{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MZART2YLXT2542PVGM3IA45KVX","short_pith_number":"pith:MZART2YL","canonical_record":{"source":{"id":"2410.01212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T03:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"c9742f988a51f317bbdbf54ed0a9cac11a34d8eb4fcc48f5ec5a65e6752843fd","abstract_canon_sha256":"06e72ec0a6a92f89e37523f4275b61d9b000c87e2ba7c42611f1375918c7a61f"},"schema_version":"1.0"},"canonical_sha256":"664119eb0bbcf5de69f533368073aaadfc31749bf3113579cfd9bbdaa11c88e4","source":{"kind":"arxiv","id":"2410.01212","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01212","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01212v1","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01212","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"MZART2YLXT25","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"MZART2YLXT2542PV","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"MZART2YL","created_at":"2026-07-05T09:14:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MZART2YLXT2542PVGM3IA45KVX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T03:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"c9742f988a51f317bbdbf54ed0a9cac11a34d8eb4fcc48f5ec5a65e6752843fd","abstract_canon_sha256":"06e72ec0a6a92f89e37523f4275b61d9b000c87e2ba7c42611f1375918c7a61f"},"schema_version":"1.0"},"canonical_sha256":"664119eb0bbcf5de69f533368073aaadfc31749bf3113579cfd9bbdaa11c88e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:44.830167Z","signature_b64":"zijxi8zvEQ1AhBVCEKkjQZ73vJa4UHiptTxaYDTQTmLK75X75muzBde6juHXfS/1ZyBtKrMggqDB3wswaF7LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664119eb0bbcf5de69f533368073aaadfc31749bf3113579cfd9bbdaa11c88e4","last_reissued_at":"2026-07-05T09:14:44.829668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:44.829668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01212","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":"2026-07-05T09:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWTEviLimRejaqP1PHtaen4HClkdGpbXwuFn4Jhx6UyAfsKG9R1uNYE/m6MuwXqlRg2Aeb4T83gX3FLhaxbbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T02:48:26.955712Z"},"content_sha256":"edce98b3acdeff4716677ff2032b46d8a449b0ccaa00c6ffe73a9a5de1983fa1","schema_version":"1.0","event_id":"sha256:edce98b3acdeff4716677ff2032b46d8a449b0ccaa00c6ffe73a9a5de1983fa1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MZART2YLXT2542PVGM3IA45KVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun, Yujie Wang","submitted_at":"2024-10-02T03:43:33Z","abstract_excerpt":"Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise constraints in expectation or enforce hard state-wise constraints with strong assumptions. The former does not exclude the probability of safety violations, while the latter is impractical. Our insight is that although it is intractable to guarantee hard state-wise constraints in a model-free setting, we can enforce state-wise safety with high probability while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01212","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/2410.01212/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":"2026-07-05T09:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d532d0evNfcsuzevFEumWNq6Ul1BLrG1f1eISqeU/FQUbdqVJHxcZigBaSe31s0dwLzWP0+J3bWSQJ+X6YevDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T02:48:26.956088Z"},"content_sha256":"036c365ee01bdce3be69f12d25b4ecab5a25d175909d582644c7c0c1552822d3","schema_version":"1.0","event_id":"sha256:036c365ee01bdce3be69f12d25b4ecab5a25d175909d582644c7c0c1552822d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZART2YLXT2542PVGM3IA45KVX/bundle.json","state_url":"https://pith.science/pith/MZART2YLXT2542PVGM3IA45KVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZART2YLXT2542PVGM3IA45KVX/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":"2026-07-18T02:48:26Z","links":{"resolver":"https://pith.science/pith/MZART2YLXT2542PVGM3IA45KVX","bundle":"https://pith.science/pith/MZART2YLXT2542PVGM3IA45KVX/bundle.json","state":"https://pith.science/pith/MZART2YLXT2542PVGM3IA45KVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZART2YLXT2542PVGM3IA45KVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZART2YLXT2542PVGM3IA45KVX","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":"06e72ec0a6a92f89e37523f4275b61d9b000c87e2ba7c42611f1375918c7a61f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T03:43:33Z","title_canon_sha256":"c9742f988a51f317bbdbf54ed0a9cac11a34d8eb4fcc48f5ec5a65e6752843fd"},"schema_version":"1.0","source":{"id":"2410.01212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01212","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01212v1","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01212","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"MZART2YLXT25","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"MZART2YLXT2542PV","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"MZART2YL","created_at":"2026-07-05T09:14:44Z"}],"graph_snapshots":[{"event_id":"sha256:036c365ee01bdce3be69f12d25b4ecab5a25d175909d582644c7c0c1552822d3","target":"graph","created_at":"2026-07-05T09:14:44Z","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/2410.01212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise constraints in expectation or enforce hard state-wise constraints with strong assumptions. The former does not exclude the probability of safety violations, while the latter is impractical. Our insight is that although it is intractable to guarantee hard state-wise constraints in a model-free setting, we can enforce state-wise safety with high probability while ","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun, Yujie Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T03:43:33Z","title":"Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01212","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:edce98b3acdeff4716677ff2032b46d8a449b0ccaa00c6ffe73a9a5de1983fa1","target":"record","created_at":"2026-07-05T09:14:44Z","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":"06e72ec0a6a92f89e37523f4275b61d9b000c87e2ba7c42611f1375918c7a61f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T03:43:33Z","title_canon_sha256":"c9742f988a51f317bbdbf54ed0a9cac11a34d8eb4fcc48f5ec5a65e6752843fd"},"schema_version":"1.0","source":{"id":"2410.01212","kind":"arxiv","version":1}},"canonical_sha256":"664119eb0bbcf5de69f533368073aaadfc31749bf3113579cfd9bbdaa11c88e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664119eb0bbcf5de69f533368073aaadfc31749bf3113579cfd9bbdaa11c88e4","first_computed_at":"2026-07-05T09:14:44.829668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:44.829668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zijxi8zvEQ1AhBVCEKkjQZ73vJa4UHiptTxaYDTQTmLK75X75muzBde6juHXfS/1ZyBtKrMggqDB3wswaF7LDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:44.830167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edce98b3acdeff4716677ff2032b46d8a449b0ccaa00c6ffe73a9a5de1983fa1","sha256:036c365ee01bdce3be69f12d25b4ecab5a25d175909d582644c7c0c1552822d3"],"state_sha256":"36f50352f991c8319855dda29604f113930a27d72b6327dc4231bdccd6b5b96b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5yBte34piGmtQES/IFwrz/lV6Q6/+CqbyiCY5y1ke+rmzKnJ8rYk5uagaqjfBT4EG5wCavJkTJF19BkF4Q3ODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T02:48:26.958435Z","bundle_sha256":"0308428d7b9d7ee5a17ad1a8d29c94464e6eac56bea02346c65ccba4961f6fda"}}