{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FISYKRAPGD22MELIDXQE5GITFZ","short_pith_number":"pith:FISYKRAP","schema_version":"1.0","canonical_sha256":"2a2585440f30f5a611681de04e99132e44e2f2724aabb72c5dac5cd1e94af9ee","source":{"kind":"arxiv","id":"2502.03640","version":3},"attestation_state":"computed","paper":{"title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","math.OC"],"primary_cat":"cs.RO","authors_text":"Chuchu Fan, Mitchell Black, Oswin So, Songyuan Zhang","submitted_at":"2025-02-05T21:51:47Z","abstract_excerpt":"Control policies that can achieve high task performance and satisfy safety constraints are desirable for any system, including multi-agent systems (MAS). One promising technique for ensuring the safety of MAS is distributed control barrier functions (CBF). However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable. To tackle these challenges, we propose DGPPO, a"},"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":"2502.03640","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-05T21:51:47Z","cross_cats_sorted":["cs.LG","cs.MA","math.OC"],"title_canon_sha256":"2174340bc0c3e826790c5a99572c1c767ddd37f8c9048c9a4284013e85ca4333","abstract_canon_sha256":"4b684a7f6bb5cbdbd7a5297e0f84c42d98ec82429a19e20c20a2906604d41312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:01.370527Z","signature_b64":"CQnSsWrJszmG5dmoOWCOkXS1CDdrSiocN1qOkR0+3BxSBL2LibRlmHaKLnvflrWHG1zkYBK2gOG4hqRxShctCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2585440f30f5a611681de04e99132e44e2f2724aabb72c5dac5cd1e94af9ee","last_reissued_at":"2026-07-05T10:31:01.369903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:01.369903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","math.OC"],"primary_cat":"cs.RO","authors_text":"Chuchu Fan, Mitchell Black, Oswin So, Songyuan Zhang","submitted_at":"2025-02-05T21:51:47Z","abstract_excerpt":"Control policies that can achieve high task performance and satisfy safety constraints are desirable for any system, including multi-agent systems (MAS). One promising technique for ensuring the safety of MAS is distributed control barrier functions (CBF). However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable. To tackle these challenges, we propose DGPPO, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03640","kind":"arxiv","version":3},"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/2502.03640/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":"2502.03640","created_at":"2026-07-05T10:31:01.369986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03640v3","created_at":"2026-07-05T10:31:01.369986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03640","created_at":"2026-07-05T10:31:01.369986+00:00"},{"alias_kind":"pith_short_12","alias_value":"FISYKRAPGD22","created_at":"2026-07-05T10:31:01.369986+00:00"},{"alias_kind":"pith_short_16","alias_value":"FISYKRAPGD22MELI","created_at":"2026-07-05T10:31:01.369986+00:00"},{"alias_kind":"pith_short_8","alias_value":"FISYKRAP","created_at":"2026-07-05T10:31:01.369986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24010","citing_title":"Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02924","citing_title":"How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ","json":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ.json","graph_json":"https://pith.science/api/pith-number/FISYKRAPGD22MELIDXQE5GITFZ/graph.json","events_json":"https://pith.science/api/pith-number/FISYKRAPGD22MELIDXQE5GITFZ/events.json","paper":"https://pith.science/paper/FISYKRAP"},"agent_actions":{"view_html":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ","download_json":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ.json","view_paper":"https://pith.science/paper/FISYKRAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03640&json=true","fetch_graph":"https://pith.science/api/pith-number/FISYKRAPGD22MELIDXQE5GITFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FISYKRAPGD22MELIDXQE5GITFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ/action/storage_attestation","attest_author":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ/action/author_attestation","sign_citation":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ/action/citation_signature","submit_replication":"https://pith.science/pith/FISYKRAPGD22MELIDXQE5GITFZ/action/replication_record"}},"created_at":"2026-07-05T10:31:01.369986+00:00","updated_at":"2026-07-05T10:31:01.369986+00:00"}