{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z6LFDTI3BIYY5QQEHE3ED7CX6N","short_pith_number":"pith:Z6LFDTI3","canonical_record":{"source":{"id":"2010.15920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T20:10:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3668f057f1fdbdcc159f57da3d633507c745279f53f9926d60d112292c9833ca","abstract_canon_sha256":"4fc17e174ff3595650424b05994ecd8279afe8b2b561ef3cc282b416af2cc01e"},"schema_version":"1.0"},"canonical_sha256":"cf9651cd1b0a318ec204393641fc57f367abe87d38cf32e32d584466e550317d","source":{"kind":"arxiv","id":"2010.15920","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.15920","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"2010.15920v2","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15920","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"Z6LFDTI3BIYY","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_16","alias_value":"Z6LFDTI3BIYY5QQE","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_8","alias_value":"Z6LFDTI3","created_at":"2026-07-05T02:40:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z6LFDTI3BIYY5QQEHE3ED7CX6N","target":"record","payload":{"canonical_record":{"source":{"id":"2010.15920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T20:10:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3668f057f1fdbdcc159f57da3d633507c745279f53f9926d60d112292c9833ca","abstract_canon_sha256":"4fc17e174ff3595650424b05994ecd8279afe8b2b561ef3cc282b416af2cc01e"},"schema_version":"1.0"},"canonical_sha256":"cf9651cd1b0a318ec204393641fc57f367abe87d38cf32e32d584466e550317d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:49.625790Z","signature_b64":"M9fv8Qrhvv+Y1V7i/udn4AKbHiRG14XSBQ+Wt8gFvOdy5cNEeulm6tPeURacfhiQV9mOqAIxr5RQvKh8lNI6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf9651cd1b0a318ec204393641fc57f367abe87d38cf32e32d584466e550317d","last_reissued_at":"2026-07-05T02:40:49.625260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:49.625260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.15920","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":"2026-07-05T02:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKcQUBHMa0Q/ekcC0xWCmWWlvzELxVKesmqloWY15OgAqJoC87vUxF0LXsxIVAl0Fzy3u1zNBn96fUKayPS5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:34:56.145185Z"},"content_sha256":"6574d30c9ca6ac35bf0f2aab1615cda4f212017f1297a6430b8f39af96a37ce4","schema_version":"1.0","event_id":"sha256:6574d30c9ca6ac35bf0f2aab1615cda4f212017f1297a6430b8f39af96a37ce4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z6LFDTI3BIYY5QQEHE3ED7CX6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ashwin Balakrishna, Brijen Thananjeyan, Chelsea Finn, Joseph E. Gonzalez, Julian Ibarz, Ken Goldberg, Krishnan Srinivasan, Michael Luo, Minho Hwang, Suraj Nair","submitted_at":"2020-10-29T20:10:02Z","abstract_excerpt":"Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint viola"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15920","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/2010.15920/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":"2026-07-05T02:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lA9NQr3cFykLVkVaxNzbMd3ilHL6DR1vhNaL7z+RAvNZWsig1An1MuK8Xi4/O3OHgRnosNK68UHadZyil8QcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:34:56.145570Z"},"content_sha256":"fcdc9f7b05707d10627745d5a66e29de580eabb4b8b5bcd6d555b24bc60001ad","schema_version":"1.0","event_id":"sha256:fcdc9f7b05707d10627745d5a66e29de580eabb4b8b5bcd6d555b24bc60001ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/bundle.json","state_url":"https://pith.science/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/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":"2026-07-08T04:34:56Z","links":{"resolver":"https://pith.science/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N","bundle":"https://pith.science/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/bundle.json","state":"https://pith.science/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6LFDTI3BIYY5QQEHE3ED7CX6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z6LFDTI3BIYY5QQEHE3ED7CX6N","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":"4fc17e174ff3595650424b05994ecd8279afe8b2b561ef3cc282b416af2cc01e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T20:10:02Z","title_canon_sha256":"3668f057f1fdbdcc159f57da3d633507c745279f53f9926d60d112292c9833ca"},"schema_version":"1.0","source":{"id":"2010.15920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.15920","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"2010.15920v2","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15920","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"Z6LFDTI3BIYY","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_16","alias_value":"Z6LFDTI3BIYY5QQE","created_at":"2026-07-05T02:40:49Z"},{"alias_kind":"pith_short_8","alias_value":"Z6LFDTI3","created_at":"2026-07-05T02:40:49Z"}],"graph_snapshots":[{"event_id":"sha256:fcdc9f7b05707d10627745d5a66e29de580eabb4b8b5bcd6d555b24bc60001ad","target":"graph","created_at":"2026-07-05T02:40:49Z","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/2010.15920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint viola","authors_text":"Ashwin Balakrishna, Brijen Thananjeyan, Chelsea Finn, Joseph E. Gonzalez, Julian Ibarz, Ken Goldberg, Krishnan Srinivasan, Michael Luo, Minho Hwang, Suraj Nair","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T20:10:02Z","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15920","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":"sha256:6574d30c9ca6ac35bf0f2aab1615cda4f212017f1297a6430b8f39af96a37ce4","target":"record","created_at":"2026-07-05T02:40:49Z","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":"4fc17e174ff3595650424b05994ecd8279afe8b2b561ef3cc282b416af2cc01e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T20:10:02Z","title_canon_sha256":"3668f057f1fdbdcc159f57da3d633507c745279f53f9926d60d112292c9833ca"},"schema_version":"1.0","source":{"id":"2010.15920","kind":"arxiv","version":2}},"canonical_sha256":"cf9651cd1b0a318ec204393641fc57f367abe87d38cf32e32d584466e550317d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf9651cd1b0a318ec204393641fc57f367abe87d38cf32e32d584466e550317d","first_computed_at":"2026-07-05T02:40:49.625260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:49.625260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M9fv8Qrhvv+Y1V7i/udn4AKbHiRG14XSBQ+Wt8gFvOdy5cNEeulm6tPeURacfhiQV9mOqAIxr5RQvKh8lNI6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:49.625790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.15920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6574d30c9ca6ac35bf0f2aab1615cda4f212017f1297a6430b8f39af96a37ce4","sha256:fcdc9f7b05707d10627745d5a66e29de580eabb4b8b5bcd6d555b24bc60001ad"],"state_sha256":"447afe3eb45508db26abe2afd16f39e4143cd3c29663cc5afe6efe23f7e84ddc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KG/Ddsy076GgUnPpG0M4/AQ9+mL9KUNGpcJqcLN3e+tduzCkgNQFgra7E3DPu07ZrRy0kslRLUDute5WtB/iDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T04:34:56.148147Z","bundle_sha256":"b7c9f5b4fe463b31cee0f9b7f65d84ff2a81c3ae3a63545a3f0977c3ef234c22"}}