{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IEMYOYVJTVSX5FQGJIO7EYPV37","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":"9b980ad3a8ee12a99a8a88e5ad50851d7387975b88ca670d586614c7b4161587","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T17:56:10Z","title_canon_sha256":"631f8b1aa15b34698d5a4a2442b1f8f99d972f80fc0dda5a10fb8fd478334166"},"schema_version":"1.0","source":{"id":"2606.25012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25012","created_at":"2026-06-25T00:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25012v1","created_at":"2026-06-25T00:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25012","created_at":"2026-06-25T00:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"IEMYOYVJTVSX","created_at":"2026-06-25T00:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"IEMYOYVJTVSX5FQG","created_at":"2026-06-25T00:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"IEMYOYVJ","created_at":"2026-06-25T00:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:55de2de4263fe9379e4e1f37c365c372a0db654d56b4dfb014400b8fea08150c","target":"graph","created_at":"2026-06-25T00:18:14Z","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/2606.25012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints. A common approach is concave scalarization, where the agent maximizes a utility $ f(J^\\pi_{r_1}, \\ldots, J^\\pi_{r_M}) $ subject to a scalarized constraint $ g(J^\\pi_{c_1}, \\ldots, J^\\pi_{c_N}) \\ge 0 $, where $J^\\pi_{r_m}$ and $J^\\pi_{c_n}$ denote the average-reward and cost under policy $\\pi$. However, the nonlinearity of $f$ and $g$ introduces bias in policy-gradient and actor-critic methods, since gradients m","authors_text":"Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T17:56:10Z","title":"Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25012","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":"sha256:92f462b79d784847613cd00f52c3bc3aa831721f2b39fdcec04bf04f73ab30cc","target":"record","created_at":"2026-06-25T00:18:14Z","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":"9b980ad3a8ee12a99a8a88e5ad50851d7387975b88ca670d586614c7b4161587","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T17:56:10Z","title_canon_sha256":"631f8b1aa15b34698d5a4a2442b1f8f99d972f80fc0dda5a10fb8fd478334166"},"schema_version":"1.0","source":{"id":"2606.25012","kind":"arxiv","version":1}},"canonical_sha256":"41198762a99d657e96064a1df261f5dff1dd16f5ba8c8357ad6442cec4b2fcf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41198762a99d657e96064a1df261f5dff1dd16f5ba8c8357ad6442cec4b2fcf6","first_computed_at":"2026-06-25T00:18:14.675550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:14.675550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4yinoBtXsbezLNnR/C2zsFqrnO6pl0QkuiQXoXCir+Ing26ZXZA7jITRsIhtUSbJ8Zl47/aPjNfqw7tY6qXAA==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:14.676093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92f462b79d784847613cd00f52c3bc3aa831721f2b39fdcec04bf04f73ab30cc","sha256:55de2de4263fe9379e4e1f37c365c372a0db654d56b4dfb014400b8fea08150c"],"state_sha256":"9968e149371fd108906f6f915d8c7a825fa63fda8e194e6977896f8e5d1340c9"}