{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CB64UDTSHVN2HB6FSYMBVSUN6Q","short_pith_number":"pith:CB64UDTS","canonical_record":{"source":{"id":"2010.14603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T20:53:20Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4259f9175dc4a8b8fee05d1c737b12d98341d06a1e25d50c3151343c1d4c9309","abstract_canon_sha256":"d59d69804485cb41c1a6fa8f65c9dc67037bba4b38c167e2714ce1ba947dfd99"},"schema_version":"1.0"},"canonical_sha256":"107dca0e723d5ba387c596181aca8df43ee220986d8437bfd7001c83db8447bf","source":{"kind":"arxiv","id":"2010.14603","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CB64UDTSHVN2HB6FSYMBVSUN6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2010.14603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T20:53:20Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4259f9175dc4a8b8fee05d1c737b12d98341d06a1e25d50c3151343c1d4c9309","abstract_canon_sha256":"d59d69804485cb41c1a6fa8f65c9dc67037bba4b38c167e2714ce1ba947dfd99"},"schema_version":"1.0"},"canonical_sha256":"107dca0e723d5ba387c596181aca8df43ee220986d8437bfd7001c83db8447bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:16.813429Z","signature_b64":"C9cTWcX7uZTkqcqoojKaGjCfrgNoNDD3wBFxas0v0vp6uJ2tyJ95nbsNmr1mmk8FYKl8dBskJQ0hnpF5YG71Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107dca0e723d5ba387c596181aca8df43ee220986d8437bfd7001c83db8447bf","last_reissued_at":"2026-07-05T01:47:16.812960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:16.812960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.14603","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":"2026-07-05T01:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbh4HaMjqCQpbM5mvReRbVgK8y7d+6WTMl0Hr21abChCmv4F1HE/iyFOrFiQvtmm+jH64cb96x+nBNKZbfUqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:32:19.649488Z"},"content_sha256":"69bb315361fcbefca99bc3f049478e442cbfe018c5b641bb3c52e94c350fd6f5","schema_version":"1.0","event_id":"sha256:69bb315361fcbefca99bc3f049478e442cbfe018c5b641bb3c52e94c350fd6f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CB64UDTSHVN2HB6FSYMBVSUN6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to be Safe: Deep RL with a Safety Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Chelsea Finn, Jie Tan, Krishnan Srinivasan, Sehoon Ha","submitted_at":"2020-10-27T20:53:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14603","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/2010.14603/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":"2026-07-05T01:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXeVL7YFyzN9SjCzi31Jcjthb2e6ef8OZtD+eK7JwnSGEjvpXZv3lrHCyyT8RbHQVZ+8lGhJuVLdEzcPChIcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:32:19.650403Z"},"content_sha256":"c1712e663937bc7b30a88154912366e40a70b2e3307d70b841b7f404a98b5ed5","schema_version":"1.0","event_id":"sha256:c1712e663937bc7b30a88154912366e40a70b2e3307d70b841b7f404a98b5ed5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/bundle.json","state_url":"https://pith.science/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/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":"2026-08-08T06:32:19Z","links":{"resolver":"https://pith.science/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q","bundle":"https://pith.science/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/bundle.json","state":"https://pith.science/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CB64UDTSHVN2HB6FSYMBVSUN6Q/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBnCq6LAMzR+SP1HJ75GUscQK66A9mmXu1w4cN6MsViEfYm09EVKAr+cJkl1vqfjbsPkbhprcESGEEDIxG1CBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:32:19.655527Z","bundle_sha256":"b454f7aaf7dc0ee4589cbdeb1cf6f0ee7185a7b17df3d53a2e8c25c877b8897c"}}