{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMSDKOHUBGWWKF6SBB55RDEDGQ","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":"8dd613e367901a3f2e254c97e60e2b2aa8c94e0e14228039823834f81eb93697","cross_cats_sorted":["cs.AI","math.DS","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-23T10:04:28Z","title_canon_sha256":"d4fa9dcf852956283a5a2589a028b48e6ce0f05c4dde9a5a3cfb481c9e6ac5a1"},"schema_version":"1.0","source":{"id":"2409.14867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14867","created_at":"2026-07-05T09:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14867v1","created_at":"2026-07-05T09:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14867","created_at":"2026-07-05T09:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"EMSDKOHUBGWW","created_at":"2026-07-05T09:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"EMSDKOHUBGWWKF6S","created_at":"2026-07-05T09:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"EMSDKOHU","created_at":"2026-07-05T09:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:8896084bd8d978b0434a7bd8edc8918a8fc0e47761193e599416d866638fb945","target":"graph","created_at":"2026-07-05T09:10:22Z","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/2409.14867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has been shown to be effective and convenient for a number of tasks in robotics. However, it requires the exploration of a sufficiently large number of state-action pairs, many of which may be unsafe or unimportant. For instance, online model-free learning can be hazardous and inefficient in the absence of guarantees that a certain set of desired states will be reached during an episode. An increasingly common approach to address safety involves the addition of a shielding system that constrains the RL actions to a safe set of actions. In turn, a difficulty for such","authors_text":"Dmitrii Dobriborsci, Grigory Yaremenko, Ngoc Quoc Huy Hoang, Pavel Osinenko, Roman Zashchitin, Ruben Contreras Maestre","cross_cats":["cs.AI","math.DS","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-23T10:04:28Z","title":"A novel agent with formal goal-reaching guarantees: an experimental study with a mobile robot"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14867","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":"sha256:0c8cb5baa2ab6838e1bc7aa63ac573256ff8a1cdff60f273c8c92dae621d25cf","target":"record","created_at":"2026-07-05T09:10:22Z","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":"8dd613e367901a3f2e254c97e60e2b2aa8c94e0e14228039823834f81eb93697","cross_cats_sorted":["cs.AI","math.DS","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-23T10:04:28Z","title_canon_sha256":"d4fa9dcf852956283a5a2589a028b48e6ce0f05c4dde9a5a3cfb481c9e6ac5a1"},"schema_version":"1.0","source":{"id":"2409.14867","kind":"arxiv","version":1}},"canonical_sha256":"23243538f409ad6517d2087bd88c8334237b9255ebbd96be9324cfa03fca0264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23243538f409ad6517d2087bd88c8334237b9255ebbd96be9324cfa03fca0264","first_computed_at":"2026-07-05T09:10:22.858092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:22.858092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WGYEIoNEo9X/Edj4gG+2DnosA3cGv5DF+4eWSjaII0UkcMFhrGSVbr9myZ+qRET+Tnbf3Py+fUWxAXRslqbYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:22.858579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c8cb5baa2ab6838e1bc7aa63ac573256ff8a1cdff60f273c8c92dae621d25cf","sha256:8896084bd8d978b0434a7bd8edc8918a8fc0e47761193e599416d866638fb945"],"state_sha256":"a91cd8a3c65ad340a5366e385f1a7a7b43650c91b41ddcff539972f4abefe105"}