{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPWCKW6FQUPJXEWPKV7UL6PL7Q","short_pith_number":"pith:YPWCKW6F","schema_version":"1.0","canonical_sha256":"c3ec255bc5851e9b92cf557f45f9ebfc01a740a2e35e83376c41ef5d3a224a0f","source":{"kind":"arxiv","id":"2403.06397","version":2},"attestation_state":"computed","paper":{"title":"DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Henglin Pu, Husheng Li, Hyung Jun Kim, Xuefeng Wang","submitted_at":"2024-03-11T03:17:33Z","abstract_excerpt":"Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through behavioral constraints. Some recent work has integrated control theory with multi-agent reinforcement learning to address the challenge of ensuring safety. However, there have been only very limited applications of Model Predictive Control (MPC) methods in this domain, primarily due to the complex and implicit dynamics characteristic of multi-agent environments. To bridge this"},"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":"2403.06397","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T03:17:33Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"7c656cba6dab35a98a5c715eb741f543d334e586b9688823bac331c8529e4d87","abstract_canon_sha256":"8ead6e804e5e1000cce31b623d3fbc5f3b50bb38c8d65f1942684da52c71884f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:57.270811Z","signature_b64":"Nu9Q1IhrtxrhN4bslgUpK6cL5oldWu3I63845vWE+/BD6vAwp57RWy9+nfLfKZdbuGS1IGQq8076ubhgQeLuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3ec255bc5851e9b92cf557f45f9ebfc01a740a2e35e83376c41ef5d3a224a0f","last_reissued_at":"2026-07-05T07:54:57.270397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:57.270397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Henglin Pu, Husheng Li, Hyung Jun Kim, Xuefeng Wang","submitted_at":"2024-03-11T03:17:33Z","abstract_excerpt":"Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through behavioral constraints. Some recent work has integrated control theory with multi-agent reinforcement learning to address the challenge of ensuring safety. However, there have been only very limited applications of Model Predictive Control (MPC) methods in this domain, primarily due to the complex and implicit dynamics characteristic of multi-agent environments. To bridge this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06397","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/2403.06397/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":"2403.06397","created_at":"2026-07-05T07:54:57.270458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06397v2","created_at":"2026-07-05T07:54:57.270458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06397","created_at":"2026-07-05T07:54:57.270458+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPWCKW6FQUPJ","created_at":"2026-07-05T07:54:57.270458+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPWCKW6FQUPJXEWP","created_at":"2026-07-05T07:54:57.270458+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPWCKW6F","created_at":"2026-07-05T07:54:57.270458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.19473","citing_title":"Stability Enhancement in Reinforcement Learning via Adaptive Control Lyapunov Function","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q","json":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q.json","graph_json":"https://pith.science/api/pith-number/YPWCKW6FQUPJXEWPKV7UL6PL7Q/graph.json","events_json":"https://pith.science/api/pith-number/YPWCKW6FQUPJXEWPKV7UL6PL7Q/events.json","paper":"https://pith.science/paper/YPWCKW6F"},"agent_actions":{"view_html":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q","download_json":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q.json","view_paper":"https://pith.science/paper/YPWCKW6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06397&json=true","fetch_graph":"https://pith.science/api/pith-number/YPWCKW6FQUPJXEWPKV7UL6PL7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/YPWCKW6FQUPJXEWPKV7UL6PL7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q/action/storage_attestation","attest_author":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q/action/author_attestation","sign_citation":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q/action/citation_signature","submit_replication":"https://pith.science/pith/YPWCKW6FQUPJXEWPKV7UL6PL7Q/action/replication_record"}},"created_at":"2026-07-05T07:54:57.270458+00:00","updated_at":"2026-07-05T07:54:57.270458+00:00"}