{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EFAVD6SNKGEOAV3H5UDB3U67DU","short_pith_number":"pith:EFAVD6SN","canonical_record":{"source":{"id":"2009.12612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:51:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3e6b2276e8a5e20f0a45cc7c06879ac3ee96a8119b63fa08ce48e839860ddfe8","abstract_canon_sha256":"2c2639380e0ba72a90624d2b8d7b18665131d1ffc031955f31ddb2f06b37a22a"},"schema_version":"1.0"},"canonical_sha256":"214151fa4d5188e05767ed061dd3df1d1469e13abc5373ef8b188ae392a38c95","source":{"kind":"arxiv","id":"2009.12612","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EFAVD6SNKGEOAV3H5UDB3U67DU","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:51:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3e6b2276e8a5e20f0a45cc7c06879ac3ee96a8119b63fa08ce48e839860ddfe8","abstract_canon_sha256":"2c2639380e0ba72a90624d2b8d7b18665131d1ffc031955f31ddb2f06b37a22a"},"schema_version":"1.0"},"canonical_sha256":"214151fa4d5188e05767ed061dd3df1d1469e13abc5373ef8b188ae392a38c95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:03.003540Z","signature_b64":"0UgADEe9rBCmR0xyGQe77PPl9tlVEjoS5mozSCCRfZYWDa4kYGBQycP8OEhmdh4FTQVZrP6vAzzFqiU8Qg2BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"214151fa4d5188e05767ed061dd3df1d1469e13abc5373ef8b188ae392a38c95","last_reissued_at":"2026-07-05T01:46:03.002972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:03.002972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12612","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLFFzo8cWwsPvxlNd0lZSQ4JhphMxtr6FHO/5KvYJSICzY0OCW8md3KU1irhZ0PXpfQZVACI/GpwSN9u3e4KAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T23:33:52.505704Z"},"content_sha256":"25c210f8c4aeaf24e4fca489d8cd6fc6c216995c6aacc2bf7859bdf4e9d6e9e8","schema_version":"1.0","event_id":"sha256:25c210f8c4aeaf24e4fca489d8cd6fc6c216995c6aacc2bf7859bdf4e9d6e9e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EFAVD6SNKGEOAV3H5UDB3U67DU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Greg Anderson, Isil Dillig, Swarat Chaudhuri","submitted_at":"2020-09-26T14:51:04Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12612","kind":"arxiv","version":2},"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/2009.12612/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":"2026-07-05T01:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3ZmXpiXnY9VGPbBphXEGgoXpkHYX2T30LZyeFPKjJYC9tGHk6ixY/1ItymdYgld/4pi3lTkg07AMO43j1zfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T23:33:52.506254Z"},"content_sha256":"4005284ac56e094477af7444d6c0884eb87e77d68ed892ebe690e2eeb4824567","schema_version":"1.0","event_id":"sha256:4005284ac56e094477af7444d6c0884eb87e77d68ed892ebe690e2eeb4824567"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/bundle.json","state_url":"https://pith.science/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/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":"2026-08-20T23:33:52Z","links":{"resolver":"https://pith.science/pith/EFAVD6SNKGEOAV3H5UDB3U67DU","bundle":"https://pith.science/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/bundle.json","state":"https://pith.science/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFAVD6SNKGEOAV3H5UDB3U67DU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tSuRkC8GXAoQRQgUlTfjK9pMhSU75yBwKtYtxjgBjJNJZddLl1hXvG53xk9aFEcc2UJ1nszHaGb6RhapSMiGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T23:33:52.511391Z","bundle_sha256":"6a41fa0f90be79d245e3aac10b193855820927c2981c528aea9d466c8cad6c7c"}}