{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MLYUAHERIUNQYMZIQ2HPM4LPVV","short_pith_number":"pith:MLYUAHER","canonical_record":{"source":{"id":"2411.02957","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:55:50Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"1fcddf278f0a5c3563f46c6ed9d88618a8a47335b591af52de407211c5b04c4f","abstract_canon_sha256":"51507ce551ef6f43cbf709bb8945c67c219da34b211007f9efad3beb72984f00"},"schema_version":"1.0"},"canonical_sha256":"62f1401c91451b0c3328868ef6716fad4e7e468e3295b2217a6bc749f648af48","source":{"kind":"arxiv","id":"2411.02957","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02957","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02957v4","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02957","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"MLYUAHERIUNQ","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"MLYUAHERIUNQYMZI","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"MLYUAHER","created_at":"2026-07-05T11:54:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MLYUAHERIUNQYMZIQ2HPM4LPVV","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02957","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:55:50Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"1fcddf278f0a5c3563f46c6ed9d88618a8a47335b591af52de407211c5b04c4f","abstract_canon_sha256":"51507ce551ef6f43cbf709bb8945c67c219da34b211007f9efad3beb72984f00"},"schema_version":"1.0"},"canonical_sha256":"62f1401c91451b0c3328868ef6716fad4e7e468e3295b2217a6bc749f648af48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:28.710850Z","signature_b64":"MJjzRrGyHUU6TSR6Nr4/PIIhSLYahPgBAHLLXzBiRap8omDFXuB9NvCz/IJ0bgrUxQJ5Q+QGLT3ilqlFiCyLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f1401c91451b0c3328868ef6716fad4e7e468e3295b2217a6bc749f648af48","last_reissued_at":"2026-07-05T11:54:28.710397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:28.710397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02957","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fcRxdkMk7i0OvonlmXfZSEv9fm2nDZEOoYWsaDQ3BaGd+vkHAcHmXAxBOXBJBS7+NZfr4QnpJf4qMXWBa8yNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:30:39.920270Z"},"content_sha256":"13f07ee7f83eb5d990c873e3c72c38bd53532dcc5f369f0e69b24cfd2871701b","schema_version":"1.0","event_id":"sha256:13f07ee7f83eb5d990c873e3c72c38bd53532dcc5f369f0e69b24cfd2871701b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MLYUAHERIUNQYMZIQ2HPM4LPVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedding Safety into RL: A New Take on Trust Region Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Johannes M\\\"uller, Nico Scherf, Nikola Milosevic","submitted_at":"2024-11-05T09:55:50Z","abstract_excerpt":"Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward maximization or allow unsafe training. We introduce Constrained Trust Region Policy Optimization (C-TRPO), which reshapes the policy space geometry to ensure trust regions contain only safe policies, guaranteeing constraint satisfaction throughout training. We analyze its theoretical properties and connections to TRPO, Natural Policy Gradient (NPG), and Constrained P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02957","kind":"arxiv","version":4},"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/2411.02957/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":"2026-07-05T11:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vLGfRRl8pgm7GVmq2LXxKHx/yZ6jX/ON/vtA2HkiNyIr3VH3dR3QF3rE/BB6xF16oc79O4l/sr2eN2gqk/PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:30:39.921228Z"},"content_sha256":"c024e4e4a8dc381ed8a694ab816bb879b33cd96bd8a66bd949c225755e336b9f","schema_version":"1.0","event_id":"sha256:c024e4e4a8dc381ed8a694ab816bb879b33cd96bd8a66bd949c225755e336b9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/bundle.json","state_url":"https://pith.science/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/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":"2026-08-08T12:30:39Z","links":{"resolver":"https://pith.science/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV","bundle":"https://pith.science/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/bundle.json","state":"https://pith.science/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLYUAHERIUNQYMZIQ2HPM4LPVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MLYUAHERIUNQYMZIQ2HPM4LPVV","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":"51507ce551ef6f43cbf709bb8945c67c219da34b211007f9efad3beb72984f00","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:55:50Z","title_canon_sha256":"1fcddf278f0a5c3563f46c6ed9d88618a8a47335b591af52de407211c5b04c4f"},"schema_version":"1.0","source":{"id":"2411.02957","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02957","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02957v4","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02957","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"MLYUAHERIUNQ","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"MLYUAHERIUNQYMZI","created_at":"2026-07-05T11:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"MLYUAHER","created_at":"2026-07-05T11:54:28Z"}],"graph_snapshots":[{"event_id":"sha256:c024e4e4a8dc381ed8a694ab816bb879b33cd96bd8a66bd949c225755e336b9f","target":"graph","created_at":"2026-07-05T11:54:28Z","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/2411.02957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward maximization or allow unsafe training. We introduce Constrained Trust Region Policy Optimization (C-TRPO), which reshapes the policy space geometry to ensure trust regions contain only safe policies, guaranteeing constraint satisfaction throughout training. We analyze its theoretical properties and connections to TRPO, Natural Policy Gradient (NPG), and Constrained P","authors_text":"Johannes M\\\"uller, Nico Scherf, Nikola Milosevic","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:55:50Z","title":"Embedding Safety into RL: A New Take on Trust Region Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02957","kind":"arxiv","version":4},"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":"sha256:13f07ee7f83eb5d990c873e3c72c38bd53532dcc5f369f0e69b24cfd2871701b","target":"record","created_at":"2026-07-05T11:54:28Z","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":"51507ce551ef6f43cbf709bb8945c67c219da34b211007f9efad3beb72984f00","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:55:50Z","title_canon_sha256":"1fcddf278f0a5c3563f46c6ed9d88618a8a47335b591af52de407211c5b04c4f"},"schema_version":"1.0","source":{"id":"2411.02957","kind":"arxiv","version":4}},"canonical_sha256":"62f1401c91451b0c3328868ef6716fad4e7e468e3295b2217a6bc749f648af48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f1401c91451b0c3328868ef6716fad4e7e468e3295b2217a6bc749f648af48","first_computed_at":"2026-07-05T11:54:28.710397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:28.710397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJjzRrGyHUU6TSR6Nr4/PIIhSLYahPgBAHLLXzBiRap8omDFXuB9NvCz/IJ0bgrUxQJ5Q+QGLT3ilqlFiCyLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:28.710850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02957","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13f07ee7f83eb5d990c873e3c72c38bd53532dcc5f369f0e69b24cfd2871701b","sha256:c024e4e4a8dc381ed8a694ab816bb879b33cd96bd8a66bd949c225755e336b9f"],"state_sha256":"163ecd3c502d0164c9432f936c248c06b76a13649d3b9de0e8cae8da2bf61c2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jesMB3f40I0NY/6JkJWfIL8/T8v/gBFZo+FgiLutEX5dNYtpxA/ubiiNdyzrpiQ7RqaNtmw3Jt+q3/X0WczBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:30:39.927901Z","bundle_sha256":"68de1ace229065904fda9ac0979388d784816b37e42f3ddb47fe3cd7de494d10"}}