{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YN7KHV4DFXOPFNGCAGUS5TGRW6","short_pith_number":"pith:YN7KHV4D","canonical_record":{"source":{"id":"2202.07789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T23:28:24Z","cross_cats_sorted":[],"title_canon_sha256":"9c76deaea9f7a9331c4b0dadc626d69b11a83518623b3a938d537b46cacf94e2","abstract_canon_sha256":"8479a44407df9759f0a1c00f4b4f4cd61c2ac198be1a34c816b75116c8972924"},"schema_version":"1.0"},"canonical_sha256":"c37ea3d7832ddcf2b4c201a92eccd1b798c618b1a3216b860b15648d2f5d0a48","source":{"kind":"arxiv","id":"2202.07789","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07789","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07789v1","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07789","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"YN7KHV4DFXOP","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_16","alias_value":"YN7KHV4DFXOPFNGC","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_8","alias_value":"YN7KHV4D","created_at":"2026-07-05T03:57:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YN7KHV4DFXOPFNGCAGUS5TGRW6","target":"record","payload":{"canonical_record":{"source":{"id":"2202.07789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T23:28:24Z","cross_cats_sorted":[],"title_canon_sha256":"9c76deaea9f7a9331c4b0dadc626d69b11a83518623b3a938d537b46cacf94e2","abstract_canon_sha256":"8479a44407df9759f0a1c00f4b4f4cd61c2ac198be1a34c816b75116c8972924"},"schema_version":"1.0"},"canonical_sha256":"c37ea3d7832ddcf2b4c201a92eccd1b798c618b1a3216b860b15648d2f5d0a48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:33.638655Z","signature_b64":"9FRWzrkkflw+yYHq3uz226eAsQzZmO/E6xD3P/yq0MixyMyFAd2raj3zWRIRKiMcihq91Y4+cR4ea87minu/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c37ea3d7832ddcf2b4c201a92eccd1b798c618b1a3216b860b15648d2f5d0a48","last_reissued_at":"2026-07-05T03:57:33.638227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:33.638227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.07789","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":"2026-07-05T03:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xk4zgb0IjId/+s7reVStaxLy7ux3U+3eDBCjKhoLsllJ29OMioisqgNYsVvvYRo720LvEfVmJpdEowA0MynQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:41:47.664602Z"},"content_sha256":"f6a79a41e08e94bfda7a1253b514b1ff207f2b6d054c4df7baac612b6fad2243","schema_version":"1.0","event_id":"sha256:f6a79a41e08e94bfda7a1253b514b1ff207f2b6d054c4df7baac612b6fad2243"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YN7KHV4DFXOPFNGCAGUS5TGRW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning by Imagining the Near Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Garrett Thomas, Tengyu Ma, Yuping Luo","submitted_at":"2022-02-15T23:28:24Z","abstract_excerpt":"Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. In this setting, a model-based agent with a sufficiently accurate model can avoid unsafe states. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07789","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/2202.07789/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":"2026-07-05T03:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBDJwntaluQMKzGEZSnAEh3SLIXHjjC2SQOwPuaKxnupN3UcDYVX7B1ajODLdPoq35qyhl2CkpxqHmb+klZQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:41:47.665535Z"},"content_sha256":"7e755f985f2b183291752f4beb039d531ad816d9a8c6e865da03b6ae48372d7f","schema_version":"1.0","event_id":"sha256:7e755f985f2b183291752f4beb039d531ad816d9a8c6e865da03b6ae48372d7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/bundle.json","state_url":"https://pith.science/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/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":"2026-08-16T14:41:47Z","links":{"resolver":"https://pith.science/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6","bundle":"https://pith.science/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/bundle.json","state":"https://pith.science/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YN7KHV4DFXOPFNGCAGUS5TGRW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YN7KHV4DFXOPFNGCAGUS5TGRW6","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":"8479a44407df9759f0a1c00f4b4f4cd61c2ac198be1a34c816b75116c8972924","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T23:28:24Z","title_canon_sha256":"9c76deaea9f7a9331c4b0dadc626d69b11a83518623b3a938d537b46cacf94e2"},"schema_version":"1.0","source":{"id":"2202.07789","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07789","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07789v1","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07789","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"YN7KHV4DFXOP","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_16","alias_value":"YN7KHV4DFXOPFNGC","created_at":"2026-07-05T03:57:33Z"},{"alias_kind":"pith_short_8","alias_value":"YN7KHV4D","created_at":"2026-07-05T03:57:33Z"}],"graph_snapshots":[{"event_id":"sha256:7e755f985f2b183291752f4beb039d531ad816d9a8c6e865da03b6ae48372d7f","target":"graph","created_at":"2026-07-05T03:57:33Z","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/2202.07789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. In this setting, a model-based agent with a sufficiently accurate model can avoid unsafe states. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstra","authors_text":"Garrett Thomas, Tengyu Ma, Yuping Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T23:28:24Z","title":"Safe Reinforcement Learning by Imagining the Near Future"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07789","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:f6a79a41e08e94bfda7a1253b514b1ff207f2b6d054c4df7baac612b6fad2243","target":"record","created_at":"2026-07-05T03:57:33Z","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":"8479a44407df9759f0a1c00f4b4f4cd61c2ac198be1a34c816b75116c8972924","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T23:28:24Z","title_canon_sha256":"9c76deaea9f7a9331c4b0dadc626d69b11a83518623b3a938d537b46cacf94e2"},"schema_version":"1.0","source":{"id":"2202.07789","kind":"arxiv","version":1}},"canonical_sha256":"c37ea3d7832ddcf2b4c201a92eccd1b798c618b1a3216b860b15648d2f5d0a48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c37ea3d7832ddcf2b4c201a92eccd1b798c618b1a3216b860b15648d2f5d0a48","first_computed_at":"2026-07-05T03:57:33.638227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:33.638227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9FRWzrkkflw+yYHq3uz226eAsQzZmO/E6xD3P/yq0MixyMyFAd2raj3zWRIRKiMcihq91Y4+cR4ea87minu/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:33.638655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07789","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6a79a41e08e94bfda7a1253b514b1ff207f2b6d054c4df7baac612b6fad2243","sha256:7e755f985f2b183291752f4beb039d531ad816d9a8c6e865da03b6ae48372d7f"],"state_sha256":"a2fe74d18304432d20049062ac602d3fe6bdb533c9c8c48cfdc22aee7be6998f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+trWLGTYcYCRfUcDNlRcr+AFWZH3YgYVu8GsTWLBRhPim2bcWYASE7+RBmF1tTWw0uzSYL2rodsFngxLYaBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T14:41:47.671756Z","bundle_sha256":"a05ee360ce997b9357302fb0f1cd5d8eb2ef6944367d9a25e1439fb558f96e5a"}}