{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:M6DH4GMVHBSD5V4PGSGCBDISEQ","short_pith_number":"pith:M6DH4GMV","canonical_record":{"source":{"id":"1709.03465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-09-11T16:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"5560d7ac583e1b99ded51149ba24f8e530b43ebe646e29b35ed3e9056cc4ccb7","abstract_canon_sha256":"a5c0373893284fb6e88fa8ce4a295a7b3e5a1c4deb86ca8ffdea5c0ec63fa938"},"schema_version":"1.0"},"canonical_sha256":"67867e199538643ed78f348c208d12243004e7027a8f16f287a2bc71cbbb5464","source":{"kind":"arxiv","id":"1709.03465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03465","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03465v1","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03465","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"M6DH4GMVHBSD","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"M6DH4GMVHBSD5V4P","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"M6DH4GMV","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:M6DH4GMVHBSD5V4PGSGCBDISEQ","target":"record","payload":{"canonical_record":{"source":{"id":"1709.03465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-09-11T16:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"5560d7ac583e1b99ded51149ba24f8e530b43ebe646e29b35ed3e9056cc4ccb7","abstract_canon_sha256":"a5c0373893284fb6e88fa8ce4a295a7b3e5a1c4deb86ca8ffdea5c0ec63fa938"},"schema_version":"1.0"},"canonical_sha256":"67867e199538643ed78f348c208d12243004e7027a8f16f287a2bc71cbbb5464","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:36.650166Z","signature_b64":"NY+25pjHJF1gkCqfps8bvUg19sLfBR8Oo0Ic34arYarnb+u3iSoiJ6kJxhQhU2c1EVcjcuoiYrRGEzI7tZoOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67867e199538643ed78f348c208d12243004e7027a8f16f287a2bc71cbbb5464","last_reissued_at":"2026-05-18T00:35:36.649770Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:36.649770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.03465","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHRIXaqvC5v5FWUytlZ1KHVxp08iZODNHqGmOa83zS+1wderHpOezCqT2Lf9yeGAoShTXt4+abSy35GmKE4YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:44:06.233931Z"},"content_sha256":"f3b8b94ed4fa8daa92f929f4c4714111167d522b76dfda58ffb6ac558e8bf7e9","schema_version":"1.0","event_id":"sha256:f3b8b94ed4fa8daa92f929f4c4714111167d522b76dfda58ffb6ac558e8bf7e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:M6DH4GMVHBSD5V4PGSGCBDISEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Learning in Weakly Coupled Markov Decision Processes: A Convergence Time Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hao Yu, Michael J. Neely, Xiaohan Wei","submitted_at":"2017-09-11T16:20:24Z","abstract_excerpt":"We consider multiple parallel Markov decision processes (MDPs) coupled by global constraints, where the time varying objective and constraint functions can only be observed after the decision is made. Special attention is given to how well the decision maker can perform in $T$ slots, starting from any state, compared to the best feasible randomized stationary policy in hindsight. We develop a new distributed online algorithm where each MDP makes its own decision each slot after observing a multiplier computed from past information. While the scenario is significantly more challenging than the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03465","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"koNru+arDK6YG5b1eoU1xPskjXJ+kHLCsKFGsqaZ93Ba5XNkE2NaHXHD+Zfo2zcSGI8kIKjpMhJ2Ot845BcIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:44:06.234673Z"},"content_sha256":"10c7d150ee0a8d9c0b07de49d26a65a63250a4007a7aad4b84ec878ca3383c36","schema_version":"1.0","event_id":"sha256:10c7d150ee0a8d9c0b07de49d26a65a63250a4007a7aad4b84ec878ca3383c36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/bundle.json","state_url":"https://pith.science/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/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":"2026-05-30T17:44:06Z","links":{"resolver":"https://pith.science/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ","bundle":"https://pith.science/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/bundle.json","state":"https://pith.science/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6DH4GMVHBSD5V4PGSGCBDISEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:M6DH4GMVHBSD5V4PGSGCBDISEQ","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":"a5c0373893284fb6e88fa8ce4a295a7b3e5a1c4deb86ca8ffdea5c0ec63fa938","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-09-11T16:20:24Z","title_canon_sha256":"5560d7ac583e1b99ded51149ba24f8e530b43ebe646e29b35ed3e9056cc4ccb7"},"schema_version":"1.0","source":{"id":"1709.03465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03465","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03465v1","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03465","created_at":"2026-05-18T00:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"M6DH4GMVHBSD","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"M6DH4GMVHBSD5V4P","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"M6DH4GMV","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:10c7d150ee0a8d9c0b07de49d26a65a63250a4007a7aad4b84ec878ca3383c36","target":"graph","created_at":"2026-05-18T00:35:36Z","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"},"paper":{"abstract_excerpt":"We consider multiple parallel Markov decision processes (MDPs) coupled by global constraints, where the time varying objective and constraint functions can only be observed after the decision is made. Special attention is given to how well the decision maker can perform in $T$ slots, starting from any state, compared to the best feasible randomized stationary policy in hindsight. We develop a new distributed online algorithm where each MDP makes its own decision each slot after observing a multiplier computed from past information. While the scenario is significantly more challenging than the ","authors_text":"Hao Yu, Michael J. Neely, Xiaohan Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-09-11T16:20:24Z","title":"Online Learning in Weakly Coupled Markov Decision Processes: A Convergence Time Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03465","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:f3b8b94ed4fa8daa92f929f4c4714111167d522b76dfda58ffb6ac558e8bf7e9","target":"record","created_at":"2026-05-18T00:35:36Z","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":"a5c0373893284fb6e88fa8ce4a295a7b3e5a1c4deb86ca8ffdea5c0ec63fa938","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-09-11T16:20:24Z","title_canon_sha256":"5560d7ac583e1b99ded51149ba24f8e530b43ebe646e29b35ed3e9056cc4ccb7"},"schema_version":"1.0","source":{"id":"1709.03465","kind":"arxiv","version":1}},"canonical_sha256":"67867e199538643ed78f348c208d12243004e7027a8f16f287a2bc71cbbb5464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67867e199538643ed78f348c208d12243004e7027a8f16f287a2bc71cbbb5464","first_computed_at":"2026-05-18T00:35:36.649770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:36.649770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NY+25pjHJF1gkCqfps8bvUg19sLfBR8Oo0Ic34arYarnb+u3iSoiJ6kJxhQhU2c1EVcjcuoiYrRGEzI7tZoOCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:36.650166Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3b8b94ed4fa8daa92f929f4c4714111167d522b76dfda58ffb6ac558e8bf7e9","sha256:10c7d150ee0a8d9c0b07de49d26a65a63250a4007a7aad4b84ec878ca3383c36"],"state_sha256":"57fb35ebaf2882fc6ecf1ce44f94687f2151918c2c7f0a09b642cf9331efada7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXmh1V5JN9lRLtlquXV6M4N4Fdi8Ct/nMWR2CvD6511yR08GcZPv3k+gi6SOjaoU9QGkEkkG62cpwK8fz865Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:44:06.238615Z","bundle_sha256":"c01a8c880d9ce846e733f4e992723b28f5c62f78940c0c300e2dafb05cb28d30"}}