{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HKO7VBALTSJKVVNWKSWLNHPOC7","short_pith_number":"pith:HKO7VBAL","canonical_record":{"source":{"id":"2607.16210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:32:57Z","cross_cats_sorted":[],"title_canon_sha256":"d60f14c93a97d643695913cd9c5158dfe7e017ac22725969a02231457f4cf118","abstract_canon_sha256":"3c2425db511e3a19706dd8f7162ee612748c9f88e622d40c2060a7c6770c7665"},"schema_version":"1.0"},"canonical_sha256":"3a9dfa840b9c92aad5b654acb69dee17c23467b4aa6ad91f9435373f50aeeb4a","source":{"kind":"arxiv","id":"2607.16210","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HKO7VBALTSJKVVNWKSWLNHPOC7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:32:57Z","cross_cats_sorted":[],"title_canon_sha256":"d60f14c93a97d643695913cd9c5158dfe7e017ac22725969a02231457f4cf118","abstract_canon_sha256":"3c2425db511e3a19706dd8f7162ee612748c9f88e622d40c2060a7c6770c7665"},"schema_version":"1.0"},"canonical_sha256":"3a9dfa840b9c92aad5b654acb69dee17c23467b4aa6ad91f9435373f50aeeb4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:05.894422Z","signature_b64":"RIctHOsfuPRH0F3V6kRgnn1iwVXsotWBhCh/k7HlX4oKCwn2HILi66MbS7j2RusBWmF21e7vXZ7MmUTiGmkOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9dfa840b9c92aad5b654acb69dee17c23467b4aa6ad91f9435373f50aeeb4a","last_reissued_at":"2026-07-21T00:20:05.893484Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:05.893484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16210","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T00:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LW3yYhc1JXaZcDA1HwZ4gHQubp7ZR5WOInyTN7ehConaMU78GhX0NnFwyq6j0T3DGC5S4WXDhQDTLpqgxeFFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:21:58.339059Z"},"content_sha256":"e0e5c40bb8d39dd753cf81a699aad90bba49bdce33fad6612b3afa0f201f00ec","schema_version":"1.0","event_id":"sha256:e0e5c40bb8d39dd753cf81a699aad90bba49bdce33fad6612b3afa0f201f00ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HKO7VBALTSJKVVNWKSWLNHPOC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on the Verification of Reinforcement Learning Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Enrico Marchesini, Ezio Bartocci, Luca Marzari","submitted_at":"2026-05-14T12:32:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16210","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/2607.16210/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T00:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uR6m7Ph5Ip20RtYD77vuCKuC5cZWe096mkk6eHhMkPyhz1FtY8oK8y9y+TjC5I2SBfeXtk6XE3MSPkkrh1XmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:21:58.339937Z"},"content_sha256":"b6ea70df3f3f02bffbd3caa2c5b00f3be50f374f9427baa493e9675a1cb55f0c","schema_version":"1.0","event_id":"sha256:b6ea70df3f3f02bffbd3caa2c5b00f3be50f374f9427baa493e9675a1cb55f0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/bundle.json","state_url":"https://pith.science/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T16:21:58Z","links":{"resolver":"https://pith.science/pith/HKO7VBALTSJKVVNWKSWLNHPOC7","bundle":"https://pith.science/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/bundle.json","state":"https://pith.science/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKO7VBALTSJKVVNWKSWLNHPOC7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBYWYEO6JfFu/Sem9tso3/RAuKquxuSToskms+gP7C+URQxOM28eN1z19FzBZ402RTLHA0Do9O/a0ibS12dCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:21:58.346925Z","bundle_sha256":"1f5554e1aa5ceb6c5f77004efc3270c7a0ae7aa745da667a7a8c2dba981319f2"}}