{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UC3RTVPWC3M6LKXMTY7PV57PRO","short_pith_number":"pith:UC3RTVPW","canonical_record":{"source":{"id":"2112.03575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T08:57:35Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d9922db397c20ca9c85f5b11f742375b2337bb0358ae19dbbb5407d2d3d32804","abstract_canon_sha256":"4203d55577328a6937fe097dd2da3d89130effe5b34e5b8416414ec719d967f3"},"schema_version":"1.0"},"canonical_sha256":"a0b719d5f616d9e5aaec9e3efaf7ef8bbd616728711188c97b94f9b0f06974e2","source":{"kind":"arxiv","id":"2112.03575","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03575","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03575v1","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03575","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"UC3RTVPWC3M6","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"UC3RTVPWC3M6LKXM","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"UC3RTVPW","created_at":"2026-07-05T03:38:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UC3RTVPWC3M6LKXMTY7PV57PRO","target":"record","payload":{"canonical_record":{"source":{"id":"2112.03575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T08:57:35Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d9922db397c20ca9c85f5b11f742375b2337bb0358ae19dbbb5407d2d3d32804","abstract_canon_sha256":"4203d55577328a6937fe097dd2da3d89130effe5b34e5b8416414ec719d967f3"},"schema_version":"1.0"},"canonical_sha256":"a0b719d5f616d9e5aaec9e3efaf7ef8bbd616728711188c97b94f9b0f06974e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:46.980178Z","signature_b64":"Go2na+nFI0ndSq5ZOCM84paP+oY+jGagG1PiDw1DSZ3V7kII+EXiQEe7REOmaaAh+ey4Frn46wl8lhz3lvYhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0b719d5f616d9e5aaec9e3efaf7ef8bbd616728711188c97b94f9b0f06974e2","last_reissued_at":"2026-07-05T03:38:46.979798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:46.979798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.03575","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":"2026-07-05T03:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SSpBPQzLzK0GDzqWKGgHQNom0SvoEfRcsJ48T7TCfonjxRv4Q4jS5pidG7yVHlBC4E5vOWxR3yJymKPGUCZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:19:10.381686Z"},"content_sha256":"35fb3b9a7723b78e37afb540a52570dfe77af1e01227805745660b003dba6f01","schema_version":"1.0","event_id":"sha256:35fb3b9a7723b78e37afb540a52570dfe77af1e01227805745660b003dba6f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UC3RTVPWC3M6LKXMTY7PV57PRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ashwin Balakrishna, Brijen Thananjeyan, Chelsea Finn, Ion Stoica, Jie Tan, Julian Ibarz, Ken Goldberg, Michael Luo, Suraj Nair","submitted_at":"2021-12-07T08:57:35Z","abstract_excerpt":"Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03575","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/2112.03575/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":"2026-07-05T03:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+09BUp44FAgh+JUIYHFOQEk1xzelwM3jxr4RJKQp3M7Bf9tAg0OsfDNLALJYxzU93P2ESNWCT+nORmdy3yknCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:19:10.382187Z"},"content_sha256":"85ff2e279b74b9671dc4ef5237f003ec1cf1b71ae5cbcb4f5afc1a325b274f9d","schema_version":"1.0","event_id":"sha256:85ff2e279b74b9671dc4ef5237f003ec1cf1b71ae5cbcb4f5afc1a325b274f9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/bundle.json","state_url":"https://pith.science/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/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":"2026-08-12T13:19:10Z","links":{"resolver":"https://pith.science/pith/UC3RTVPWC3M6LKXMTY7PV57PRO","bundle":"https://pith.science/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/bundle.json","state":"https://pith.science/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UC3RTVPWC3M6LKXMTY7PV57PRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UC3RTVPWC3M6LKXMTY7PV57PRO","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":"4203d55577328a6937fe097dd2da3d89130effe5b34e5b8416414ec719d967f3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T08:57:35Z","title_canon_sha256":"d9922db397c20ca9c85f5b11f742375b2337bb0358ae19dbbb5407d2d3d32804"},"schema_version":"1.0","source":{"id":"2112.03575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03575","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03575v1","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03575","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"UC3RTVPWC3M6","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"UC3RTVPWC3M6LKXM","created_at":"2026-07-05T03:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"UC3RTVPW","created_at":"2026-07-05T03:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:85ff2e279b74b9671dc4ef5237f003ec1cf1b71ae5cbcb4f5afc1a325b274f9d","target":"graph","created_at":"2026-07-05T03:38:46Z","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/2112.03575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a ran","authors_text":"Ashwin Balakrishna, Brijen Thananjeyan, Chelsea Finn, Ion Stoica, Jie Tan, Julian Ibarz, Ken Goldberg, Michael Luo, Suraj Nair","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T08:57:35Z","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03575","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":"sha256:35fb3b9a7723b78e37afb540a52570dfe77af1e01227805745660b003dba6f01","target":"record","created_at":"2026-07-05T03:38:46Z","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":"4203d55577328a6937fe097dd2da3d89130effe5b34e5b8416414ec719d967f3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T08:57:35Z","title_canon_sha256":"d9922db397c20ca9c85f5b11f742375b2337bb0358ae19dbbb5407d2d3d32804"},"schema_version":"1.0","source":{"id":"2112.03575","kind":"arxiv","version":1}},"canonical_sha256":"a0b719d5f616d9e5aaec9e3efaf7ef8bbd616728711188c97b94f9b0f06974e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0b719d5f616d9e5aaec9e3efaf7ef8bbd616728711188c97b94f9b0f06974e2","first_computed_at":"2026-07-05T03:38:46.979798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:46.979798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Go2na+nFI0ndSq5ZOCM84paP+oY+jGagG1PiDw1DSZ3V7kII+EXiQEe7REOmaaAh+ey4Frn46wl8lhz3lvYhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:46.980178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35fb3b9a7723b78e37afb540a52570dfe77af1e01227805745660b003dba6f01","sha256:85ff2e279b74b9671dc4ef5237f003ec1cf1b71ae5cbcb4f5afc1a325b274f9d"],"state_sha256":"c59acc12c10de5bc5f913edde69d55b34de58e91b29738ed1f825aa3f06d7c0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6S+HPldKV4N6PBV+IaWLAF8k5+ulNt7t51sxR7KFZ2RUbFGYTK5o9ycQQAaGoDn1U4vx6aNtIQ3Szl+T+kR2DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:19:10.386615Z","bundle_sha256":"fd56da0833f8b906113a4280d29b1963ab1eda930d07073a52b8037948aa8b5a"}}