{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EFAVD6SNKGEOAV3H5UDB3U67DU","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":"2c2639380e0ba72a90624d2b8d7b18665131d1ffc031955f31ddb2f06b37a22a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:51:04Z","title_canon_sha256":"3e6b2276e8a5e20f0a45cc7c06879ac3ee96a8119b63fa08ce48e839860ddfe8"},"schema_version":"1.0","source":{"id":"2009.12612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12612","created_at":"2026-07-05T01:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12612v2","created_at":"2026-07-05T01:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12612","created_at":"2026-07-05T01:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"EFAVD6SNKGEO","created_at":"2026-07-05T01:46:03Z"},{"alias_kind":"pith_short_16","alias_value":"EFAVD6SNKGEOAV3H","created_at":"2026-07-05T01:46:03Z"},{"alias_kind":"pith_short_8","alias_value":"EFAVD6SN","created_at":"2026-07-05T01:46:03Z"}],"graph_snapshots":[{"event_id":"sha256:4005284ac56e094477af7444d6c0884eb87e77d68ed892ebe690e2eeb4824567","target":"graph","created_at":"2026-07-05T01:46:03Z","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/2009.12612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neural networks within a learning loop is computationally infeasible. We address this challenge using two policy classes: a general, neurosymbolic class with approximate gradients and a more restricted class of symbolic policies that allows efficient verification. Our learning algorithm is a mirror descent over policies: in each iteration, it safely lifts a symbolic policy into the ","authors_text":"Abhinav Verma, Greg Anderson, Isil Dillig, Swarat Chaudhuri","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:51:04Z","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12612","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":"sha256:25c210f8c4aeaf24e4fca489d8cd6fc6c216995c6aacc2bf7859bdf4e9d6e9e8","target":"record","created_at":"2026-07-05T01:46:03Z","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":"2c2639380e0ba72a90624d2b8d7b18665131d1ffc031955f31ddb2f06b37a22a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:51:04Z","title_canon_sha256":"3e6b2276e8a5e20f0a45cc7c06879ac3ee96a8119b63fa08ce48e839860ddfe8"},"schema_version":"1.0","source":{"id":"2009.12612","kind":"arxiv","version":2}},"canonical_sha256":"214151fa4d5188e05767ed061dd3df1d1469e13abc5373ef8b188ae392a38c95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"214151fa4d5188e05767ed061dd3df1d1469e13abc5373ef8b188ae392a38c95","first_computed_at":"2026-07-05T01:46:03.002972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:46:03.002972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0UgADEe9rBCmR0xyGQe77PPl9tlVEjoS5mozSCCRfZYWDa4kYGBQycP8OEhmdh4FTQVZrP6vAzzFqiU8Qg2BCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:46:03.003540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25c210f8c4aeaf24e4fca489d8cd6fc6c216995c6aacc2bf7859bdf4e9d6e9e8","sha256:4005284ac56e094477af7444d6c0884eb87e77d68ed892ebe690e2eeb4824567"],"state_sha256":"e2e72e66caf5d09808091690db6cbe89c58c044759051020f94c34ab3fcb2a0c"}