{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZE4NLNT53AELX7P2O2AC4ALUB7","short_pith_number":"pith:ZE4NLNT5","schema_version":"1.0","canonical_sha256":"c938d5b67dd808bbfdfa76802e01740ff6756474ce4fb50395a109aeb5981bd7","source":{"kind":"arxiv","id":"2606.27861","version":1},"attestation_state":"computed","paper":{"title":"PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Del Prete, Jiatao Ding, Matteo Saveriano, Songqun Gao","submitted_at":"2026-06-26T08:59:38Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising solution to accomplish complex robotic control tasks; however, most of the current work ignores the safety requirements. Safe RL seeks to maximize task performance while satisfying explicit physical constraints, but current algorithms struggle to learn the policy efficiently with precise constraint satisfaction. This work proposes PPO-EAL, a novel first-order constrained policy optimization framework that integrates exact augmented Lagrangian optimization into proximal policy optimization for safe robotic control. By combining clipped poli"},"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":"2606.27861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-26T08:59:38Z","cross_cats_sorted":[],"title_canon_sha256":"d8eeb7b19b934b81b9a55aecb1f47a497699f59a76c45efeda8abb9e41b5a063","abstract_canon_sha256":"2457264e4dbfe1e8478134d7bee6222581fdbf9767e85856b49e35e587070b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:50.943750Z","signature_b64":"EZWmYnPQI9v8W+1vUGbzu/K/oQ67N9fVliu85xkJtgpcqzvI9oCV1coM7f0Mwqz/crUQZeNW5rYhR0IEUct3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c938d5b67dd808bbfdfa76802e01740ff6756474ce4fb50395a109aeb5981bd7","last_reissued_at":"2026-06-29T01:14:50.943160Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:50.943160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Del Prete, Jiatao Ding, Matteo Saveriano, Songqun Gao","submitted_at":"2026-06-26T08:59:38Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising solution to accomplish complex robotic control tasks; however, most of the current work ignores the safety requirements. Safe RL seeks to maximize task performance while satisfying explicit physical constraints, but current algorithms struggle to learn the policy efficiently with precise constraint satisfaction. This work proposes PPO-EAL, a novel first-order constrained policy optimization framework that integrates exact augmented Lagrangian optimization into proximal policy optimization for safe robotic control. By combining clipped poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27861","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/2606.27861/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":"2606.27861","created_at":"2026-06-29T01:14:50.943265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27861v1","created_at":"2026-06-29T01:14:50.943265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27861","created_at":"2026-06-29T01:14:50.943265+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE4NLNT53AEL","created_at":"2026-06-29T01:14:50.943265+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE4NLNT53AELX7P2","created_at":"2026-06-29T01:14:50.943265+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE4NLNT5","created_at":"2026-06-29T01:14:50.943265+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/ZE4NLNT53AELX7P2O2AC4ALUB7","json":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7.json","graph_json":"https://pith.science/api/pith-number/ZE4NLNT53AELX7P2O2AC4ALUB7/graph.json","events_json":"https://pith.science/api/pith-number/ZE4NLNT53AELX7P2O2AC4ALUB7/events.json","paper":"https://pith.science/paper/ZE4NLNT5"},"agent_actions":{"view_html":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7","download_json":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7.json","view_paper":"https://pith.science/paper/ZE4NLNT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27861&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE4NLNT53AELX7P2O2AC4ALUB7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE4NLNT53AELX7P2O2AC4ALUB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7/action/storage_attestation","attest_author":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7/action/author_attestation","sign_citation":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7/action/citation_signature","submit_replication":"https://pith.science/pith/ZE4NLNT53AELX7P2O2AC4ALUB7/action/replication_record"}},"created_at":"2026-06-29T01:14:50.943265+00:00","updated_at":"2026-06-29T01:14:50.943265+00:00"}