{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4RRM4ZJAAS77XZO2SNKR5KRDMJ","short_pith_number":"pith:4RRM4ZJA","canonical_record":{"source":{"id":"1805.07918","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8","abstract_canon_sha256":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4"},"schema_version":"1.0"},"canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","source":{"kind":"arxiv","id":"1805.07918","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07918v6","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"4RRM4ZJAAS77","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"4RRM4ZJAAS77XZO2","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"4RRM4ZJA","created_at":"2026-07-05T00:58:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4RRM4ZJAAS77XZO2SNKR5KRDMJ","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07918","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8","abstract_canon_sha256":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4"},"schema_version":"1.0"},"canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:30.668809Z","signature_b64":"w9P1csuMoZTCSq7JV/y56OvKMcHguNjzJGp6iSbKA6C6P2yHkWyF0WIuxQu6ynLhpxP+8iFWHo6F1xTgu2cUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","last_reissued_at":"2026-07-05T00:58:30.668214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:30.668214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07918","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PY4ylG2ocvDYQLL41nUIsUL4B6fn7Z7xpSEo7PUHZKPGKtMjZUC+xoQUGV4tw5uJPlkV1W3u1h6mJ0HQ1vbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:21:51.679761Z"},"content_sha256":"8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626","schema_version":"1.0","event_id":"sha256:8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4RRM4ZJAAS77XZO2SNKR5KRDMJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Primal-Dual Distributed Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Donghwan Lee, Jianghai Hu","submitted_at":"2018-05-21T06:56:04Z","abstract_excerpt":"The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement learning (RL) algorithm that learns an infinite horizon discounted cost function (or value function) for a given fixed policy without the model knowledge. In the multi-agent MDP each agent receives a local reward through a local processing. The agents communicate over sparse and random networks to learn the global value function corresponding to the aggregate of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07918","kind":"arxiv","version":6},"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/1805.07918/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":"2026-07-05T00:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgccGfAuygvOXbhBMujbrEFETedD2zLnKue5qmoUEqUqQ19xlk5WfAfXvWJZIOfpT1OjK6SlCtXOk5+LTN/wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:21:51.680852Z"},"content_sha256":"52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee","schema_version":"1.0","event_id":"sha256:52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/bundle.json","state_url":"https://pith.science/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/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":"2026-08-15T02:21:51Z","links":{"resolver":"https://pith.science/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ","bundle":"https://pith.science/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/bundle.json","state":"https://pith.science/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RRM4ZJAAS77XZO2SNKR5KRDMJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4RRM4ZJAAS77XZO2SNKR5KRDMJ","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":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8"},"schema_version":"1.0","source":{"id":"1805.07918","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07918v6","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"4RRM4ZJAAS77","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"4RRM4ZJAAS77XZO2","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"4RRM4ZJA","created_at":"2026-07-05T00:58:30Z"}],"graph_snapshots":[{"event_id":"sha256:52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee","target":"graph","created_at":"2026-07-05T00:58:30Z","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/1805.07918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement learning (RL) algorithm that learns an infinite horizon discounted cost function (or value function) for a given fixed policy without the model knowledge. In the multi-agent MDP each agent receives a local reward through a local processing. The agents communicate over sparse and random networks to learn the global value function corresponding to the aggregate of","authors_text":"Donghwan Lee, Jianghai Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title":"Primal-Dual Distributed Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07918","kind":"arxiv","version":6},"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":"sha256:8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626","target":"record","created_at":"2026-07-05T00:58:30Z","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":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8"},"schema_version":"1.0","source":{"id":"1805.07918","kind":"arxiv","version":6}},"canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","first_computed_at":"2026-07-05T00:58:30.668214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:30.668214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w9P1csuMoZTCSq7JV/y56OvKMcHguNjzJGp6iSbKA6C6P2yHkWyF0WIuxQu6ynLhpxP+8iFWHo6F1xTgu2cUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:30.668809Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07918","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626","sha256:52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee"],"state_sha256":"966e2a1e89060e7bed859fdebfa33bf6c216c897474e79e0ce26643711cd0099"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sp3+OYWWr8vbmsSpOaUOJDF0cSSLIi9H75UkbsppuOxtMnwNbw+DztnU4ScC/Cvf6roWx5TYU1JGhd8JsEx7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:21:51.690047Z","bundle_sha256":"4930e63ea132e3fca436ddbad9e716ec9a2f0eae440b2dd7dd319fbf8bc8132c"}}