{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4DAYUPQRZGZU6DSDT6H3IQ3ED4","short_pith_number":"pith:4DAYUPQR","canonical_record":{"source":{"id":"2307.07176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T06:00:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6a8e5c695425ca67a70710f1f233dd340b9ae2522bc3392508cda04eafb36983","abstract_canon_sha256":"f96be1f3defdac2737fc3bf1d739998788a5898eec7fead1ea22cf49f8d83632"},"schema_version":"1.0"},"canonical_sha256":"e0c18a3e11c9b34f0e439f8fb443641f1745fd82a1c43434ac7c9ec63fcd91ae","source":{"kind":"arxiv","id":"2307.07176","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07176","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07176v3","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07176","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"4DAYUPQRZGZU","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"4DAYUPQRZGZU6DSD","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"4DAYUPQR","created_at":"2026-07-05T08:53:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4DAYUPQRZGZU6DSDT6H3IQ3ED4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T06:00:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6a8e5c695425ca67a70710f1f233dd340b9ae2522bc3392508cda04eafb36983","abstract_canon_sha256":"f96be1f3defdac2737fc3bf1d739998788a5898eec7fead1ea22cf49f8d83632"},"schema_version":"1.0"},"canonical_sha256":"e0c18a3e11c9b34f0e439f8fb443641f1745fd82a1c43434ac7c9ec63fcd91ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:16.528772Z","signature_b64":"C+E9A9hn+YwISFGb5g4A97rVR87Ss74LszwCcnPzHEWsvjQld1Up4kCnpii12EXVkgbyivmEWGyBaUlwy+mbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0c18a3e11c9b34f0e439f8fb443641f1745fd82a1c43434ac7c9ec63fcd91ae","last_reissued_at":"2026-07-05T08:53:16.528328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:16.528328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07176","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LiU6gd2l8DqBv9d4Jr+hGG5RCxn9Csp4pyOpmJsI9uJtxYqqWCnGfDw9JaPnor4WuEQHhnopVgc+ukLXObQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:47.579129Z"},"content_sha256":"d264a212a28ba2f82569a9557e0daf826c474d97e9fce8bb0c0bf753edd7e6fa","schema_version":"1.0","event_id":"sha256:d264a212a28ba2f82569a9557e0daf826c474d97e9fce8bb0c0bf753edd7e6fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4DAYUPQRZGZU6DSDT6H3IQ3ED4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SafeDreamer: Safe Reinforcement Learning with World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Borong Zhang, Chunhe Xia, Jiaming Ji, Weidong Huang, Yaodong Yang","submitted_at":"2023-07-14T06:00:08Z","abstract_excerpt":"The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07176","kind":"arxiv","version":3},"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/2307.07176/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":"2026-07-05T08:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/vAiXaKAiljznbrtr05inqzhHRzzRk/de0ym95zra+lSsfj3rXv4QFNxj2A94iDLEK5GadzAlx8fkrB2U9FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:47.579641Z"},"content_sha256":"aec05e4231db1fba5bc18e1f29b2e3ced763bc48186b0c902598fbf36f227e05","schema_version":"1.0","event_id":"sha256:aec05e4231db1fba5bc18e1f29b2e3ced763bc48186b0c902598fbf36f227e05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/bundle.json","state_url":"https://pith.science/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/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":"2026-08-07T01:04:47Z","links":{"resolver":"https://pith.science/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4","bundle":"https://pith.science/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/bundle.json","state":"https://pith.science/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DAYUPQRZGZU6DSDT6H3IQ3ED4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4DAYUPQRZGZU6DSDT6H3IQ3ED4","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":"f96be1f3defdac2737fc3bf1d739998788a5898eec7fead1ea22cf49f8d83632","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T06:00:08Z","title_canon_sha256":"6a8e5c695425ca67a70710f1f233dd340b9ae2522bc3392508cda04eafb36983"},"schema_version":"1.0","source":{"id":"2307.07176","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07176","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07176v3","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07176","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"4DAYUPQRZGZU","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"4DAYUPQRZGZU6DSD","created_at":"2026-07-05T08:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"4DAYUPQR","created_at":"2026-07-05T08:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:aec05e4231db1fba5bc18e1f29b2e3ced763bc48186b0c902598fbf36f227e05","target":"graph","created_at":"2026-07-05T08:53:16Z","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/2307.07176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based","authors_text":"Borong Zhang, Chunhe Xia, Jiaming Ji, Weidong Huang, Yaodong Yang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T06:00:08Z","title":"SafeDreamer: Safe Reinforcement Learning with World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07176","kind":"arxiv","version":3},"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:d264a212a28ba2f82569a9557e0daf826c474d97e9fce8bb0c0bf753edd7e6fa","target":"record","created_at":"2026-07-05T08:53:16Z","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":"f96be1f3defdac2737fc3bf1d739998788a5898eec7fead1ea22cf49f8d83632","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T06:00:08Z","title_canon_sha256":"6a8e5c695425ca67a70710f1f233dd340b9ae2522bc3392508cda04eafb36983"},"schema_version":"1.0","source":{"id":"2307.07176","kind":"arxiv","version":3}},"canonical_sha256":"e0c18a3e11c9b34f0e439f8fb443641f1745fd82a1c43434ac7c9ec63fcd91ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0c18a3e11c9b34f0e439f8fb443641f1745fd82a1c43434ac7c9ec63fcd91ae","first_computed_at":"2026-07-05T08:53:16.528328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:16.528328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+E9A9hn+YwISFGb5g4A97rVR87Ss74LszwCcnPzHEWsvjQld1Up4kCnpii12EXVkgbyivmEWGyBaUlwy+mbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:16.528772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07176","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d264a212a28ba2f82569a9557e0daf826c474d97e9fce8bb0c0bf753edd7e6fa","sha256:aec05e4231db1fba5bc18e1f29b2e3ced763bc48186b0c902598fbf36f227e05"],"state_sha256":"0e0fc14cd2ae2ca09c2c8c053906e7d96b49ae968c51d0acb83e709b300dfc8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AG9kUvftwn8iNEbQgP/CEn5Y+hxHy1ttbDBVgt897JnczFuDDBumhFcp0FSTAwAXiDaf6pOi0z96yXCxAzTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:04:47.584692Z","bundle_sha256":"fa0d2c52096ed1ddf36fa14503f4075f98bd67f50ee71f14d85a39c2a456e59b"}}