{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DY4S6F4PPHG623OIOUGLA7N36P","short_pith_number":"pith:DY4S6F4P","canonical_record":{"source":{"id":"2306.11700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T17:27:31Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"2c47f317309ac95c26ebeb7965ed366431c84e1c383ee58ff52de2ce2cb5e168","abstract_canon_sha256":"89bd978a0cd89bf62b5feea479d06400302181dc4527c8e5a0f3da256f9649a2"},"schema_version":"1.0"},"canonical_sha256":"1e392f178f79cded6dc8750cb07dbbf3c0cd1cb524873ec5a4f4628c679acadc","source":{"kind":"arxiv","id":"2306.11700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11700","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11700v2","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11700","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_12","alias_value":"DY4S6F4PPHG6","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_16","alias_value":"DY4S6F4PPHG623OI","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_8","alias_value":"DY4S6F4P","created_at":"2026-07-05T07:34:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DY4S6F4PPHG623OIOUGLA7N36P","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T17:27:31Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"2c47f317309ac95c26ebeb7965ed366431c84e1c383ee58ff52de2ce2cb5e168","abstract_canon_sha256":"89bd978a0cd89bf62b5feea479d06400302181dc4527c8e5a0f3da256f9649a2"},"schema_version":"1.0"},"canonical_sha256":"1e392f178f79cded6dc8750cb07dbbf3c0cd1cb524873ec5a4f4628c679acadc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:15.556878Z","signature_b64":"WX3s4SKc5tTv4OhJMe+8VlACOYnY1Y5KeG+50kHqBfwtkBOwwDjVfdS5gJ6vYu5YIFTlx0jo4fbLaWQ1e7XaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e392f178f79cded6dc8750cb07dbbf3c0cd1cb524873ec5a4f4628c679acadc","last_reissued_at":"2026-07-05T07:34:15.556421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:15.556421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:34:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XwniOA5UFRKlrOXuLmP8oDUj1BHl9H7rPeHAGiCdY4VzlHTiKdvhsj+GQgmD0gjgvx7OaaJsO8iE1Oqfm5PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:21:00.583959Z"},"content_sha256":"b4844cfd91651214c7f5d52c99fbe0719bb6a1830fabddc85cd8c9a866d13e9a","schema_version":"1.0","event_id":"sha256:b4844cfd91651214c7f5d52c99fbe0719bb6a1830fabddc85cd8c9a866d13e9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DY4S6F4PPHG623OIOUGLA7N36P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Alejandro Ribeiro, Chen-Yu Wei, Dongsheng Ding, Kaiqing Zhang","submitted_at":"2023-06-20T17:27:31Z","abstract_excerpt":"We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation of policy iterates in these methods has not been fully understood, bringing out issues such as violation of constraints and sensitivity to hyper-parameters. To fill this gap, we employ the Lagrangian method to cast a constrained MDP into a constrained saddle-point problem in which max/min players correspond to primal/dual variables, respectively, and develop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11700","kind":"arxiv","version":2},"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/2306.11700/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":"2026-07-05T07:34:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hVBJmVKyMKmayQxEDhccBJeWPm4vE8CDGWXLSl42+o4S5l4OpHZjXdrqQ5TtSLEk1cI9uzD/hAn04XPnisnKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:21:00.584450Z"},"content_sha256":"13acf0d95a561a7ad33586815893526f635ba0062955a29d07a90be1fed0e985","schema_version":"1.0","event_id":"sha256:13acf0d95a561a7ad33586815893526f635ba0062955a29d07a90be1fed0e985"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DY4S6F4PPHG623OIOUGLA7N36P/bundle.json","state_url":"https://pith.science/pith/DY4S6F4PPHG623OIOUGLA7N36P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DY4S6F4PPHG623OIOUGLA7N36P/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":"2026-08-15T03:21:00Z","links":{"resolver":"https://pith.science/pith/DY4S6F4PPHG623OIOUGLA7N36P","bundle":"https://pith.science/pith/DY4S6F4PPHG623OIOUGLA7N36P/bundle.json","state":"https://pith.science/pith/DY4S6F4PPHG623OIOUGLA7N36P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DY4S6F4PPHG623OIOUGLA7N36P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DY4S6F4PPHG623OIOUGLA7N36P","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":"89bd978a0cd89bf62b5feea479d06400302181dc4527c8e5a0f3da256f9649a2","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T17:27:31Z","title_canon_sha256":"2c47f317309ac95c26ebeb7965ed366431c84e1c383ee58ff52de2ce2cb5e168"},"schema_version":"1.0","source":{"id":"2306.11700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11700","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11700v2","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11700","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_12","alias_value":"DY4S6F4PPHG6","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_16","alias_value":"DY4S6F4PPHG623OI","created_at":"2026-07-05T07:34:15Z"},{"alias_kind":"pith_short_8","alias_value":"DY4S6F4P","created_at":"2026-07-05T07:34:15Z"}],"graph_snapshots":[{"event_id":"sha256:13acf0d95a561a7ad33586815893526f635ba0062955a29d07a90be1fed0e985","target":"graph","created_at":"2026-07-05T07:34:15Z","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/2306.11700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation of policy iterates in these methods has not been fully understood, bringing out issues such as violation of constraints and sensitivity to hyper-parameters. To fill this gap, we employ the Lagrangian method to cast a constrained MDP into a constrained saddle-point problem in which max/min players correspond to primal/dual variables, respectively, and develop","authors_text":"Alejandro Ribeiro, Chen-Yu Wei, Dongsheng Ding, Kaiqing Zhang","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T17:27:31Z","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11700","kind":"arxiv","version":2},"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:b4844cfd91651214c7f5d52c99fbe0719bb6a1830fabddc85cd8c9a866d13e9a","target":"record","created_at":"2026-07-05T07:34:15Z","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":"89bd978a0cd89bf62b5feea479d06400302181dc4527c8e5a0f3da256f9649a2","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T17:27:31Z","title_canon_sha256":"2c47f317309ac95c26ebeb7965ed366431c84e1c383ee58ff52de2ce2cb5e168"},"schema_version":"1.0","source":{"id":"2306.11700","kind":"arxiv","version":2}},"canonical_sha256":"1e392f178f79cded6dc8750cb07dbbf3c0cd1cb524873ec5a4f4628c679acadc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e392f178f79cded6dc8750cb07dbbf3c0cd1cb524873ec5a4f4628c679acadc","first_computed_at":"2026-07-05T07:34:15.556421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:15.556421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WX3s4SKc5tTv4OhJMe+8VlACOYnY1Y5KeG+50kHqBfwtkBOwwDjVfdS5gJ6vYu5YIFTlx0jo4fbLaWQ1e7XaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:15.556878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4844cfd91651214c7f5d52c99fbe0719bb6a1830fabddc85cd8c9a866d13e9a","sha256:13acf0d95a561a7ad33586815893526f635ba0062955a29d07a90be1fed0e985"],"state_sha256":"a2c4c28aed348aa82e3383bfa734ea26750a870164762537f01689db98123307"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUqLhKsOQ+JrUGNRY6c0zSoYPhYwfGYvzJZkoN1JO0iTOyrSkSqlr9rlnnZGWVRIOsJSfKYhEpg5WH3cO5InAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:21:00.589458Z","bundle_sha256":"22e494074322756609e0444cd623a41c8eb449d4cdf8673685d03094daa5d5b8"}}