{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CNWINKR4K7TM3KXKSKZ4FXEJD7","short_pith_number":"pith:CNWINKR4","canonical_record":{"source":{"id":"2302.04375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ef679078eab6e73ebb36aa296c068e91b57eb25c5c6c3122f36a24644ab604e","abstract_canon_sha256":"6f7429bbcca79927e325174a872f23285f81f5d7ac9d018ad4db630cf267c4be"},"schema_version":"1.0"},"canonical_sha256":"136c86aa3c57e6cdaaea92b3c2dc891ff6d37d049c81251ff4590640717075a4","source":{"kind":"arxiv","id":"2302.04375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04375","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04375v1","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04375","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_12","alias_value":"CNWINKR4K7TM","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_16","alias_value":"CNWINKR4K7TM3KXK","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_8","alias_value":"CNWINKR4","created_at":"2026-07-05T05:40:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CNWINKR4K7TM3KXKSKZ4FXEJD7","target":"record","payload":{"canonical_record":{"source":{"id":"2302.04375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ef679078eab6e73ebb36aa296c068e91b57eb25c5c6c3122f36a24644ab604e","abstract_canon_sha256":"6f7429bbcca79927e325174a872f23285f81f5d7ac9d018ad4db630cf267c4be"},"schema_version":"1.0"},"canonical_sha256":"136c86aa3c57e6cdaaea92b3c2dc891ff6d37d049c81251ff4590640717075a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:13.158370Z","signature_b64":"rANjtCWkWYqUw/vet1WdyiFpLz4jNMRNZfU7OYtaynPb2y+RHMQ8IVdaiU94gmBk0WaFyeadp8vhBV8DVvOvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"136c86aa3c57e6cdaaea92b3c2dc891ff6d37d049c81251ff4590640717075a4","last_reissued_at":"2026-07-05T05:40:13.157841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:13.157841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.04375","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":"2026-07-05T05:40:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XCpOa0Nkf8vSBu08rjB181CCCBQBoPBU96satFFleB3p/J/NdYh6s8KtrIdQEN4b97FyUL6D1VfMvhG4rnP1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:39.721341Z"},"content_sha256":"1777a21070dd4c45978f83d94331795ba6c5a605cadc9c194afd949a59f6cc12","schema_version":"1.0","event_id":"sha256:1777a21070dd4c45978f83d94331795ba6c5a605cadc9c194afd949a59f6cc12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CNWINKR4K7TM3KXKSKZ4FXEJD7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ming Shi, Ness Shroff, Yingbin Liang","submitted_at":"2023-02-08T23:42:04Z","abstract_excerpt":"In many applications of Reinforcement Learning (RL), it is critically important that the algorithm performs safely, such that instantaneous hard constraints are satisfied at each step, and unsafe states and actions are avoided. However, existing algorithms for ''safe'' RL are often designed under constraints that either require expected cumulative costs to be bounded or assume all states are safe. Thus, such algorithms could violate instantaneous hard constraints and traverse unsafe states (and actions) in practice. Therefore, in this paper, we develop the first near-optimal safe RL algorithm "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04375","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/2302.04375/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":"2026-07-05T05:40:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMnzJtcTe9zpwSkY8lkfLZZHf2buvcFh1zqBwnaLTIwvIvT+SNY57xbmQz+1VGecfTREUSAfcRf0Lr/TLjsDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:39.721997Z"},"content_sha256":"eaceb868fc86549f312dd7375652bddcf021ec49b0516f662f9313551c599141","schema_version":"1.0","event_id":"sha256:eaceb868fc86549f312dd7375652bddcf021ec49b0516f662f9313551c599141"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/bundle.json","state_url":"https://pith.science/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/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":"2026-08-10T10:11:39Z","links":{"resolver":"https://pith.science/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7","bundle":"https://pith.science/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/bundle.json","state":"https://pith.science/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNWINKR4K7TM3KXKSKZ4FXEJD7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CNWINKR4K7TM3KXKSKZ4FXEJD7","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":"6f7429bbcca79927e325174a872f23285f81f5d7ac9d018ad4db630cf267c4be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:04Z","title_canon_sha256":"0ef679078eab6e73ebb36aa296c068e91b57eb25c5c6c3122f36a24644ab604e"},"schema_version":"1.0","source":{"id":"2302.04375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04375","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04375v1","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04375","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_12","alias_value":"CNWINKR4K7TM","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_16","alias_value":"CNWINKR4K7TM3KXK","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_8","alias_value":"CNWINKR4","created_at":"2026-07-05T05:40:13Z"}],"graph_snapshots":[{"event_id":"sha256:eaceb868fc86549f312dd7375652bddcf021ec49b0516f662f9313551c599141","target":"graph","created_at":"2026-07-05T05:40:13Z","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/2302.04375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many applications of Reinforcement Learning (RL), it is critically important that the algorithm performs safely, such that instantaneous hard constraints are satisfied at each step, and unsafe states and actions are avoided. However, existing algorithms for ''safe'' RL are often designed under constraints that either require expected cumulative costs to be bounded or assume all states are safe. Thus, such algorithms could violate instantaneous hard constraints and traverse unsafe states (and actions) in practice. Therefore, in this paper, we develop the first near-optimal safe RL algorithm ","authors_text":"Ming Shi, Ness Shroff, Yingbin Liang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:04Z","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04375","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":"sha256:1777a21070dd4c45978f83d94331795ba6c5a605cadc9c194afd949a59f6cc12","target":"record","created_at":"2026-07-05T05:40:13Z","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":"6f7429bbcca79927e325174a872f23285f81f5d7ac9d018ad4db630cf267c4be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:04Z","title_canon_sha256":"0ef679078eab6e73ebb36aa296c068e91b57eb25c5c6c3122f36a24644ab604e"},"schema_version":"1.0","source":{"id":"2302.04375","kind":"arxiv","version":1}},"canonical_sha256":"136c86aa3c57e6cdaaea92b3c2dc891ff6d37d049c81251ff4590640717075a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"136c86aa3c57e6cdaaea92b3c2dc891ff6d37d049c81251ff4590640717075a4","first_computed_at":"2026-07-05T05:40:13.157841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:13.157841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rANjtCWkWYqUw/vet1WdyiFpLz4jNMRNZfU7OYtaynPb2y+RHMQ8IVdaiU94gmBk0WaFyeadp8vhBV8DVvOvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:13.158370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1777a21070dd4c45978f83d94331795ba6c5a605cadc9c194afd949a59f6cc12","sha256:eaceb868fc86549f312dd7375652bddcf021ec49b0516f662f9313551c599141"],"state_sha256":"548773997feae2463b601eb74d4225d5332bcc9e2c96f27986b64915bd9a9aca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7eXnlM1zgl2EgLpbOts6v6GCU0fMKndcshDGnWJTzqrtfkZTrMNINO7EG9pPNqibWqL6pYNIJRSLVGmxpHWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:11:39.726768Z","bundle_sha256":"e3f3d37a5e8f8e0f91dab3c5ecf6a0922ed129a808be87accce284bb5a8de454"}}