{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MQYAMW7RYJJRXESUJH4YYP5NP3","short_pith_number":"pith:MQYAMW7R","canonical_record":{"source":{"id":"2312.15127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","cross_cats_sorted":[],"title_canon_sha256":"c17f784558e6a068873247c1a28084b492feaa72f081d274ab7bb4cb7e68d049","abstract_canon_sha256":"8620dcef6393a0f8882318a1788e1a52e6d7ca6015f38229040d55cd208a8052"},"schema_version":"1.0"},"canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","source":{"kind":"arxiv","id":"2312.15127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15127","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15127v1","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15127","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"MQYAMW7RYJJR","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"MQYAMW7RYJJRXESU","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"MQYAMW7R","created_at":"2026-07-05T07:27:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MQYAMW7RYJJRXESUJH4YYP5NP3","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","cross_cats_sorted":[],"title_canon_sha256":"c17f784558e6a068873247c1a28084b492feaa72f081d274ab7bb4cb7e68d049","abstract_canon_sha256":"8620dcef6393a0f8882318a1788e1a52e6d7ca6015f38229040d55cd208a8052"},"schema_version":"1.0"},"canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:31.202326Z","signature_b64":"QSKZyZKsGt5eH1YRtwSTYcawfBVrJhNzfQ2QK1IZJj6rgSfy30n9HqI4TTTZichOY+NGZDq00wh7XDFvPrJFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","last_reissued_at":"2026-07-05T07:27:31.201905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:31.201905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15127","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":"2026-07-05T07:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uPQlQ5Gul4xfwiOM76qcbU/74IiR0e52kF1dec5B27zyTE5EUo+exKslXpc3wPF9bL7++m10ykGgmWbFYtdaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:35:55.855462Z"},"content_sha256":"12a7ea4c578ec59c1b48626e57a896673bdf6ba73fa5eb01590746f238ef466e","schema_version":"1.0","event_id":"sha256:12a7ea4c578ec59c1b48626e57a896673bdf6ba73fa5eb01590746f238ef466e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MQYAMW7RYJJRXESUJH4YYP5NP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Peide Huang, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zuxin Liu","submitted_at":"2023-12-23T00:55:09Z","abstract_excerpt":"Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges associated with solving multi-constraint (MC) safe RL problems. We approach the safe RL problem from the perspective of Multi-Objective Optimization (MOO) and propose a unified framework designed for MC safe RL algorithms. This framework highlights the manipulation of gradients derived from constraints. Leveraging insights from this framework and recognizing the si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15127","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/2312.15127/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":"2026-07-05T07:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HET4vQSgO4zRMzIMfWnyDf4MfF6gKC4nxSUb7YsB5DF2jj+6Gc4HiNgeUGhAlGzh2efMYvjgTSSKF4rc61b+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:35:55.855949Z"},"content_sha256":"5ab3bacfa5dcae7232cab1797bc7eb77b4961a5d5e00bc1e039cc29496d6e273","schema_version":"1.0","event_id":"sha256:5ab3bacfa5dcae7232cab1797bc7eb77b4961a5d5e00bc1e039cc29496d6e273"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/bundle.json","state_url":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/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":"2026-08-06T09:35:55Z","links":{"resolver":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3","bundle":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/bundle.json","state":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MQYAMW7RYJJRXESUJH4YYP5NP3","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":"8620dcef6393a0f8882318a1788e1a52e6d7ca6015f38229040d55cd208a8052","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","title_canon_sha256":"c17f784558e6a068873247c1a28084b492feaa72f081d274ab7bb4cb7e68d049"},"schema_version":"1.0","source":{"id":"2312.15127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15127","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15127v1","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15127","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"MQYAMW7RYJJR","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"MQYAMW7RYJJRXESU","created_at":"2026-07-05T07:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"MQYAMW7R","created_at":"2026-07-05T07:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:5ab3bacfa5dcae7232cab1797bc7eb77b4961a5d5e00bc1e039cc29496d6e273","target":"graph","created_at":"2026-07-05T07:27:31Z","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/2312.15127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges associated with solving multi-constraint (MC) safe RL problems. We approach the safe RL problem from the perspective of Multi-Objective Optimization (MOO) and propose a unified framework designed for MC safe RL algorithms. This framework highlights the manipulation of gradients derived from constraints. Leveraging insights from this framework and recognizing the si","authors_text":"Ding Zhao, Peide Huang, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zuxin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15127","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":"sha256:12a7ea4c578ec59c1b48626e57a896673bdf6ba73fa5eb01590746f238ef466e","target":"record","created_at":"2026-07-05T07:27:31Z","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":"8620dcef6393a0f8882318a1788e1a52e6d7ca6015f38229040d55cd208a8052","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","title_canon_sha256":"c17f784558e6a068873247c1a28084b492feaa72f081d274ab7bb4cb7e68d049"},"schema_version":"1.0","source":{"id":"2312.15127","kind":"arxiv","version":1}},"canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","first_computed_at":"2026-07-05T07:27:31.201905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:31.201905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QSKZyZKsGt5eH1YRtwSTYcawfBVrJhNzfQ2QK1IZJj6rgSfy30n9HqI4TTTZichOY+NGZDq00wh7XDFvPrJFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:31.202326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12a7ea4c578ec59c1b48626e57a896673bdf6ba73fa5eb01590746f238ef466e","sha256:5ab3bacfa5dcae7232cab1797bc7eb77b4961a5d5e00bc1e039cc29496d6e273"],"state_sha256":"1e5e11f86352f37566075d639f9aab98d5e956e8929e448e2a85e8e8069caf53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnE8l/VyKMUr0+Ffzdu+zwFexNT9bQimcEKbvZAYLdSXbqm/CdNSKWdTlNqM8Ni8wLBNfud4fu9nnNF7kYq8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:35:55.861198Z","bundle_sha256":"1cd4da5790ea3e25ed942d9c2d94061dd4ec43fc70b186603b5853492a9a96b7"}}