{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ICE2BBPNW6ENFUMR7FS3HRZOCY","short_pith_number":"pith:ICE2BBPN","canonical_record":{"source":{"id":"1908.02805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"b8d2a7ca2f4f9f6b5319b31c8d5dfd2a0cbe27cb421b9dfd96419fbc60d0edd6","abstract_canon_sha256":"fe79e7b58d59b285d76de49cbbf36c5e43324c93e77d311a089a08ece0efd213"},"schema_version":"1.0"},"canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","source":{"kind":"arxiv","id":"1908.02805","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02805","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02805v4","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02805","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_12","alias_value":"ICE2BBPNW6EN","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_16","alias_value":"ICE2BBPNW6ENFUMR","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_8","alias_value":"ICE2BBPN","created_at":"2026-07-05T03:29:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ICE2BBPNW6ENFUMR7FS3HRZOCY","target":"record","payload":{"canonical_record":{"source":{"id":"1908.02805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"b8d2a7ca2f4f9f6b5319b31c8d5dfd2a0cbe27cb421b9dfd96419fbc60d0edd6","abstract_canon_sha256":"fe79e7b58d59b285d76de49cbbf36c5e43324c93e77d311a089a08ece0efd213"},"schema_version":"1.0"},"canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:12.818215Z","signature_b64":"oH54tNjzulRXAnyiSX8XNAXOKCQonSr6A5taU07lbq02f8S1HeXx/BG9r52HE6uWDoPL+EFAMneyXxOLfxukDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","last_reissued_at":"2026-07-05T03:29:12.817791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:12.817791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.02805","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":"2026-07-05T03:29:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38Un+FYIOq/ZHk6Ehl+LsqyZdhOka97hQ+fTHhmgriQcVHgSRJmcT0QaYRQKwX2PBtS32FoYjnrH56HBtbNqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:16:57.702467Z"},"content_sha256":"8daab5885107d288ab90d7e7e8b87c72fb4fbd47ee7ccd12f55e4a661c08fd38","schema_version":"1.0","event_id":"sha256:8daab5885107d288ab90d7e7e8b87c72fb4fbd47ee7ccd12f55e4a661c08fd38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ICE2BBPNW6ENFUMR7FS3HRZOCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Dongsheng Ding, Mihailo R. Jovanovi\\'c, Xiaohan Wei, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-08-07T19:25:37Z","abstract_excerpt":"We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local computation and communication over a connected undirected network. This problem arises in various large-scale multi-agent systems, including power grids, intelligent transportation systems, wireless sensor networks, and multi-agent robotics. When the dimension of state-action space is large, the temporal-difference learning with linear function approximation i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02805","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/1908.02805/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":"2026-07-05T03:29:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tot7xlMXRI1Ih4qaApI6nBEh9BNKx1zKPCsYghz+gGdmS76WwZooZRGhXyl6IyYoo+gTJo5NNP6GbW1qAp+ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:16:57.703018Z"},"content_sha256":"5f917083ad8f8eb30c8c65ddec62364394b7e81177c49c9111dd948cd753ac0d","schema_version":"1.0","event_id":"sha256:5f917083ad8f8eb30c8c65ddec62364394b7e81177c49c9111dd948cd753ac0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/bundle.json","state_url":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/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":"2026-08-14T22:16:57Z","links":{"resolver":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY","bundle":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/bundle.json","state":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ICE2BBPNW6ENFUMR7FS3HRZOCY","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":"fe79e7b58d59b285d76de49cbbf36c5e43324c93e77d311a089a08ece0efd213","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","title_canon_sha256":"b8d2a7ca2f4f9f6b5319b31c8d5dfd2a0cbe27cb421b9dfd96419fbc60d0edd6"},"schema_version":"1.0","source":{"id":"1908.02805","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02805","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02805v4","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02805","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_12","alias_value":"ICE2BBPNW6EN","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_16","alias_value":"ICE2BBPNW6ENFUMR","created_at":"2026-07-05T03:29:12Z"},{"alias_kind":"pith_short_8","alias_value":"ICE2BBPN","created_at":"2026-07-05T03:29:12Z"}],"graph_snapshots":[{"event_id":"sha256:5f917083ad8f8eb30c8c65ddec62364394b7e81177c49c9111dd948cd753ac0d","target":"graph","created_at":"2026-07-05T03:29:12Z","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/1908.02805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local computation and communication over a connected undirected network. This problem arises in various large-scale multi-agent systems, including power grids, intelligent transportation systems, wireless sensor networks, and multi-agent robotics. When the dimension of state-action space is large, the temporal-difference learning with linear function approximation i","authors_text":"Dongsheng Ding, Mihailo R. Jovanovi\\'c, Xiaohan Wei, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","title":"Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02805","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":"sha256:8daab5885107d288ab90d7e7e8b87c72fb4fbd47ee7ccd12f55e4a661c08fd38","target":"record","created_at":"2026-07-05T03:29:12Z","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":"fe79e7b58d59b285d76de49cbbf36c5e43324c93e77d311a089a08ece0efd213","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","title_canon_sha256":"b8d2a7ca2f4f9f6b5319b31c8d5dfd2a0cbe27cb421b9dfd96419fbc60d0edd6"},"schema_version":"1.0","source":{"id":"1908.02805","kind":"arxiv","version":4}},"canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","first_computed_at":"2026-07-05T03:29:12.817791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:12.817791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oH54tNjzulRXAnyiSX8XNAXOKCQonSr6A5taU07lbq02f8S1HeXx/BG9r52HE6uWDoPL+EFAMneyXxOLfxukDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:12.818215Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02805","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8daab5885107d288ab90d7e7e8b87c72fb4fbd47ee7ccd12f55e4a661c08fd38","sha256:5f917083ad8f8eb30c8c65ddec62364394b7e81177c49c9111dd948cd753ac0d"],"state_sha256":"cc7537807d23e35bfb98733dbab81f3f3d3bdb54946c8221be2012410b34c09b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iLpJeFkmU5IDita54qGWfgDbI2x+vwd/UDtYRv1HLoD4dnRXKdVmO0pgcJIKR16nu0Z9UBbST4DBAq4ExFvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:16:57.706686Z","bundle_sha256":"b8c4c263b49c718f17d8d95d3112b69e8f9a7ce4cc7f079c04644ed301d84199"}}