{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S6RMGIJWVH3JLVID45IETWBCUF","short_pith_number":"pith:S6RMGIJW","canonical_record":{"source":{"id":"2308.13140","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-25T02:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"02135595b0f7956c3a5bf0719ba5821d3fd180110b8a30fb31e75b43c1ea197e","abstract_canon_sha256":"b09edd36193990d0d200bbe13c62e360a7038f44d5943dcc5d64a38bdbff90ef"},"schema_version":"1.0"},"canonical_sha256":"97a2c32136a9f695d503e75049d822a15574b94095dec517533e2802d21683aa","source":{"kind":"arxiv","id":"2308.13140","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13140","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13140v5","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13140","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"S6RMGIJWVH3J","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"S6RMGIJWVH3JLVID","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"S6RMGIJW","created_at":"2026-07-05T11:14:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S6RMGIJWVH3JLVID45IETWBCUF","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13140","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-25T02:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"02135595b0f7956c3a5bf0719ba5821d3fd180110b8a30fb31e75b43c1ea197e","abstract_canon_sha256":"b09edd36193990d0d200bbe13c62e360a7038f44d5943dcc5d64a38bdbff90ef"},"schema_version":"1.0"},"canonical_sha256":"97a2c32136a9f695d503e75049d822a15574b94095dec517533e2802d21683aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:45.831508Z","signature_b64":"SvA/SfXkp/uMJ3n6EPdvfzwYfnFz5PU5ytZ9rak61zVU3yynCvhDUswK7lBK2iYnUCnVVL/FwVOq0EqX6LSQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a2c32136a9f695d503e75049d822a15574b94095dec517533e2802d21683aa","last_reissued_at":"2026-07-05T11:14:45.831066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:45.831066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13140","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkVv8NviEGHN1eF9P5IaihphmuZDLzmlaDCf8eUbadYWD/oy3CMvyhUo4w4gGb/UBd+UFGH7C/cRw3OOKejmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:11:09.936349Z"},"content_sha256":"f2c5eaeda5aeed19ec898ef0da18342d6bb50b07c998563b5ea9d7cc29ef6eed","schema_version":"1.0","event_id":"sha256:f2c5eaeda5aeed19ec898ef0da18342d6bb50b07c998563b5ea9d7cc29ef6eed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S6RMGIJWVH3JLVID45IETWBCUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","submitted_at":"2023-08-25T02:33:11Z","abstract_excerpt":"Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL agent learns from those mistakes. On the other hand, safe control techniques ensure persistent safety satisfaction but demand strong priors on system dynamics, which is usually hard to obtain in practice. To address these problems, we present Safe Set Guided State-wise Constrained Policy Optimization (S-3PO), a pioneering algorithm generating state-wise safe opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13140","kind":"arxiv","version":5},"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/2308.13140/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":"2026-07-05T11:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K02IAq/YjC882oLBcYsWIudiq4HZcKij1nFEvqsWMSym6qjkHIotGvMxAAC5hwF3KghqrqBJ9GN9XhmeCkIxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:11:09.937138Z"},"content_sha256":"100770b74b3a42027b52549b91343d2491b2dbaca7c967fefc362d495fef9ef6","schema_version":"1.0","event_id":"sha256:100770b74b3a42027b52549b91343d2491b2dbaca7c967fefc362d495fef9ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6RMGIJWVH3JLVID45IETWBCUF/bundle.json","state_url":"https://pith.science/pith/S6RMGIJWVH3JLVID45IETWBCUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6RMGIJWVH3JLVID45IETWBCUF/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":"2026-08-19T11:11:09Z","links":{"resolver":"https://pith.science/pith/S6RMGIJWVH3JLVID45IETWBCUF","bundle":"https://pith.science/pith/S6RMGIJWVH3JLVID45IETWBCUF/bundle.json","state":"https://pith.science/pith/S6RMGIJWVH3JLVID45IETWBCUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6RMGIJWVH3JLVID45IETWBCUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S6RMGIJWVH3JLVID45IETWBCUF","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":"b09edd36193990d0d200bbe13c62e360a7038f44d5943dcc5d64a38bdbff90ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-25T02:33:11Z","title_canon_sha256":"02135595b0f7956c3a5bf0719ba5821d3fd180110b8a30fb31e75b43c1ea197e"},"schema_version":"1.0","source":{"id":"2308.13140","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13140","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13140v5","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13140","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"S6RMGIJWVH3J","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"S6RMGIJWVH3JLVID","created_at":"2026-07-05T11:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"S6RMGIJW","created_at":"2026-07-05T11:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:100770b74b3a42027b52549b91343d2491b2dbaca7c967fefc362d495fef9ef6","target":"graph","created_at":"2026-07-05T11:14:45Z","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/2308.13140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL agent learns from those mistakes. On the other hand, safe control techniques ensure persistent safety satisfaction but demand strong priors on system dynamics, which is usually hard to obtain in practice. To address these problems, we present Safe Set Guided State-wise Constrained Policy Optimization (S-3PO), a pioneering algorithm generating state-wise safe opt","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-25T02:33:11Z","title":"Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13140","kind":"arxiv","version":5},"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:f2c5eaeda5aeed19ec898ef0da18342d6bb50b07c998563b5ea9d7cc29ef6eed","target":"record","created_at":"2026-07-05T11:14:45Z","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":"b09edd36193990d0d200bbe13c62e360a7038f44d5943dcc5d64a38bdbff90ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-25T02:33:11Z","title_canon_sha256":"02135595b0f7956c3a5bf0719ba5821d3fd180110b8a30fb31e75b43c1ea197e"},"schema_version":"1.0","source":{"id":"2308.13140","kind":"arxiv","version":5}},"canonical_sha256":"97a2c32136a9f695d503e75049d822a15574b94095dec517533e2802d21683aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a2c32136a9f695d503e75049d822a15574b94095dec517533e2802d21683aa","first_computed_at":"2026-07-05T11:14:45.831066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:45.831066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SvA/SfXkp/uMJ3n6EPdvfzwYfnFz5PU5ytZ9rak61zVU3yynCvhDUswK7lBK2iYnUCnVVL/FwVOq0EqX6LSQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:45.831508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13140","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2c5eaeda5aeed19ec898ef0da18342d6bb50b07c998563b5ea9d7cc29ef6eed","sha256:100770b74b3a42027b52549b91343d2491b2dbaca7c967fefc362d495fef9ef6"],"state_sha256":"b4f89e5dcd82042f667a744fac2d38f861b706c53a5736c479201900b0b0921a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6S/8u788h373I1yzKIgN6fZXsKrvFzswxQSPEOZy49yWk6q2nPfWy3y7gs+I2XQJyqsaN42cT1noq5XED0FBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:11:09.941756Z","bundle_sha256":"96a8eae4dfb3547cff667aed0f68862bb4babaa351659a0ca94d5a84c7889863"}}