{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQVRL6J6DSTRDXH2C5DOUCAOAL","short_pith_number":"pith:RQVRL6J6","schema_version":"1.0","canonical_sha256":"8c2b15f93e1ca711dcfa1746ea080e02e990f10b6a71e32017cb9199ee4757a2","source":{"kind":"arxiv","id":"2504.06670","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kaifeng Wang, Qi Liu, Xin Gao, Xueyuan Li, Yinsong Chen","submitted_at":"2025-04-09T08:13:14Z","abstract_excerpt":"In multi-agent safety-critical scenarios, traditional autonomous driving frameworks face significant challenges in balancing safety constraints and task performance. These frameworks struggle to quantify dynamic interaction risks in real-time and depend heavily on manual rules, resulting in low computational efficiency and conservative strategies. To address these limitations, we propose a Dynamic Residual Safe Reinforcement Learning (DRS-RL) framework grounded in a safety-enhanced networked Markov decision process. It's the first time that the weak-to-strong theory is introduced into multi-ag"},"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":"2504.06670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-09T08:13:14Z","cross_cats_sorted":[],"title_canon_sha256":"63bfa5a520d14d661657b95d2c6eb3571acc673fab40616e86e8064dcbd0604d","abstract_canon_sha256":"16159c029ddf2dfbf152a1d0cf5032c76378e191db7006eed1165a9d31fbcb16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:43.864323Z","signature_b64":"XFZRVLhjiPWA0zaCJFzeyt7zgDlxX6QSSOxgrEz/onRizfN0HfnmawH4NpZldCnU+OcXyxyaAzVZjSg/oOVkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c2b15f93e1ca711dcfa1746ea080e02e990f10b6a71e32017cb9199ee4757a2","last_reissued_at":"2026-07-05T10:46:43.863827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:43.863827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kaifeng Wang, Qi Liu, Xin Gao, Xueyuan Li, Yinsong Chen","submitted_at":"2025-04-09T08:13:14Z","abstract_excerpt":"In multi-agent safety-critical scenarios, traditional autonomous driving frameworks face significant challenges in balancing safety constraints and task performance. These frameworks struggle to quantify dynamic interaction risks in real-time and depend heavily on manual rules, resulting in low computational efficiency and conservative strategies. To address these limitations, we propose a Dynamic Residual Safe Reinforcement Learning (DRS-RL) framework grounded in a safety-enhanced networked Markov decision process. It's the first time that the weak-to-strong theory is introduced into multi-ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06670","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/2504.06670/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":"2504.06670","created_at":"2026-07-05T10:46:43.863895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06670v1","created_at":"2026-07-05T10:46:43.863895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06670","created_at":"2026-07-05T10:46:43.863895+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQVRL6J6DSTR","created_at":"2026-07-05T10:46:43.863895+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQVRL6J6DSTRDXH2","created_at":"2026-07-05T10:46:43.863895+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQVRL6J6","created_at":"2026-07-05T10:46:43.863895+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/RQVRL6J6DSTRDXH2C5DOUCAOAL","json":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL.json","graph_json":"https://pith.science/api/pith-number/RQVRL6J6DSTRDXH2C5DOUCAOAL/graph.json","events_json":"https://pith.science/api/pith-number/RQVRL6J6DSTRDXH2C5DOUCAOAL/events.json","paper":"https://pith.science/paper/RQVRL6J6"},"agent_actions":{"view_html":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL","download_json":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL.json","view_paper":"https://pith.science/paper/RQVRL6J6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06670&json=true","fetch_graph":"https://pith.science/api/pith-number/RQVRL6J6DSTRDXH2C5DOUCAOAL/graph.json","fetch_events":"https://pith.science/api/pith-number/RQVRL6J6DSTRDXH2C5DOUCAOAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL/action/storage_attestation","attest_author":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL/action/author_attestation","sign_citation":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL/action/citation_signature","submit_replication":"https://pith.science/pith/RQVRL6J6DSTRDXH2C5DOUCAOAL/action/replication_record"}},"created_at":"2026-07-05T10:46:43.863895+00:00","updated_at":"2026-07-05T10:46:43.863895+00:00"}