{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:USEANPOAX4KPWRQ7V2RV7JB54H","short_pith_number":"pith:USEANPOA","canonical_record":{"source":{"id":"2204.05176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"227c00f4c18c3b88fb7e64d6c613e284aadaa8c6261356324f0f66eb040593cc","abstract_canon_sha256":"8c2c7aa8efc78133a9f60c179aa49807d9945dbc35f25fe6c2b87ec46ed9bebe"},"schema_version":"1.0"},"canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","source":{"kind":"arxiv","id":"2204.05176","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05176","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05176v1","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05176","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"USEANPOAX4KP","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"USEANPOAX4KPWRQ7","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"USEANPOA","created_at":"2026-07-05T04:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:USEANPOAX4KPWRQ7V2RV7JB54H","target":"record","payload":{"canonical_record":{"source":{"id":"2204.05176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"227c00f4c18c3b88fb7e64d6c613e284aadaa8c6261356324f0f66eb040593cc","abstract_canon_sha256":"8c2c7aa8efc78133a9f60c179aa49807d9945dbc35f25fe6c2b87ec46ed9bebe"},"schema_version":"1.0"},"canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:18.171023Z","signature_b64":"tnCqvwfTYlMh6HHCxT3nc9ObfYX9hiRCF1Z6c0x+UEz9H3Sz2MU2mfJhy3P4u9mtzxYObBBrCmsOBP1zqxL1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","last_reissued_at":"2026-07-05T04:13:18.170564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:18.170564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.05176","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":"2026-07-05T04:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3O14pY0jDa0X8k/yOdXbPAPZNJV51xigN6WZYYTmjJUWZdgQyCtCvSeED+smF+YbcG46RDK1uSHU4yQFnA/NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:11:12.289368Z"},"content_sha256":"8bdc52efadc324e18c782dbb1447e6e97a2c0303b1260792d51f425b5aa016a9","schema_version":"1.0","event_id":"sha256:8bdc52efadc324e18c782dbb1447e6e97a2c0303b1260792d51f425b5aa016a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:USEANPOAX4KPWRQ7V2RV7JB54H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Painless Policy Optimization for Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arushi Jain, Csaba Szepesvari, Doina Precup, Reza Babanezhad, Sharan Vaswani","submitted_at":"2022-04-11T15:08:09Z","abstract_excerpt":"We study policy optimization in an infinite horizon, $\\gamma$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05176","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/2204.05176/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":"2026-07-05T04:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+o3pgCC41Yb9Fvk+4xbna34mN1878X8CL8ljGfVtsSLJCQHxHMprOQbCM/6JdkmKhEJ7dAuVDI7zsuZNTiH1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:11:12.289740Z"},"content_sha256":"ceb433fb534ccf939f5c161aa5fc92eeb5c797ff12b07f9b5dce29ed5a1ac78a","schema_version":"1.0","event_id":"sha256:ceb433fb534ccf939f5c161aa5fc92eeb5c797ff12b07f9b5dce29ed5a1ac78a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/bundle.json","state_url":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USEANPOAX4KPWRQ7V2RV7JB54H/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":"2026-07-07T15:11:12Z","links":{"resolver":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H","bundle":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/bundle.json","state":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USEANPOAX4KPWRQ7V2RV7JB54H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:USEANPOAX4KPWRQ7V2RV7JB54H","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":"8c2c7aa8efc78133a9f60c179aa49807d9945dbc35f25fe6c2b87ec46ed9bebe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","title_canon_sha256":"227c00f4c18c3b88fb7e64d6c613e284aadaa8c6261356324f0f66eb040593cc"},"schema_version":"1.0","source":{"id":"2204.05176","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05176","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05176v1","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05176","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"USEANPOAX4KP","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"USEANPOAX4KPWRQ7","created_at":"2026-07-05T04:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"USEANPOA","created_at":"2026-07-05T04:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:ceb433fb534ccf939f5c161aa5fc92eeb5c797ff12b07f9b5dce29ed5a1ac78a","target":"graph","created_at":"2026-07-05T04:13:18Z","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/2204.05176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study policy optimization in an infinite horizon, $\\gamma$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework ","authors_text":"Arushi Jain, Csaba Szepesvari, Doina Precup, Reza Babanezhad, Sharan Vaswani","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","title":"Towards Painless Policy Optimization for Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05176","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":"sha256:8bdc52efadc324e18c782dbb1447e6e97a2c0303b1260792d51f425b5aa016a9","target":"record","created_at":"2026-07-05T04:13:18Z","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":"8c2c7aa8efc78133a9f60c179aa49807d9945dbc35f25fe6c2b87ec46ed9bebe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","title_canon_sha256":"227c00f4c18c3b88fb7e64d6c613e284aadaa8c6261356324f0f66eb040593cc"},"schema_version":"1.0","source":{"id":"2204.05176","kind":"arxiv","version":1}},"canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","first_computed_at":"2026-07-05T04:13:18.170564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:18.170564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnCqvwfTYlMh6HHCxT3nc9ObfYX9hiRCF1Z6c0x+UEz9H3Sz2MU2mfJhy3P4u9mtzxYObBBrCmsOBP1zqxL1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:18.171023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05176","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bdc52efadc324e18c782dbb1447e6e97a2c0303b1260792d51f425b5aa016a9","sha256:ceb433fb534ccf939f5c161aa5fc92eeb5c797ff12b07f9b5dce29ed5a1ac78a"],"state_sha256":"72e5bf6d80e887e433c4c8f95b1a595557e8538272e2ff30c361784a6219d24f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"etZzng/RVES7WTCPPZvtY0wtwUGv3WVGYP7r7r/3DgM47W80ZEJ5lzzhlgavSrQFQMsD/Bki8QXjyWg0/foNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:11:12.291650Z","bundle_sha256":"aa74e256d43a0c634a609482ff97991dcb79e98a432362715a637886a0222c55"}}