{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HKO7VBALTSJKVVNWKSWLNHPOC7","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":"3c2425db511e3a19706dd8f7162ee612748c9f88e622d40c2060a7c6770c7665","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:32:57Z","title_canon_sha256":"d60f14c93a97d643695913cd9c5158dfe7e017ac22725969a02231457f4cf118"},"schema_version":"1.0","source":{"id":"2607.16210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16210","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16210v1","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16210","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"HKO7VBALTSJK","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"HKO7VBALTSJKVVNW","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"HKO7VBAL","created_at":"2026-07-21T00:20:05Z"}],"graph_snapshots":[{"event_id":"sha256:b6ea70df3f3f02bffbd3caa2c5b00f3be50f374f9427baa493e9675a1cb55f0c","target":"graph","created_at":"2026-07-21T00:20:05Z","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/2607.16210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment. Recent advances in policy expressiveness and scale have intensified this challenge, leading to a rapidly growing but conceptually fragmented body of work on RL policy verification. This survey provides a unifying perspective on RL verification methods. We introduce a taxonomy that clarifies relationships among existing approaches along three axes: verification paradigm (formal versus prob","authors_text":"Enrico Marchesini, Ezio Bartocci, Luca Marzari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:32:57Z","title":"A Survey on the Verification of Reinforcement Learning Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16210","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:e0e5c40bb8d39dd753cf81a699aad90bba49bdce33fad6612b3afa0f201f00ec","target":"record","created_at":"2026-07-21T00:20:05Z","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":"3c2425db511e3a19706dd8f7162ee612748c9f88e622d40c2060a7c6770c7665","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:32:57Z","title_canon_sha256":"d60f14c93a97d643695913cd9c5158dfe7e017ac22725969a02231457f4cf118"},"schema_version":"1.0","source":{"id":"2607.16210","kind":"arxiv","version":1}},"canonical_sha256":"3a9dfa840b9c92aad5b654acb69dee17c23467b4aa6ad91f9435373f50aeeb4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a9dfa840b9c92aad5b654acb69dee17c23467b4aa6ad91f9435373f50aeeb4a","first_computed_at":"2026-07-21T00:20:05.893484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:05.893484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIctHOsfuPRH0F3V6kRgnn1iwVXsotWBhCh/k7HlX4oKCwn2HILi66MbS7j2RusBWmF21e7vXZ7MmUTiGmkOCg==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:05.894422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0e5c40bb8d39dd753cf81a699aad90bba49bdce33fad6612b3afa0f201f00ec","sha256:b6ea70df3f3f02bffbd3caa2c5b00f3be50f374f9427baa493e9675a1cb55f0c"],"state_sha256":"75fab3621e5348a8468fa903bf3344b07972e57a73d78dcd60c4d7dd04fee5a2"}