{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DOCLTGMLIFL2Y5LX7PZZVCSHCY","short_pith_number":"pith:DOCLTGML","canonical_record":{"source":{"id":"2409.03915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T21:23:51Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e61ab771f677e6874f62f2903a9094db3eeb8b327f9c1dc93efe66ff7328dee1","abstract_canon_sha256":"dfd8f38b7d3d0efe2194b166e65e7a9f63ea21cdc55d547b0e563a0bd52ad591"},"schema_version":"1.0"},"canonical_sha256":"1b84b9998b4157ac7577fbf39a8a47162c2bdf135d5a98780dffcd3fb538c089","source":{"kind":"arxiv","id":"2409.03915","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03915","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03915v3","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03915","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"DOCLTGMLIFL2","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"DOCLTGMLIFL2Y5LX","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"DOCLTGML","created_at":"2026-06-02T01:03:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DOCLTGMLIFL2Y5LX7PZZVCSHCY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.03915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T21:23:51Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e61ab771f677e6874f62f2903a9094db3eeb8b327f9c1dc93efe66ff7328dee1","abstract_canon_sha256":"dfd8f38b7d3d0efe2194b166e65e7a9f63ea21cdc55d547b0e563a0bd52ad591"},"schema_version":"1.0"},"canonical_sha256":"1b84b9998b4157ac7577fbf39a8a47162c2bdf135d5a98780dffcd3fb538c089","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:29.218353Z","signature_b64":"4QPdzG/prqdP+deUuLnAbLSxtUhQY6i6rbn4GZp/iWYIsezWZ3QMWj0/qhCKbDAE/EeV80winG6h3FAo5FiTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b84b9998b4157ac7577fbf39a8a47162c2bdf135d5a98780dffcd3fb538c089","last_reissued_at":"2026-06-02T01:03:29.217931Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:29.217931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.03915","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+KxHDN5IuCrFt/FXfI97JYTD4XDVnSZGUs1oDylrf72eiLXZ+xVixJFpi22cJpaJgkhZUNmiVrvSWCoFEUpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:43:02.151996Z"},"content_sha256":"b78b824d20c17be73f127c6e588a5a1d4db10d94cb6bbf2e9cd80a3f8c318541","schema_version":"1.0","event_id":"sha256:b78b824d20c17be73f127c6e588a5a1d4db10d94cb6bbf2e9cd80a3f8c318541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DOCLTGMLIFL2Y5LX7PZZVCSHCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huizhen Yu, Richard S. Sutton, Yi Wan","submitted_at":"2024-09-05T21:23:51Z","abstract_excerpt":"This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously considered, thereby yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine the shadowing properties of asynchronous SA, building on a dynamical systems approach of Hirsch and Bena\\\"{i}m. These results provide a theor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03915","kind":"arxiv","version":3},"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/2409.03915/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":"2026-06-02T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5w8Gbyb37Vk5PfGCSkfc2u2xwRoK1SmjMckbPjhBcrnUYwiwTI5LJQLCfJ3Y3Aetoz7Hup3VJiiPx3VrIjgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:43:02.152616Z"},"content_sha256":"43bfbbc6ab731143bde79aef24a9d111fa02f88fd09ad3d3e876fe5d89595bed","schema_version":"1.0","event_id":"sha256:43bfbbc6ab731143bde79aef24a9d111fa02f88fd09ad3d3e876fe5d89595bed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/bundle.json","state_url":"https://pith.science/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/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":"2026-06-30T05:43:02Z","links":{"resolver":"https://pith.science/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY","bundle":"https://pith.science/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/bundle.json","state":"https://pith.science/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DOCLTGMLIFL2Y5LX7PZZVCSHCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DOCLTGMLIFL2Y5LX7PZZVCSHCY","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":"dfd8f38b7d3d0efe2194b166e65e7a9f63ea21cdc55d547b0e563a0bd52ad591","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T21:23:51Z","title_canon_sha256":"e61ab771f677e6874f62f2903a9094db3eeb8b327f9c1dc93efe66ff7328dee1"},"schema_version":"1.0","source":{"id":"2409.03915","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03915","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03915v3","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03915","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"DOCLTGMLIFL2","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"DOCLTGMLIFL2Y5LX","created_at":"2026-06-02T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"DOCLTGML","created_at":"2026-06-02T01:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:43bfbbc6ab731143bde79aef24a9d111fa02f88fd09ad3d3e876fe5d89595bed","target":"graph","created_at":"2026-06-02T01:03:29Z","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/2409.03915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously considered, thereby yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine the shadowing properties of asynchronous SA, building on a dynamical systems approach of Hirsch and Bena\\\"{i}m. These results provide a theor","authors_text":"Huizhen Yu, Richard S. Sutton, Yi Wan","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T21:23:51Z","title":"Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03915","kind":"arxiv","version":3},"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:b78b824d20c17be73f127c6e588a5a1d4db10d94cb6bbf2e9cd80a3f8c318541","target":"record","created_at":"2026-06-02T01:03:29Z","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":"dfd8f38b7d3d0efe2194b166e65e7a9f63ea21cdc55d547b0e563a0bd52ad591","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T21:23:51Z","title_canon_sha256":"e61ab771f677e6874f62f2903a9094db3eeb8b327f9c1dc93efe66ff7328dee1"},"schema_version":"1.0","source":{"id":"2409.03915","kind":"arxiv","version":3}},"canonical_sha256":"1b84b9998b4157ac7577fbf39a8a47162c2bdf135d5a98780dffcd3fb538c089","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b84b9998b4157ac7577fbf39a8a47162c2bdf135d5a98780dffcd3fb538c089","first_computed_at":"2026-06-02T01:03:29.217931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:29.217931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QPdzG/prqdP+deUuLnAbLSxtUhQY6i6rbn4GZp/iWYIsezWZ3QMWj0/qhCKbDAE/EeV80winG6h3FAo5FiTBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:29.218353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03915","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b78b824d20c17be73f127c6e588a5a1d4db10d94cb6bbf2e9cd80a3f8c318541","sha256:43bfbbc6ab731143bde79aef24a9d111fa02f88fd09ad3d3e876fe5d89595bed"],"state_sha256":"62edc156396ca05391ab758fb73f2a741de446c4daed057fc7cef36b5764d214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5IeJDuMN2CiPmISFrjWthaOvRz4wLKxYtnlCVf5ZLb/IyiCHRWAZ+CKQpNIU5rm2sIxnKQc0d2XSVkmxMBeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T05:43:02.155369Z","bundle_sha256":"ebce618aa08d7e01705879a2517fd447c8593b0e985b9353111ed001fdefc90f"}}