{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KLFSVBUNWHRE7YBNVEOESTCCZF","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":"e45f0502b57a31b521587a069f7ca4e56827c13752ad6621e1afada506877b2f","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-12-13T01:28:59Z","title_canon_sha256":"a2ec73d401276a4c5a703e3c9be1abf0cd3c612b09a5a00f31bcb8535b79b6cf"},"schema_version":"1.0","source":{"id":"2312.07828","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07828","created_at":"2026-07-05T09:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07828v2","created_at":"2026-07-05T09:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07828","created_at":"2026-07-05T09:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"KLFSVBUNWHRE","created_at":"2026-07-05T09:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"KLFSVBUNWHRE7YBN","created_at":"2026-07-05T09:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"KLFSVBUN","created_at":"2026-07-05T09:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:4b12dc101809de026370c907655d14a3516384ce8091177b68aa8e9b309d7419","target":"graph","created_at":"2026-07-05T09:45:42Z","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/2312.07828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces the reinforcement learning backup shield (RLBUS), an algorithm that guarantees safe exploration in reinforcement learning (RL) by incorporating backup control barrier functions (BCBFs). RLBUS constructs an implicit control forward invariant subset of the safe set using multiple backup policies, ensuring safety in the presence of input constraints. While traditional BCBFs often result in conservative control forward-invariant sets due to the design of backup controllers, RLBUS addresses this limitation by leveraging model-free RL to train an additional backup policy, which","authors_text":"Amirsaeid Safari, Pedram Rabiee","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-12-13T01:28:59Z","title":"Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training Time Safety Violations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07828","kind":"arxiv","version":2},"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":"sha256:332dcd29f156625d1e54c4613582f2b9226f38b9467d92c7a06319c1e23b9bed","target":"record","created_at":"2026-07-05T09:45:42Z","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":"e45f0502b57a31b521587a069f7ca4e56827c13752ad6621e1afada506877b2f","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-12-13T01:28:59Z","title_canon_sha256":"a2ec73d401276a4c5a703e3c9be1abf0cd3c612b09a5a00f31bcb8535b79b6cf"},"schema_version":"1.0","source":{"id":"2312.07828","kind":"arxiv","version":2}},"canonical_sha256":"52cb2a868db1e24fe02da91c494c42c97598fd1f75c5e236aab3e396054eef1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52cb2a868db1e24fe02da91c494c42c97598fd1f75c5e236aab3e396054eef1f","first_computed_at":"2026-07-05T09:45:42.422369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:42.422369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bJB/Bb9YTQ8ACicrQKAHerlizIfhnaB7TjK7B4VUw5fXqnobDV3BkWh0xJkHVZzw2IBa5GczOhaAGm8+PkhyBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:42.422805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07828","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:332dcd29f156625d1e54c4613582f2b9226f38b9467d92c7a06319c1e23b9bed","sha256:4b12dc101809de026370c907655d14a3516384ce8091177b68aa8e9b309d7419"],"state_sha256":"19097e73641d2e832b4103437bc49213effd1280e401006c48929b4f438b4611"}