{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WLDHGRFIIS6AIBC7XC67JNEVEJ","short_pith_number":"pith:WLDHGRFI","canonical_record":{"source":{"id":"2112.07701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T19:09:14Z","cross_cats_sorted":[],"title_canon_sha256":"776d510ca6c019d38692d024824d69df8bc7a84d817f03be633c2e02321baa3b","abstract_canon_sha256":"254dcd67c8cbebb0d5400bd4ad00f99ab9cafcf913c847895f214a7a79f0345c"},"schema_version":"1.0"},"canonical_sha256":"b2c67344a844bc04045fb8bdf4b4952274faefa8a5e6eb736a08cd6ea04285c9","source":{"kind":"arxiv","id":"2112.07701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07701","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07701v1","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07701","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_12","alias_value":"WLDHGRFIIS6A","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_16","alias_value":"WLDHGRFIIS6AIBC7","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_8","alias_value":"WLDHGRFI","created_at":"2026-07-05T03:41:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WLDHGRFIIS6AIBC7XC67JNEVEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T19:09:14Z","cross_cats_sorted":[],"title_canon_sha256":"776d510ca6c019d38692d024824d69df8bc7a84d817f03be633c2e02321baa3b","abstract_canon_sha256":"254dcd67c8cbebb0d5400bd4ad00f99ab9cafcf913c847895f214a7a79f0345c"},"schema_version":"1.0"},"canonical_sha256":"b2c67344a844bc04045fb8bdf4b4952274faefa8a5e6eb736a08cd6ea04285c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:05.530076Z","signature_b64":"0hInhnfDrnRZqZVls3fLo1kMuJBi40a7/bH5TfLeOGTCX/nhG+86wm/+I8Y76noxVAx54kdAbAX5D7Pn0vt8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c67344a844bc04045fb8bdf4b4952274faefa8a5e6eb736a08cd6ea04285c9","last_reissued_at":"2026-07-05T03:41:05.529636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:05.529636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07701","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":"2026-07-05T03:41:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdQKHYpyytr+5bHbPD8kR60f0A34KpL7POqSUKKRtfLibGs5d0Lh7nwQsTsN5Fssaj2pzZIqBvP74r0lq/oMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:59:35.463757Z"},"content_sha256":"3127d807b79841cf68393f3a37dec6181d4361d3ad6ce1b57f4aaa4b9776065d","schema_version":"1.0","event_id":"sha256:3127d807b79841cf68393f3a37dec6181d4361d3ad6ce1b57f4aaa4b9776065d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WLDHGRFIIS6AIBC7XC67JNEVEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Shen, Dinesh Jayaraman, Osbert Bastani, Yecheng Jason Ma","submitted_at":"2021-12-14T19:09:14Z","abstract_excerpt":"Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies that obey all constraints using simulated samples from a learned model. However, imperfect models can result in real-world constraint violations even for actions that are predicted to satisfy all constraints. We propose Conservative and Adaptive Penalty (CAP), a model-based safe RL framework that accounts for potential modeling errors by capturing model uncer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07701","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/2112.07701/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":"2026-07-05T03:41:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iMxzm93F17GrXNU4Qixtwj567YCTu25bFuQ9jyBI0jF6AzlrKNMTcwg9CQHl9XuNO/JJ1eftwlBv9ZFRMp9YDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:59:35.464149Z"},"content_sha256":"5d1f13b076ac94ae6e3b663395228998948f828a41ab77d7da57bb44cdccd716","schema_version":"1.0","event_id":"sha256:5d1f13b076ac94ae6e3b663395228998948f828a41ab77d7da57bb44cdccd716"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/bundle.json","state_url":"https://pith.science/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/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":"2026-07-14T12:59:35Z","links":{"resolver":"https://pith.science/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ","bundle":"https://pith.science/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/bundle.json","state":"https://pith.science/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLDHGRFIIS6AIBC7XC67JNEVEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WLDHGRFIIS6AIBC7XC67JNEVEJ","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":"254dcd67c8cbebb0d5400bd4ad00f99ab9cafcf913c847895f214a7a79f0345c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T19:09:14Z","title_canon_sha256":"776d510ca6c019d38692d024824d69df8bc7a84d817f03be633c2e02321baa3b"},"schema_version":"1.0","source":{"id":"2112.07701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07701","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07701v1","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07701","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_12","alias_value":"WLDHGRFIIS6A","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_16","alias_value":"WLDHGRFIIS6AIBC7","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_8","alias_value":"WLDHGRFI","created_at":"2026-07-05T03:41:05Z"}],"graph_snapshots":[{"event_id":"sha256:5d1f13b076ac94ae6e3b663395228998948f828a41ab77d7da57bb44cdccd716","target":"graph","created_at":"2026-07-05T03:41:05Z","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/2112.07701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies that obey all constraints using simulated samples from a learned model. However, imperfect models can result in real-world constraint violations even for actions that are predicted to satisfy all constraints. We propose Conservative and Adaptive Penalty (CAP), a model-based safe RL framework that accounts for potential modeling errors by capturing model uncer","authors_text":"Andrew Shen, Dinesh Jayaraman, Osbert Bastani, Yecheng Jason Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T19:09:14Z","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07701","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":"sha256:3127d807b79841cf68393f3a37dec6181d4361d3ad6ce1b57f4aaa4b9776065d","target":"record","created_at":"2026-07-05T03:41:05Z","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":"254dcd67c8cbebb0d5400bd4ad00f99ab9cafcf913c847895f214a7a79f0345c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T19:09:14Z","title_canon_sha256":"776d510ca6c019d38692d024824d69df8bc7a84d817f03be633c2e02321baa3b"},"schema_version":"1.0","source":{"id":"2112.07701","kind":"arxiv","version":1}},"canonical_sha256":"b2c67344a844bc04045fb8bdf4b4952274faefa8a5e6eb736a08cd6ea04285c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2c67344a844bc04045fb8bdf4b4952274faefa8a5e6eb736a08cd6ea04285c9","first_computed_at":"2026-07-05T03:41:05.529636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:05.529636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0hInhnfDrnRZqZVls3fLo1kMuJBi40a7/bH5TfLeOGTCX/nhG+86wm/+I8Y76noxVAx54kdAbAX5D7Pn0vt8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:05.530076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3127d807b79841cf68393f3a37dec6181d4361d3ad6ce1b57f4aaa4b9776065d","sha256:5d1f13b076ac94ae6e3b663395228998948f828a41ab77d7da57bb44cdccd716"],"state_sha256":"adbe18f6420dfb52ccff6df02d50df0d62621869f6b842ef303e5644f01145e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHWcPegPn7/vocmPvI3llflXNcv3dLUeEmQXHOsAFYZGxecUiP/MPksgA80mDakHMgXdQ/CaRNoEUcRbTkahAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T12:59:35.467018Z","bundle_sha256":"a11e06179283b256fddfcaf2fba89b1feaa4c97728bd6413ae27cba9b8798267"}}