{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LFQJXD4HMREF3D375TF4EZP473","short_pith_number":"pith:LFQJXD4H","canonical_record":{"source":{"id":"2406.15788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T08:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"cd60693b8f994c092ffc83e0606c8dda2bafb9f3b4df4e16a3aa377007f476a5","abstract_canon_sha256":"d93c321a1f8a19ac67a8ebaa14d31edb902ed2f777cd735fb922af50979a0d20"},"schema_version":"1.0"},"canonical_sha256":"59609b8f8764485d8f7feccbc265fcfec486bd9d29e64971ed15328cf6838d80","source":{"kind":"arxiv","id":"2406.15788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15788","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15788v1","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15788","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"LFQJXD4HMREF","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"LFQJXD4HMREF3D37","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"LFQJXD4H","created_at":"2026-07-05T08:35:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LFQJXD4HMREF3D375TF4EZP473","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T08:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"cd60693b8f994c092ffc83e0606c8dda2bafb9f3b4df4e16a3aa377007f476a5","abstract_canon_sha256":"d93c321a1f8a19ac67a8ebaa14d31edb902ed2f777cd735fb922af50979a0d20"},"schema_version":"1.0"},"canonical_sha256":"59609b8f8764485d8f7feccbc265fcfec486bd9d29e64971ed15328cf6838d80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:27.699306Z","signature_b64":"f2a++kmF4Xf9FotaoLcv+WgWM9RwK9D1zXfIkRy8qB6iFt10qCWp+yuYWfWFvEAdf+4/fIFm86dKc4Vmf9zbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59609b8f8764485d8f7feccbc265fcfec486bd9d29e64971ed15328cf6838d80","last_reissued_at":"2026-07-05T08:35:27.698847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:27.698847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15788","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":"2026-07-05T08:35:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7GXnvVe0GFlIEWYhhxkuMfbBzPyS5JDqOModnAl6WxDKxCb1g7oyquYIobgYUrPamKv4eadxuD9vHZ/IfStCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:21:18.118656Z"},"content_sha256":"12b4ff666b544d741c886ff0ab56928dbe663724d59bbab577773a8932cc808d","schema_version":"1.0","event_id":"sha256:12b4ff666b544d741c886ff0ab56928dbe663724d59bbab577773a8932cc808d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LFQJXD4HMREF3D375TF4EZP473","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Kishan Panaganti, Laixi Shi, Yanan Sui, Yisong Yue, Zhengfei Zhang","submitted_at":"2024-06-22T08:51:57Z","abstract_excerpt":"We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15788","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/2406.15788/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":"2026-07-05T08:35:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UhysbrHusviUP2VFsUxgRqnC64SoMNamh8NwwKUkYNBhdRfH8l8JNC6x0qvai/Rw2eDFOXlTdhL5hNJ35n3KCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:21:18.119195Z"},"content_sha256":"767aa57590a28e5d50cfc75ddc3d3fd44735259d3fc7836234d53c113e57db9d","schema_version":"1.0","event_id":"sha256:767aa57590a28e5d50cfc75ddc3d3fd44735259d3fc7836234d53c113e57db9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFQJXD4HMREF3D375TF4EZP473/bundle.json","state_url":"https://pith.science/pith/LFQJXD4HMREF3D375TF4EZP473/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFQJXD4HMREF3D375TF4EZP473/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":"2026-08-05T20:21:18Z","links":{"resolver":"https://pith.science/pith/LFQJXD4HMREF3D375TF4EZP473","bundle":"https://pith.science/pith/LFQJXD4HMREF3D375TF4EZP473/bundle.json","state":"https://pith.science/pith/LFQJXD4HMREF3D375TF4EZP473/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFQJXD4HMREF3D375TF4EZP473/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LFQJXD4HMREF3D375TF4EZP473","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":"d93c321a1f8a19ac67a8ebaa14d31edb902ed2f777cd735fb922af50979a0d20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T08:51:57Z","title_canon_sha256":"cd60693b8f994c092ffc83e0606c8dda2bafb9f3b4df4e16a3aa377007f476a5"},"schema_version":"1.0","source":{"id":"2406.15788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15788","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15788v1","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15788","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"LFQJXD4HMREF","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"LFQJXD4HMREF3D37","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"LFQJXD4H","created_at":"2026-07-05T08:35:27Z"}],"graph_snapshots":[{"event_id":"sha256:767aa57590a28e5d50cfc75ddc3d3fd44735259d3fc7836234d53c113e57db9d","target":"graph","created_at":"2026-07-05T08:35:27Z","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/2406.15788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based ","authors_text":"Adam Wierman, Kishan Panaganti, Laixi Shi, Yanan Sui, Yisong Yue, Zhengfei Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T08:51:57Z","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15788","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":"sha256:12b4ff666b544d741c886ff0ab56928dbe663724d59bbab577773a8932cc808d","target":"record","created_at":"2026-07-05T08:35:27Z","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":"d93c321a1f8a19ac67a8ebaa14d31edb902ed2f777cd735fb922af50979a0d20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T08:51:57Z","title_canon_sha256":"cd60693b8f994c092ffc83e0606c8dda2bafb9f3b4df4e16a3aa377007f476a5"},"schema_version":"1.0","source":{"id":"2406.15788","kind":"arxiv","version":1}},"canonical_sha256":"59609b8f8764485d8f7feccbc265fcfec486bd9d29e64971ed15328cf6838d80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59609b8f8764485d8f7feccbc265fcfec486bd9d29e64971ed15328cf6838d80","first_computed_at":"2026-07-05T08:35:27.698847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:27.698847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f2a++kmF4Xf9FotaoLcv+WgWM9RwK9D1zXfIkRy8qB6iFt10qCWp+yuYWfWFvEAdf+4/fIFm86dKc4Vmf9zbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:27.699306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12b4ff666b544d741c886ff0ab56928dbe663724d59bbab577773a8932cc808d","sha256:767aa57590a28e5d50cfc75ddc3d3fd44735259d3fc7836234d53c113e57db9d"],"state_sha256":"3805cadaec710ce379e9d0c6a77412edfc7948e4978d050514f9155bd23ca145"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYoPi1n+PHn1BjrovogGS9B9hySP40Ded7hmNggkFDjedCtRk16Ee9XdSHwjYHA7UUeTIGcLYh7xrWzNPlVCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:21:18.125210Z","bundle_sha256":"fcbfed85b3c9586162a94f3c94a8c8c11d536fa663aa3e3252c263ed7d7f8fc5"}}