1ed99709e4c2a","last_reissued_at":"2026-07-05T09:10:42.464667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:42.464667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Ehsan Sabouni, Fei Miao, Furong Huang, H M Sabbir Ahmad, Wenchao Li, Yanchao Sun, Zhili Zhang","submitted_at":"2023-09-20T04:34:09Z","abstract_excerpt":"We address the problem of coordination and control of Connected and Automated Vehicles (CAVs) in the presence of imperfect observations in mixed traffic environment. A commonly used approach is learning-based decision-making, such as reinforcement learning (RL). However, most existing safe RL methods suffer from two limitations: (i) they assume accurate state information, and (ii) safety is generally defined over the expectation of the trajectories. It remains challenging to design optimal coordination between multi-agents while ensuring hard safety constraints under system state uncertainties"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11057","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/2309.11057/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":"2309.11057","created_at":"2026-07-05T09:10:42.464724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11057v2","created_at":"2026-07-05T09:10:42.464724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11057","created_at":"2026-07-05T09:10:42.464724+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKVDOKOUP6RW","created_at":"2026-07-05T09:10:42.464724+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKVDOKOUP6RWT766","created_at":"2026-07-05T09:10:42.464724+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKVDOKOU","created_at":"2026-07-05T09:10:42.464724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.00982","citing_title":"Robust and Safe Multi-Agent Reinforcement Learning with Communication for Autonomous Vehicles: From Simulation to Hardware","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD","json":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD.json","graph_json":"https://pith.science/api/pith-number/GKVDOKOUP6RWT766464E3INAZD/graph.json","events_json":"https://pith.science/api/pith-number/GKVDOKOUP6RWT766464E3INAZD/events.json","paper":"https://pith.science/paper/GKVDOKOU"},"agent_actions":{"view_html":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD","download_json":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD.json","view_paper":"https://pith.science/paper/GKVDOKOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11057&json=true","fetch_graph":"https://pith.science/api/pith-number/GKVDOKOUP6RWT766464E3INAZD/graph.json","fetch_events":"https://pith.science/api/pith-number/GKVDOKOUP6RWT766464E3INAZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD/action/storage_attestation","attest_author":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD/action/author_attestation","sign_citation":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD/action/citation_signature","submit_replication":"https://pith.science/pith/GKVDOKOUP6RWT766464E3INAZD/action/replication_record"}},"created_at":"2026-07-05T09:10:42.464724+00:00","updated_at":"2026-07-05T09:10:42.464724+00:00"}