{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZCBBJTLJQL55XV6PLNJKUOANHA","short_pith_number":"pith:ZCBBJTLJ","schema_version":"1.0","canonical_sha256":"c88214cd6982fbdbd7cf5b52aa380d3810e59f3c5954966365873bd8e76abcb7","source":{"kind":"arxiv","id":"2606.22509","version":1},"attestation_state":"computed","paper":{"title":"Imagine to Ensure Safety in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aleksandr I. Panov, Artem Latyshev, Gregory Gorbov","submitted_at":"2026-06-21T14:04:04Z","abstract_excerpt":"This work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints. This challenge becomes even more pronounced in long-horizon tasks, where existing safe methods face fundamental limitations due to compounding estimation errors and restricted exploration capabilities. To address this problem, we propose a method that combines a learnable world model with two complementary policies a high-level policy and a low-level policy to promote safety at both hierarchical levels. The high-l"},"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":"2606.22509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-21T14:04:04Z","cross_cats_sorted":[],"title_canon_sha256":"ebef2cef7b1327195b98643d625ce348ace350e5b43f66f6f47fe717eeef05a2","abstract_canon_sha256":"939218df826215099dfacd720e57b0a759ec7418b53f3a8c2a7a0269cef6c41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:40.418431Z","signature_b64":"34V/dIV2pPH13eAwzE2x6lhWh+3ApE4U14JBCtKIr9YpE/Qelck0MBdhFYEj2RMWI5rFGTyV8EJMDcGrZBBuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c88214cd6982fbdbd7cf5b52aa380d3810e59f3c5954966365873bd8e76abcb7","last_reissued_at":"2026-06-23T02:13:40.418051Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:40.418051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imagine to Ensure Safety in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aleksandr I. Panov, Artem Latyshev, Gregory Gorbov","submitted_at":"2026-06-21T14:04:04Z","abstract_excerpt":"This work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints. This challenge becomes even more pronounced in long-horizon tasks, where existing safe methods face fundamental limitations due to compounding estimation errors and restricted exploration capabilities. To address this problem, we propose a method that combines a learnable world model with two complementary policies a high-level policy and a low-level policy to promote safety at both hierarchical levels. The high-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22509","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/2606.22509/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":"2606.22509","created_at":"2026-06-23T02:13:40.418115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22509v1","created_at":"2026-06-23T02:13:40.418115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22509","created_at":"2026-06-23T02:13:40.418115+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCBBJTLJQL55","created_at":"2026-06-23T02:13:40.418115+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCBBJTLJQL55XV6P","created_at":"2026-06-23T02:13:40.418115+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCBBJTLJ","created_at":"2026-06-23T02:13:40.418115+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/ZCBBJTLJQL55XV6PLNJKUOANHA","json":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA.json","graph_json":"https://pith.science/api/pith-number/ZCBBJTLJQL55XV6PLNJKUOANHA/graph.json","events_json":"https://pith.science/api/pith-number/ZCBBJTLJQL55XV6PLNJKUOANHA/events.json","paper":"https://pith.science/paper/ZCBBJTLJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA","download_json":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA.json","view_paper":"https://pith.science/paper/ZCBBJTLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22509&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCBBJTLJQL55XV6PLNJKUOANHA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCBBJTLJQL55XV6PLNJKUOANHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA/action/storage_attestation","attest_author":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA/action/author_attestation","sign_citation":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA/action/citation_signature","submit_replication":"https://pith.science/pith/ZCBBJTLJQL55XV6PLNJKUOANHA/action/replication_record"}},"created_at":"2026-06-23T02:13:40.418115+00:00","updated_at":"2026-06-23T02:13:40.418115+00:00"}