{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CEBYXZII4454PISFSJSUI4NKRN","short_pith_number":"pith:CEBYXZII","schema_version":"1.0","canonical_sha256":"11038be508e73bc7a24592654471aa8b690626e76dcc1009df729ccac10de74e","source":{"kind":"arxiv","id":"2207.00842","version":1},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Hairuo Wei, Hao Xiong, Huanhui Cao, Lin Zhang, Wenjie Lu, Zhiyuan Cai","submitted_at":"2022-07-02T14:21:40Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following a learned policy may suffer a vehicle with unpredictable aggressive behaviors or even being pursued by a vehicle following a Nash strategy. To address the safety issue of the self-driven vehicle in this scenario, this paper conducts a preliminary study based on a system of robots. A safe RL framework with safety guarantees is developed for a robot being purs"},"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":"2207.00842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-07-02T14:21:40Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"537dab352f192746a5b84ddf5e85543ea62f2b0fd6688640be7abc6a13195d1e","abstract_canon_sha256":"2455bceaddd73744ee93a5e5003c3efffaf8a34807acaf24523acd329b2a085e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:53.083124Z","signature_b64":"6YgG5mbQNSMVPH/EnY6NMUbQ/9+rp2xkLkATF9qe9RBPZgmx9y1CC7DkLl0f5JR8PjJzqLMnEFQd3z5XG7Z2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11038be508e73bc7a24592654471aa8b690626e76dcc1009df729ccac10de74e","last_reissued_at":"2026-07-05T04:36:53.082783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:53.082783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Hairuo Wei, Hao Xiong, Huanhui Cao, Lin Zhang, Wenjie Lu, Zhiyuan Cai","submitted_at":"2022-07-02T14:21:40Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following a learned policy may suffer a vehicle with unpredictable aggressive behaviors or even being pursued by a vehicle following a Nash strategy. To address the safety issue of the self-driven vehicle in this scenario, this paper conducts a preliminary study based on a system of robots. A safe RL framework with safety guarantees is developed for a robot being purs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00842","kind":"arxiv","version":1},"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/2207.00842/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":"2207.00842","created_at":"2026-07-05T04:36:53.082838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00842v1","created_at":"2026-07-05T04:36:53.082838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00842","created_at":"2026-07-05T04:36:53.082838+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEBYXZII4454","created_at":"2026-07-05T04:36:53.082838+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEBYXZII4454PISF","created_at":"2026-07-05T04:36:53.082838+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEBYXZII","created_at":"2026-07-05T04:36:53.082838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN","json":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN.json","graph_json":"https://pith.science/api/pith-number/CEBYXZII4454PISFSJSUI4NKRN/graph.json","events_json":"https://pith.science/api/pith-number/CEBYXZII4454PISFSJSUI4NKRN/events.json","paper":"https://pith.science/paper/CEBYXZII"},"agent_actions":{"view_html":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN","download_json":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN.json","view_paper":"https://pith.science/paper/CEBYXZII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00842&json=true","fetch_graph":"https://pith.science/api/pith-number/CEBYXZII4454PISFSJSUI4NKRN/graph.json","fetch_events":"https://pith.science/api/pith-number/CEBYXZII4454PISFSJSUI4NKRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN/action/storage_attestation","attest_author":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN/action/author_attestation","sign_citation":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN/action/citation_signature","submit_replication":"https://pith.science/pith/CEBYXZII4454PISFSJSUI4NKRN/action/replication_record"}},"created_at":"2026-07-05T04:36:53.082838+00:00","updated_at":"2026-07-05T04:36:53.082838+00:00"}