{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SB75YY52HA7ZALUTXFZXUP6MRD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"022a3a92e8fd96376c2c14f07898bedfbce9665b4fde9c1e9f1c3ff5d6795453","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T15:20:55Z","title_canon_sha256":"044ca894bc3a96088ea0fc0577ccbee57598acd7637fbdb99c47ab8af77ff392"},"schema_version":"1.0","source":{"id":"2104.06922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06922","created_at":"2026-07-05T02:32:11Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06922v1","created_at":"2026-07-05T02:32:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06922","created_at":"2026-07-05T02:32:11Z"},{"alias_kind":"pith_short_12","alias_value":"SB75YY52HA7Z","created_at":"2026-07-05T02:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"SB75YY52HA7ZALUT","created_at":"2026-07-05T02:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"SB75YY52","created_at":"2026-07-05T02:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:09d08c0d8ed54ff4c446b961035b3d90874b89cd287e0680d04d701b44f479a1","target":"graph","created_at":"2026-07-05T02:32:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.06922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast to the traditional RL objective, safe exploration considers the maximization of expected returns under safety constraints expressed in expected cost returns. We introduce a model-based safe exploration algorithm for constrained high-dimensional control to address the often prohibitively high sample complexity of model-free safe exploration algorithms. Furthe","authors_text":"J. Marius Z\\\"ollner, Karam Daaboul, Moritz A. Zanger","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T15:20:55Z","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06922","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cad1d26b5b7b476fffbfe237b2c5f5b6ac75b082b0a0fef1947583c8311b9fa9","target":"record","created_at":"2026-07-05T02:32:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"022a3a92e8fd96376c2c14f07898bedfbce9665b4fde9c1e9f1c3ff5d6795453","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T15:20:55Z","title_canon_sha256":"044ca894bc3a96088ea0fc0577ccbee57598acd7637fbdb99c47ab8af77ff392"},"schema_version":"1.0","source":{"id":"2104.06922","kind":"arxiv","version":1}},"canonical_sha256":"907fdc63ba383f902e93b9737a3fcc88ddc0b86fde6f91a0b2791a978e79d7d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"907fdc63ba383f902e93b9737a3fcc88ddc0b86fde6f91a0b2791a978e79d7d1","first_computed_at":"2026-07-05T02:32:11.084596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:11.084596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gJbNsRXHe4lwNqpR4F8IHrsNpqikLGj0mhbSM7i4gmPjEFOk7NGqtfpturlviZOg6dT5XQE4M8VJbhZ8JtuzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:11.085128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cad1d26b5b7b476fffbfe237b2c5f5b6ac75b082b0a0fef1947583c8311b9fa9","sha256:09d08c0d8ed54ff4c446b961035b3d90874b89cd287e0680d04d701b44f479a1"],"state_sha256":"4fb9f8fed78cf83c8959234db68a2f705a4f141338b158986315dc318c24a235"}