{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YZTWFDKPVSL7XPSGZZ4J5FYQYN","short_pith_number":"pith:YZTWFDKP","canonical_record":{"source":{"id":"2405.20467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T20:29:52Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a2c02e33947c0630bc85045af7c377c5fe10c54a26a4756baaef8a9eb2e44334","abstract_canon_sha256":"d5d56e0a83bd3b0c8fab02c1a14dfe155dd7015c0ef4ba2e86ec9dca16073753"},"schema_version":"1.0"},"canonical_sha256":"c667628d4fac97fbbe46ce789e9710c35f346cb00c878eced85804e14ece7f4e","source":{"kind":"arxiv","id":"2405.20467","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20467","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20467v2","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20467","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"YZTWFDKPVSL7","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"YZTWFDKPVSL7XPSG","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"YZTWFDKP","created_at":"2026-07-05T09:09:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YZTWFDKPVSL7XPSGZZ4J5FYQYN","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T20:29:52Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a2c02e33947c0630bc85045af7c377c5fe10c54a26a4756baaef8a9eb2e44334","abstract_canon_sha256":"d5d56e0a83bd3b0c8fab02c1a14dfe155dd7015c0ef4ba2e86ec9dca16073753"},"schema_version":"1.0"},"canonical_sha256":"c667628d4fac97fbbe46ce789e9710c35f346cb00c878eced85804e14ece7f4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:22.921679Z","signature_b64":"JIPqd4pyHBZn/50casxOmIq2L4hsWqwRKfMfvonlmhKpCE77NHElmJsn3D5KuobbmZr0xIGOKh3D5sFyXxUZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c667628d4fac97fbbe46ce789e9710c35f346cb00c878eced85804e14ece7f4e","last_reissued_at":"2026-07-05T09:09:22.921185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:22.921185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20467","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":"2026-07-05T09:09:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocSZIAS7IcUMe2Yz8EkuLaAdAM+5gd6aJUca+cpE1wWsBSljILG9gp12MGaKL0+7lHN3fHNZtZrzr0rfUMyKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:40:52.196206Z"},"content_sha256":"1f7351109d4a9691a24c28c21ed6589182bf6d3e41bcdb85dd7a947ca9ef58ca","schema_version":"1.0","event_id":"sha256:1f7351109d4a9691a24c28c21ed6589182bf6d3e41bcdb85dd7a947ca9ef58ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YZTWFDKPVSL7XPSGZZ4J5FYQYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Performance of NPG in Countable State-Space Average-Cost RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Isaac Grosof, R. Srikant, Siva Theja Maguluri, Yashaswini Murthy","submitted_at":"2024-05-30T20:29:52Z","abstract_excerpt":"We consider policy optimization methods in reinforcement learning settings where the state space is arbitrarily large, or even countably infinite. The motivation arises from control problems in communication networks, matching markets, and other queueing systems. Specifically, we consider the popular Natural Policy Gradient (NPG) algorithm, which has been studied in the past only under the assumption that the cost is bounded and the state space is finite, neither of which holds for the aforementioned control problems. Assuming a Lyapunov drift condition, which is naturally satisfied in some ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20467","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/2405.20467/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":"2026-07-05T09:09:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkBX/va4kiNMHJcDTfndwyfTWxx8Xv44kuVaH1+ZA/nz4xAE/iRVpLAiYerEHoPiNRLYc/2kUOcP6JAPtKj8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:40:52.196600Z"},"content_sha256":"78bfde043c318d5012cf0ceb1bd5b3761d688c43c9d13d20934132eb7e44cf58","schema_version":"1.0","event_id":"sha256:78bfde043c318d5012cf0ceb1bd5b3761d688c43c9d13d20934132eb7e44cf58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/bundle.json","state_url":"https://pith.science/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/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":"2026-07-05T14:40:52Z","links":{"resolver":"https://pith.science/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN","bundle":"https://pith.science/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/bundle.json","state":"https://pith.science/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZTWFDKPVSL7XPSGZZ4J5FYQYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YZTWFDKPVSL7XPSGZZ4J5FYQYN","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":"d5d56e0a83bd3b0c8fab02c1a14dfe155dd7015c0ef4ba2e86ec9dca16073753","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T20:29:52Z","title_canon_sha256":"a2c02e33947c0630bc85045af7c377c5fe10c54a26a4756baaef8a9eb2e44334"},"schema_version":"1.0","source":{"id":"2405.20467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20467","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20467v2","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20467","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"YZTWFDKPVSL7","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"YZTWFDKPVSL7XPSG","created_at":"2026-07-05T09:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"YZTWFDKP","created_at":"2026-07-05T09:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:78bfde043c318d5012cf0ceb1bd5b3761d688c43c9d13d20934132eb7e44cf58","target":"graph","created_at":"2026-07-05T09:09:22Z","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/2405.20467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider policy optimization methods in reinforcement learning settings where the state space is arbitrarily large, or even countably infinite. The motivation arises from control problems in communication networks, matching markets, and other queueing systems. Specifically, we consider the popular Natural Policy Gradient (NPG) algorithm, which has been studied in the past only under the assumption that the cost is bounded and the state space is finite, neither of which holds for the aforementioned control problems. Assuming a Lyapunov drift condition, which is naturally satisfied in some ca","authors_text":"Isaac Grosof, R. Srikant, Siva Theja Maguluri, Yashaswini Murthy","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T20:29:52Z","title":"Performance of NPG in Countable State-Space Average-Cost RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20467","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":"sha256:1f7351109d4a9691a24c28c21ed6589182bf6d3e41bcdb85dd7a947ca9ef58ca","target":"record","created_at":"2026-07-05T09:09:22Z","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":"d5d56e0a83bd3b0c8fab02c1a14dfe155dd7015c0ef4ba2e86ec9dca16073753","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T20:29:52Z","title_canon_sha256":"a2c02e33947c0630bc85045af7c377c5fe10c54a26a4756baaef8a9eb2e44334"},"schema_version":"1.0","source":{"id":"2405.20467","kind":"arxiv","version":2}},"canonical_sha256":"c667628d4fac97fbbe46ce789e9710c35f346cb00c878eced85804e14ece7f4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c667628d4fac97fbbe46ce789e9710c35f346cb00c878eced85804e14ece7f4e","first_computed_at":"2026-07-05T09:09:22.921185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:22.921185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JIPqd4pyHBZn/50casxOmIq2L4hsWqwRKfMfvonlmhKpCE77NHElmJsn3D5KuobbmZr0xIGOKh3D5sFyXxUZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:22.921679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f7351109d4a9691a24c28c21ed6589182bf6d3e41bcdb85dd7a947ca9ef58ca","sha256:78bfde043c318d5012cf0ceb1bd5b3761d688c43c9d13d20934132eb7e44cf58"],"state_sha256":"89a2b0f4b13b0a4f6663534e668d7ac9a27b4b07bbab4015dd3d07fbe00d2c37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSnFRwX+kh1htAvS7odMaaM1SnNXdKgvbF3xLbAQHQphb6gg4W8Wq7NU2r8S4eiIG5UbtUwXkXGx9ccbTK9QAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:40:52.198784Z","bundle_sha256":"e01522206dfc7813440904d5bc5ef663d390b9f23f21184c327b5fa766a747fe"}}