{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJBREWYPZESSBWGS7APFSOBXAR","short_pith_number":"pith:YJBREWYP","schema_version":"1.0","canonical_sha256":"c243125b0fc92520d8d2f81e593837046ef23228076dca7826e1145fe908f969","source":{"kind":"arxiv","id":"2402.02025","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Xun Shen, Yanan Sui","submitted_at":"2024-02-03T04:40:31Z","abstract_excerpt":"Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent safe RL approach is based on a constrained criterion, which seeks to maximize the expected cumulative reward subject to specific safety constraints. Despite recent effort to enhance safety in RL, a systematic understanding of the field remains difficult. This challenge stems from the diversity of constraint representations and little exploration of their in"},"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":"2402.02025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T04:40:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74f9a7f98e2f34c033da5c7903d4cddd1162b5b516bf7af87316d980c7b4cc39","abstract_canon_sha256":"6420ef948a0efdffd9bfce3c335040150013d99006eafea0e927d40e92ea0285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:46.901679Z","signature_b64":"tqMdTt/l9MuPfQhLkD7Nq9nt+sTqkalgANyqf2O56eC/CYNJyIj9CysvjQfu8f/fBhb5aufRi4eVH50Qag8yDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c243125b0fc92520d8d2f81e593837046ef23228076dca7826e1145fe908f969","last_reissued_at":"2026-07-05T08:16:46.901200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:46.901200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Xun Shen, Yanan Sui","submitted_at":"2024-02-03T04:40:31Z","abstract_excerpt":"Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent safe RL approach is based on a constrained criterion, which seeks to maximize the expected cumulative reward subject to specific safety constraints. Despite recent effort to enhance safety in RL, a systematic understanding of the field remains difficult. This challenge stems from the diversity of constraint representations and little exploration of their in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02025","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/2402.02025/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":"2402.02025","created_at":"2026-07-05T08:16:46.901251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02025v2","created_at":"2026-07-05T08:16:46.901251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02025","created_at":"2026-07-05T08:16:46.901251+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJBREWYPZESS","created_at":"2026-07-05T08:16:46.901251+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJBREWYPZESSBWGS","created_at":"2026-07-05T08:16:46.901251+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJBREWYP","created_at":"2026-07-05T08:16:46.901251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27659","citing_title":"Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16344","citing_title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18841","citing_title":"From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18842","citing_title":"Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23775","citing_title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR","json":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR.json","graph_json":"https://pith.science/api/pith-number/YJBREWYPZESSBWGS7APFSOBXAR/graph.json","events_json":"https://pith.science/api/pith-number/YJBREWYPZESSBWGS7APFSOBXAR/events.json","paper":"https://pith.science/paper/YJBREWYP"},"agent_actions":{"view_html":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR","download_json":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR.json","view_paper":"https://pith.science/paper/YJBREWYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02025&json=true","fetch_graph":"https://pith.science/api/pith-number/YJBREWYPZESSBWGS7APFSOBXAR/graph.json","fetch_events":"https://pith.science/api/pith-number/YJBREWYPZESSBWGS7APFSOBXAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR/action/storage_attestation","attest_author":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR/action/author_attestation","sign_citation":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR/action/citation_signature","submit_replication":"https://pith.science/pith/YJBREWYPZESSBWGS7APFSOBXAR/action/replication_record"}},"created_at":"2026-07-05T08:16:46.901251+00:00","updated_at":"2026-07-05T08:16:46.901251+00:00"}