{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZMG62VBIOXBKQC3GWKMMOSJKQR","short_pith_number":"pith:ZMG62VBI","canonical_record":{"source":{"id":"1902.05632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T22:36:54Z","cross_cats_sorted":[],"title_canon_sha256":"56b15c7f09557c4f34dff082570c609bb9840a5f7ce1c3f0bdc57c91cbd33b4e","abstract_canon_sha256":"7782053f6e063a07951838e47562ac427a3da21922d17ea2e11f3f1d38792021"},"schema_version":"1.0"},"canonical_sha256":"cb0ded542875c2a80b66b298c7492a84550b31f96e2f7d4e97850e6395acb555","source":{"kind":"arxiv","id":"1902.05632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05632","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05632v1","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05632","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZMG62VBIOXBK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZMG62VBIOXBKQC3G","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZMG62VBI","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZMG62VBIOXBKQC3GWKMMOSJKQR","target":"record","payload":{"canonical_record":{"source":{"id":"1902.05632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T22:36:54Z","cross_cats_sorted":[],"title_canon_sha256":"56b15c7f09557c4f34dff082570c609bb9840a5f7ce1c3f0bdc57c91cbd33b4e","abstract_canon_sha256":"7782053f6e063a07951838e47562ac427a3da21922d17ea2e11f3f1d38792021"},"schema_version":"1.0"},"canonical_sha256":"cb0ded542875c2a80b66b298c7492a84550b31f96e2f7d4e97850e6395acb555","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.628944Z","signature_b64":"RFLTebWkv+B8iw/o0cGnJEVglPBWCKjOzBsU3a/CixA6tmH/lyZkF7tlf8VIaN+QZuMA8icJgceBnNV4kmikAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb0ded542875c2a80b66b298c7492a84550b31f96e2f7d4e97850e6395acb555","last_reissued_at":"2026-05-17T23:44:21.628211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.628211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.05632","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":"2026-05-17T23:44:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1eJeyD54zYeAjslapP+Yd0p4k0b0jSnX0r2oJ5PKfwB9Fjnd4vL751XfqC+S5yhP3LGBsRcYuBWvat5HjEZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:13:01.891404Z"},"content_sha256":"8ef039ee6e3b96d5bc87ea52faa54322cc36ca4f8fc170db00d9020d0025066e","schema_version":"1.0","event_id":"sha256:8ef039ee6e3b96d5bc87ea52faa54322cc36ca4f8fc170db00d9020d0025066e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZMG62VBIOXBKQC3GWKMMOSJKQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Verifiably Safe Off-Model Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andre Platzer, Nathan Fulton","submitted_at":"2019-02-14T22:36:54Z","abstract_excerpt":"The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning or constrained optimization. Given a single correct model and associated safety constraint, these approaches guarantee efficient learning while provably avoiding behaviors outside the safety constraint. Acting well given an accurate environmental model is an important pre-requisite for safe learning, but is ultimately insufficient for systems tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05632","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":""},"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":"2026-05-17T23:44:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAKzeBDSSq9bD8d4aCGfZuQ6NmUem7gbdvkGFxrzdQ9H8b/s+pFYLIT9zADfsYmSMGOynSbH2YXHQEBaaNc6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:13:01.892034Z"},"content_sha256":"67499dd8b4f21c8e89d8eaa02ecc3731df88181a4c34b155d33f6c7608aeaec1","schema_version":"1.0","event_id":"sha256:67499dd8b4f21c8e89d8eaa02ecc3731df88181a4c34b155d33f6c7608aeaec1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/bundle.json","state_url":"https://pith.science/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/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":"2026-05-23T08:13:01Z","links":{"resolver":"https://pith.science/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR","bundle":"https://pith.science/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/bundle.json","state":"https://pith.science/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMG62VBIOXBKQC3GWKMMOSJKQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZMG62VBIOXBKQC3GWKMMOSJKQR","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":"7782053f6e063a07951838e47562ac427a3da21922d17ea2e11f3f1d38792021","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T22:36:54Z","title_canon_sha256":"56b15c7f09557c4f34dff082570c609bb9840a5f7ce1c3f0bdc57c91cbd33b4e"},"schema_version":"1.0","source":{"id":"1902.05632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05632","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05632v1","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05632","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZMG62VBIOXBK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZMG62VBIOXBKQC3G","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZMG62VBI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:67499dd8b4f21c8e89d8eaa02ecc3731df88181a4c34b155d33f6c7608aeaec1","target":"graph","created_at":"2026-05-17T23:44:21Z","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"},"paper":{"abstract_excerpt":"The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning or constrained optimization. Given a single correct model and associated safety constraint, these approaches guarantee efficient learning while provably avoiding behaviors outside the safety constraint. Acting well given an accurate environmental model is an important pre-requisite for safe learning, but is ultimately insufficient for systems tha","authors_text":"Andre Platzer, Nathan Fulton","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T22:36:54Z","title":"Verifiably Safe Off-Model Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05632","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":"sha256:8ef039ee6e3b96d5bc87ea52faa54322cc36ca4f8fc170db00d9020d0025066e","target":"record","created_at":"2026-05-17T23:44:21Z","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":"7782053f6e063a07951838e47562ac427a3da21922d17ea2e11f3f1d38792021","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T22:36:54Z","title_canon_sha256":"56b15c7f09557c4f34dff082570c609bb9840a5f7ce1c3f0bdc57c91cbd33b4e"},"schema_version":"1.0","source":{"id":"1902.05632","kind":"arxiv","version":1}},"canonical_sha256":"cb0ded542875c2a80b66b298c7492a84550b31f96e2f7d4e97850e6395acb555","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb0ded542875c2a80b66b298c7492a84550b31f96e2f7d4e97850e6395acb555","first_computed_at":"2026-05-17T23:44:21.628211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:21.628211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RFLTebWkv+B8iw/o0cGnJEVglPBWCKjOzBsU3a/CixA6tmH/lyZkF7tlf8VIaN+QZuMA8icJgceBnNV4kmikAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:21.628944Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ef039ee6e3b96d5bc87ea52faa54322cc36ca4f8fc170db00d9020d0025066e","sha256:67499dd8b4f21c8e89d8eaa02ecc3731df88181a4c34b155d33f6c7608aeaec1"],"state_sha256":"2d6c23a56e6b70aeb45ee67f6f9624534eb62dce013dd0b210767befa0283ccf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+EyjLnyiV3qzx/6PGijGeAZe5Fo4pO9G49tEHfTUc7/wcypp3SiB5Awj01K3c6/ccRoWb0VeJ7gFYW5LuiwcCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T08:13:01.895635Z","bundle_sha256":"120ff6713ae7854d5cc0c69354539e542942db05f49dd04bec463dd239331e75"}}