{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q3SBFNVOTGPK2FZSXKCSQMZYSC","short_pith_number":"pith:Q3SBFNVO","canonical_record":{"source":{"id":"2405.02754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"015843ce54b107c4e6f8fc5edf06e29fca505b759f988dbe64bc3120167aa378","abstract_canon_sha256":"db17fdbb40ebd5c63fea6ddea23b89c13864442646dafbb2efb3588d2eef214b"},"schema_version":"1.0"},"canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","source":{"kind":"arxiv","id":"2405.02754","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02754","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02754v2","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02754","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"Q3SBFNVOTGPK","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"Q3SBFNVOTGPK2FZS","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"Q3SBFNVO","created_at":"2026-07-05T11:53:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q3SBFNVOTGPK2FZSXKCSQMZYSC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"015843ce54b107c4e6f8fc5edf06e29fca505b759f988dbe64bc3120167aa378","abstract_canon_sha256":"db17fdbb40ebd5c63fea6ddea23b89c13864442646dafbb2efb3588d2eef214b"},"schema_version":"1.0"},"canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:26.741704Z","signature_b64":"0nRywI190m8QmLdKwcmMDoTK2OhtXuOBeNWgaSdvGS4vBxnObpZ+EBGJf+0IVKrf1gKU3+7tnD/cy5+TKIRsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","last_reissued_at":"2026-07-05T11:53:26.741229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:26.741229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02754","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":"2026-07-05T11:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UHrrgMVJdlkgmjgg3abYxTD7n+I6T/8NgG4uzY3/lppudqKslSpXXEeWr7ppkct8P4T62Zb84mkFpM4GEkA+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T14:00:48.947066Z"},"content_sha256":"879c96373cb3b509e99fd2f0eb203811ef2a6aceb9faf0c939d2c6f1ad249c32","schema_version":"1.0","event_id":"sha256:879c96373cb3b509e99fd2f0eb203811ef2a6aceb9faf0c939d2c6f1ad249c32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q3SBFNVOTGPK2FZSXKCSQMZYSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Changliu Liu, Feihan Li, Weiye Zhao","submitted_at":"2024-05-04T20:59:06Z","abstract_excerpt":"Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can satisfy system safety in expectation through reward shaping, designing agents to consistently meet hard constraints (e.g., safety specifications) at every time step remains a formidable challenge. In contrast, existing work in the field of safe control provides guarantees on persistent satisfaction of hard safety constraints. However, these methods require explic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02754","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/2405.02754/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":"2026-07-05T11:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNaFgBD2RhxuSxGo5ccHz+X8eihdpM/eTxfjOKdXVMM9kjut72o240/LDxoNE0KfpTy7F+8i2FzKS9W3O71NDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T14:00:48.947453Z"},"content_sha256":"8abceff0e7d33802b4092fc8c2ca8513595d1b039facfa6b20462eecbd76e1ef","schema_version":"1.0","event_id":"sha256:8abceff0e7d33802b4092fc8c2ca8513595d1b039facfa6b20462eecbd76e1ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/bundle.json","state_url":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/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":"2026-07-13T14:00:48Z","links":{"resolver":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC","bundle":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/bundle.json","state":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3SBFNVOTGPK2FZSXKCSQMZYSC","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":"db17fdbb40ebd5c63fea6ddea23b89c13864442646dafbb2efb3588d2eef214b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","title_canon_sha256":"015843ce54b107c4e6f8fc5edf06e29fca505b759f988dbe64bc3120167aa378"},"schema_version":"1.0","source":{"id":"2405.02754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02754","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02754v2","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02754","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"Q3SBFNVOTGPK","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"Q3SBFNVOTGPK2FZS","created_at":"2026-07-05T11:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"Q3SBFNVO","created_at":"2026-07-05T11:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:8abceff0e7d33802b4092fc8c2ca8513595d1b039facfa6b20462eecbd76e1ef","target":"graph","created_at":"2026-07-05T11:53:26Z","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/2405.02754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can satisfy system safety in expectation through reward shaping, designing agents to consistently meet hard constraints (e.g., safety specifications) at every time step remains a formidable challenge. In contrast, existing work in the field of safe control provides guarantees on persistent satisfaction of hard safety constraints. However, these methods require explic","authors_text":"Changliu Liu, Feihan Li, Weiye Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","title":"Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02754","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":"sha256:879c96373cb3b509e99fd2f0eb203811ef2a6aceb9faf0c939d2c6f1ad249c32","target":"record","created_at":"2026-07-05T11:53:26Z","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":"db17fdbb40ebd5c63fea6ddea23b89c13864442646dafbb2efb3588d2eef214b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","title_canon_sha256":"015843ce54b107c4e6f8fc5edf06e29fca505b759f988dbe64bc3120167aa378"},"schema_version":"1.0","source":{"id":"2405.02754","kind":"arxiv","version":2}},"canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","first_computed_at":"2026-07-05T11:53:26.741229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:26.741229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nRywI190m8QmLdKwcmMDoTK2OhtXuOBeNWgaSdvGS4vBxnObpZ+EBGJf+0IVKrf1gKU3+7tnD/cy5+TKIRsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:26.741704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879c96373cb3b509e99fd2f0eb203811ef2a6aceb9faf0c939d2c6f1ad249c32","sha256:8abceff0e7d33802b4092fc8c2ca8513595d1b039facfa6b20462eecbd76e1ef"],"state_sha256":"5a354c4addee4662a871e53c5be75d356fdc9460fb2495548f3b31b47bf3ceb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFOwUcQUsk5v8M3Xn6ft97CAvFFp3qvuP+ZzMm6xGdfUK/haFoBeHfmMLoKWwMUuu+codQCEdvnvsmZlxLVlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T14:00:48.949598Z","bundle_sha256":"e69f14325062105baad57cc49ac6e26802a6cdbbe7cc2822cf062dc13f0ed18c"}}