{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EPXL6C77P2AI5ZHQ2R72EW4CX3","short_pith_number":"pith:EPXL6C77","canonical_record":{"source":{"id":"2402.15650","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T23:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a101735719178879cad0e3cbcd4acfa1be5fa604632081ccfb486628fab10480","abstract_canon_sha256":"057b861b10d45b46a801c78e4e3f481ede1529fa7bb36f76d38f68897813c8b0"},"schema_version":"1.0"},"canonical_sha256":"23eebf0bff7e808ee4f0d47fa25b82bed83bf33d94a0512690f3baa71ef508d5","source":{"kind":"arxiv","id":"2402.15650","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15650","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15650v3","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15650","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_12","alias_value":"EPXL6C77P2AI","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPXL6C77P2AI5ZHQ","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPXL6C77","created_at":"2026-07-05T09:00:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EPXL6C77P2AI5ZHQ2R72EW4CX3","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15650","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T23:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a101735719178879cad0e3cbcd4acfa1be5fa604632081ccfb486628fab10480","abstract_canon_sha256":"057b861b10d45b46a801c78e4e3f481ede1529fa7bb36f76d38f68897813c8b0"},"schema_version":"1.0"},"canonical_sha256":"23eebf0bff7e808ee4f0d47fa25b82bed83bf33d94a0512690f3baa71ef508d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:22.249300Z","signature_b64":"TfNA5NVdTWHN/kj+dDLYiIR0NkGut6lPDq4or0sFo7tSzQE4VpN1hyvEe3Ck/q2l9os1uTQtbRmJzpvGVJ0wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23eebf0bff7e808ee4f0d47fa25b82bed83bf33d94a0512690f3baa71ef508d5","last_reissued_at":"2026-07-05T09:00:22.248805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:22.248805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15650","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":"2026-07-05T09:00:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDMc48kRmV0R3LfoBmDyG3reupCezErHkYijS/2IP8tMWmnDxl7ZWhqtgauIFPF783OtopM/tokBP9LcifTGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:54:47.526442Z"},"content_sha256":"d31d192e785de9f4fdb44afa26b8b219badffc89edfb3624c12cfe4643afd569","schema_version":"1.0","event_id":"sha256:d31d192e785de9f4fdb44afa26b8b219badffc89edfb3624c12cfe4643afd569"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EPXL6C77P2AI5ZHQ2R72EW4CX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandr Petiushko, Animesh Garg, Jonathan Booher, Khashayar Rohanimanesh, Wei Liu, Zihan Zhou","submitted_at":"2024-02-23T23:22:06Z","abstract_excerpt":"Safe reinforcement learning tasks are a challenging domain despite being very common in the real world. The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. To address this issue, we first describe the problem with a stronger Uniformly Constrained MDP (UCMDP) model where we impose constraints on all reachable states; we then propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives accordin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15650","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/2402.15650/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":"2026-07-05T09:00:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8JUqUXx+vMSrLQOHX+0IXl0IY/s1boA7sPsLWsNAagylRX6n70zWhTO865ZO9u6K+40K+5BNJRxYFweN/OmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:54:47.526833Z"},"content_sha256":"514d6957ea29923ebadb2b05bdce87923ff55550d451ec935f883301d449e7f0","schema_version":"1.0","event_id":"sha256:514d6957ea29923ebadb2b05bdce87923ff55550d451ec935f883301d449e7f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/bundle.json","state_url":"https://pith.science/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/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":"2026-08-13T09:54:47Z","links":{"resolver":"https://pith.science/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3","bundle":"https://pith.science/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/bundle.json","state":"https://pith.science/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPXL6C77P2AI5ZHQ2R72EW4CX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EPXL6C77P2AI5ZHQ2R72EW4CX3","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":"057b861b10d45b46a801c78e4e3f481ede1529fa7bb36f76d38f68897813c8b0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T23:22:06Z","title_canon_sha256":"a101735719178879cad0e3cbcd4acfa1be5fa604632081ccfb486628fab10480"},"schema_version":"1.0","source":{"id":"2402.15650","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15650","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15650v3","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15650","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_12","alias_value":"EPXL6C77P2AI","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPXL6C77P2AI5ZHQ","created_at":"2026-07-05T09:00:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPXL6C77","created_at":"2026-07-05T09:00:22Z"}],"graph_snapshots":[{"event_id":"sha256:514d6957ea29923ebadb2b05bdce87923ff55550d451ec935f883301d449e7f0","target":"graph","created_at":"2026-07-05T09:00:22Z","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/2402.15650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning tasks are a challenging domain despite being very common in the real world. The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. To address this issue, we first describe the problem with a stronger Uniformly Constrained MDP (UCMDP) model where we impose constraints on all reachable states; we then propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives accordin","authors_text":"Aleksandr Petiushko, Animesh Garg, Jonathan Booher, Khashayar Rohanimanesh, Wei Liu, Zihan Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T23:22:06Z","title":"Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15650","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:d31d192e785de9f4fdb44afa26b8b219badffc89edfb3624c12cfe4643afd569","target":"record","created_at":"2026-07-05T09:00:22Z","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":"057b861b10d45b46a801c78e4e3f481ede1529fa7bb36f76d38f68897813c8b0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T23:22:06Z","title_canon_sha256":"a101735719178879cad0e3cbcd4acfa1be5fa604632081ccfb486628fab10480"},"schema_version":"1.0","source":{"id":"2402.15650","kind":"arxiv","version":3}},"canonical_sha256":"23eebf0bff7e808ee4f0d47fa25b82bed83bf33d94a0512690f3baa71ef508d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23eebf0bff7e808ee4f0d47fa25b82bed83bf33d94a0512690f3baa71ef508d5","first_computed_at":"2026-07-05T09:00:22.248805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:22.248805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TfNA5NVdTWHN/kj+dDLYiIR0NkGut6lPDq4or0sFo7tSzQE4VpN1hyvEe3Ck/q2l9os1uTQtbRmJzpvGVJ0wDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:22.249300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15650","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31d192e785de9f4fdb44afa26b8b219badffc89edfb3624c12cfe4643afd569","sha256:514d6957ea29923ebadb2b05bdce87923ff55550d451ec935f883301d449e7f0"],"state_sha256":"29bb06dc7ba4f83cb969cbd0f59bf96af7708c98763e341c55bbd5b6fa9621db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAX5MpdkLm9DDqmROaZCQhyighn1V4uzj90+hv4B9zjC3D0wJcnzro+KO/Qp7NwWixEkDVNJRSaP8HBmR5YlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T09:54:47.529750Z","bundle_sha256":"cb61428b96d73b05f0726ed1be49b4f76e3a9c147cc64ff978e3a9c0784b273d"}}