{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6SZWATWXADYN5I6ODTSKFEXDDU","short_pith_number":"pith:6SZWATWX","canonical_record":{"source":{"id":"2506.07040","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"307efb1d672774fc5294eded69349723c5197cfa72366a00b557a5838892fb1d","abstract_canon_sha256":"1fed25d88f7b6099685c81d3294c17899c5c42379689033d72b4857558bc90cd"},"schema_version":"1.0"},"canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","source":{"kind":"arxiv","id":"2506.07040","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07040","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07040v4","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07040","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"6SZWATWXADYN","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"6SZWATWXADYN5I6O","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"6SZWATWX","created_at":"2026-07-14T01:21:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6SZWATWXADYN5I6ODTSKFEXDDU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07040","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"307efb1d672774fc5294eded69349723c5197cfa72366a00b557a5838892fb1d","abstract_canon_sha256":"1fed25d88f7b6099685c81d3294c17899c5c42379689033d72b4857558bc90cd"},"schema_version":"1.0"},"canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:59.598647Z","signature_b64":"PHzLeJzsB5tBHVX2eU66IILNGyoghMTExN+Jl+YHZMhSNnoTXN9T6KnJcvX7CdNmh6yLGVy9qGgNcdZzbfhBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","last_reissued_at":"2026-07-14T01:21:59.597713Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:59.597713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07040","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVCucpl5FWaOb8otz2BWchEnM8gCu6vD1icQLoXKZ/mDxeghJTL8LL7gKbIk9M2bwckeFOTzkxRzcm+vbFNpAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:39.478195Z"},"content_sha256":"ec387f41dce379a9ac8ed6aff5cc0fa9071e52da393236a16fc86c65f69f32c2","schema_version":"1.0","event_id":"sha256:ec387f41dce379a9ac8ed6aff5cc0fa9071e52da393236a16fc86c65f69f32c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6SZWATWXADYN5I6ODTSKFEXDDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Swetha Ganesh, Vaneet Aggarwal, Yang Xu","submitted_at":"2025-06-08T08:26:27Z","abstract_excerpt":"We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor-critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust $Q$-function with $\\tilde{\\mathca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07040","kind":"arxiv","version":4},"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/2506.07040/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":"2026-07-14T01:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xTqeFqsxUYYCk3kaqSG/jYjKZTRvqHQGP0fOL5/aeFaLNFG6Ea67XpG4ANlfRc2PLEQNRE7nJAnIRQPXjOoHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:39.478761Z"},"content_sha256":"e5f6784bc831e6526640a2317e8c502ceae6b96136818aa9000e81a1ac7e6c63","schema_version":"1.0","event_id":"sha256:e5f6784bc831e6526640a2317e8c502ceae6b96136818aa9000e81a1ac7e6c63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/bundle.json","state_url":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SZWATWXADYN5I6ODTSKFEXDDU/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":"2026-08-08T17:01:39Z","links":{"resolver":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU","bundle":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/bundle.json","state":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SZWATWXADYN5I6ODTSKFEXDDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6SZWATWXADYN5I6ODTSKFEXDDU","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":"1fed25d88f7b6099685c81d3294c17899c5c42379689033d72b4857558bc90cd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","title_canon_sha256":"307efb1d672774fc5294eded69349723c5197cfa72366a00b557a5838892fb1d"},"schema_version":"1.0","source":{"id":"2506.07040","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07040","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07040v4","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07040","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"6SZWATWXADYN","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"6SZWATWXADYN5I6O","created_at":"2026-07-14T01:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"6SZWATWX","created_at":"2026-07-14T01:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:e5f6784bc831e6526640a2317e8c502ceae6b96136818aa9000e81a1ac7e6c63","target":"graph","created_at":"2026-07-14T01:21:59Z","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/2506.07040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor-critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust $Q$-function with $\\tilde{\\mathca","authors_text":"Swetha Ganesh, Vaneet Aggarwal, Yang Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07040","kind":"arxiv","version":4},"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:ec387f41dce379a9ac8ed6aff5cc0fa9071e52da393236a16fc86c65f69f32c2","target":"record","created_at":"2026-07-14T01:21:59Z","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":"1fed25d88f7b6099685c81d3294c17899c5c42379689033d72b4857558bc90cd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","title_canon_sha256":"307efb1d672774fc5294eded69349723c5197cfa72366a00b557a5838892fb1d"},"schema_version":"1.0","source":{"id":"2506.07040","kind":"arxiv","version":4}},"canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","first_computed_at":"2026-07-14T01:21:59.597713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:59.597713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHzLeJzsB5tBHVX2eU66IILNGyoghMTExN+Jl+YHZMhSNnoTXN9T6KnJcvX7CdNmh6yLGVy9qGgNcdZzbfhBAw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:59.598647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07040","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec387f41dce379a9ac8ed6aff5cc0fa9071e52da393236a16fc86c65f69f32c2","sha256:e5f6784bc831e6526640a2317e8c502ceae6b96136818aa9000e81a1ac7e6c63"],"state_sha256":"914e76c12a0e73bd733fe31071165559d98378ab5661561bd770a6dd7b34399e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdE+h6pVJWkZ+rJy3ic9OzaJamJJoZNegqyb11ti6cOitmo+vGuAk2VVUHMJApiF17Y7IUbw8FXSE/KvRTcFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:01:39.484352Z","bundle_sha256":"ce084abccfef5472b25d0c72c816223848165023f4143beabcada3610eb44b06"}}