{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CB64UDTSHVN2HB6FSYMBVSUN6Q","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":"d59d69804485cb41c1a6fa8f65c9dc67037bba4b38c167e2714ce1ba947dfd99","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T20:53:20Z","title_canon_sha256":"4259f9175dc4a8b8fee05d1c737b12d98341d06a1e25d50c3151343c1d4c9309"},"schema_version":"1.0","source":{"id":"2010.14603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14603","created_at":"2026-07-05T01:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14603v1","created_at":"2026-07-05T01:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14603","created_at":"2026-07-05T01:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"CB64UDTSHVN2","created_at":"2026-07-05T01:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"CB64UDTSHVN2HB6F","created_at":"2026-07-05T01:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"CB64UDTS","created_at":"2026-07-05T01:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:c1712e663937bc7b30a88154912366e40a70b2e3307d70b841b7f404a98b5ed5","target":"graph","created_at":"2026-07-05T01:47:16Z","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/2010.14603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on the policy's behavior. However, just as learning has enabled progress in large-scale development of AI systems, learning safety specifications may also be necessary to ensure safety in messy open-world environments where manual safety specifications cannot scale. Akin to how humans learn incrementally starting in child-safe environments, we propose to learn","authors_text":"Benjamin Eysenbach, Chelsea Finn, Jie Tan, Krishnan Srinivasan, Sehoon Ha","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T20:53:20Z","title":"Learning to be Safe: Deep RL with a Safety Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14603","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":"sha256:69bb315361fcbefca99bc3f049478e442cbfe018c5b641bb3c52e94c350fd6f5","target":"record","created_at":"2026-07-05T01:47:16Z","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":"d59d69804485cb41c1a6fa8f65c9dc67037bba4b38c167e2714ce1ba947dfd99","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T20:53:20Z","title_canon_sha256":"4259f9175dc4a8b8fee05d1c737b12d98341d06a1e25d50c3151343c1d4c9309"},"schema_version":"1.0","source":{"id":"2010.14603","kind":"arxiv","version":1}},"canonical_sha256":"107dca0e723d5ba387c596181aca8df43ee220986d8437bfd7001c83db8447bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"107dca0e723d5ba387c596181aca8df43ee220986d8437bfd7001c83db8447bf","first_computed_at":"2026-07-05T01:47:16.812960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:16.812960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C9cTWcX7uZTkqcqoojKaGjCfrgNoNDD3wBFxas0v0vp6uJ2tyJ95nbsNmr1mmk8FYKl8dBskJQ0hnpF5YG71Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:16.813429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69bb315361fcbefca99bc3f049478e442cbfe018c5b641bb3c52e94c350fd6f5","sha256:c1712e663937bc7b30a88154912366e40a70b2e3307d70b841b7f404a98b5ed5"],"state_sha256":"b8569c5256bff110c9d1468fea406c3bc5eac13f224b2af55768af63508a648d"}