{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:VIPIYBMFNXHZ7SIBOMVCAIBLM5","short_pith_number":"pith:VIPIYBMF","canonical_record":{"source":{"id":"2003.00433","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-01T08:12:08Z","cross_cats_sorted":["cs.MA","math.OC","stat.ML"],"title_canon_sha256":"1f8a5e4fa422640e0bb3e712872bcc0169aa165837ba7aa6ad551b611bf43148","abstract_canon_sha256":"29056c84a3345b3692ea5b9966ffab2acef8b5a7adad6f49e61649d881275d21"},"schema_version":"1.0"},"canonical_sha256":"aa1e8c05856dcf9fc901732a20202b6743fe2ccfb1ec579c409eb1481299d4e0","source":{"kind":"arxiv","id":"2003.00433","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00433","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00433v3","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00433","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"VIPIYBMFNXHZ","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"VIPIYBMFNXHZ7SIB","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"VIPIYBMF","created_at":"2026-07-05T02:08:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:VIPIYBMFNXHZ7SIBOMVCAIBLM5","target":"record","payload":{"canonical_record":{"source":{"id":"2003.00433","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-01T08:12:08Z","cross_cats_sorted":["cs.MA","math.OC","stat.ML"],"title_canon_sha256":"1f8a5e4fa422640e0bb3e712872bcc0169aa165837ba7aa6ad551b611bf43148","abstract_canon_sha256":"29056c84a3345b3692ea5b9966ffab2acef8b5a7adad6f49e61649d881275d21"},"schema_version":"1.0"},"canonical_sha256":"aa1e8c05856dcf9fc901732a20202b6743fe2ccfb1ec579c409eb1481299d4e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:48.094255Z","signature_b64":"s53V0kklOJgeJNv04y5UmW/9W9u2b+mCcBMJ3F40K7wn24Irx01nv2B4FaG83oGnE94CmCCOE6/6Z6QCkaQhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1e8c05856dcf9fc901732a20202b6743fe2ccfb1ec579c409eb1481299d4e0","last_reissued_at":"2026-07-05T02:08:48.093770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:48.093770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.00433","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":"2026-07-05T02:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLrjYDRV61K5OiqMt1RcFgJsVLYWIVnJMG449eyHeHT4wLCxFd9f+Yo6BGmNg2fPUL3lIJoPKK8qc/CK7sSdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:59:32.719813Z"},"content_sha256":"97ba42f8df98986368af5d0a6121d752210a391f2ecf6cb994df1e74d39313d7","schema_version":"1.0","event_id":"sha256:97ba42f8df98986368af5d0a6121d752210a391f2ecf6cb994df1e74d39313d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:VIPIYBMFNXHZ7SIBOMVCAIBLM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fully Asynchronous Policy Evaluation in Distributed Reinforcement Learning over Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaqi Zhang, Kaiqing Zhang, Keyou You, Tamer Ba\\c{s}ar, Xingyu Sha","submitted_at":"2020-03-01T08:12:08Z","abstract_excerpt":"This paper proposes a \\emph{fully asynchronous} scheme for the policy evaluation problem of distributed reinforcement learning (DisRL) over directed peer-to-peer networks. Without waiting for any other node of the network, each node can locally update its value function at any time by using (possibly delayed) information from its neighbors. This is in sharp contrast to the gossip-based scheme where a pair of nodes concurrently update. Though the fully asynchronous setting involves a difficult multi-timescale decision problem, we design a novel stochastic average gradient (SAG) based distribute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00433","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/2003.00433/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":"2026-07-05T02:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+3FbDSIOamKBta+XmJyoE9FqRhdEsu3CoLVouzGkl/U+tC2WpHgnyiu/sPvAGIhBZlAhXfFtf3Xj/3dWYvTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:59:32.720321Z"},"content_sha256":"3c5ef8e7595d71b3eb6d31606fa0270eb5d2a31bc0f07992444664783b98b0d6","schema_version":"1.0","event_id":"sha256:3c5ef8e7595d71b3eb6d31606fa0270eb5d2a31bc0f07992444664783b98b0d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/bundle.json","state_url":"https://pith.science/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/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":"2026-08-15T04:59:32Z","links":{"resolver":"https://pith.science/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5","bundle":"https://pith.science/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/bundle.json","state":"https://pith.science/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIPIYBMFNXHZ7SIBOMVCAIBLM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VIPIYBMFNXHZ7SIBOMVCAIBLM5","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":"29056c84a3345b3692ea5b9966ffab2acef8b5a7adad6f49e61649d881275d21","cross_cats_sorted":["cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-01T08:12:08Z","title_canon_sha256":"1f8a5e4fa422640e0bb3e712872bcc0169aa165837ba7aa6ad551b611bf43148"},"schema_version":"1.0","source":{"id":"2003.00433","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00433","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00433v3","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00433","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"VIPIYBMFNXHZ","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"VIPIYBMFNXHZ7SIB","created_at":"2026-07-05T02:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"VIPIYBMF","created_at":"2026-07-05T02:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:3c5ef8e7595d71b3eb6d31606fa0270eb5d2a31bc0f07992444664783b98b0d6","target":"graph","created_at":"2026-07-05T02:08:48Z","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/2003.00433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a \\emph{fully asynchronous} scheme for the policy evaluation problem of distributed reinforcement learning (DisRL) over directed peer-to-peer networks. Without waiting for any other node of the network, each node can locally update its value function at any time by using (possibly delayed) information from its neighbors. This is in sharp contrast to the gossip-based scheme where a pair of nodes concurrently update. Though the fully asynchronous setting involves a difficult multi-timescale decision problem, we design a novel stochastic average gradient (SAG) based distribute","authors_text":"Jiaqi Zhang, Kaiqing Zhang, Keyou You, Tamer Ba\\c{s}ar, Xingyu Sha","cross_cats":["cs.MA","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-01T08:12:08Z","title":"Fully Asynchronous Policy Evaluation in Distributed Reinforcement Learning over Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00433","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":"sha256:97ba42f8df98986368af5d0a6121d752210a391f2ecf6cb994df1e74d39313d7","target":"record","created_at":"2026-07-05T02:08:48Z","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":"29056c84a3345b3692ea5b9966ffab2acef8b5a7adad6f49e61649d881275d21","cross_cats_sorted":["cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-01T08:12:08Z","title_canon_sha256":"1f8a5e4fa422640e0bb3e712872bcc0169aa165837ba7aa6ad551b611bf43148"},"schema_version":"1.0","source":{"id":"2003.00433","kind":"arxiv","version":3}},"canonical_sha256":"aa1e8c05856dcf9fc901732a20202b6743fe2ccfb1ec579c409eb1481299d4e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa1e8c05856dcf9fc901732a20202b6743fe2ccfb1ec579c409eb1481299d4e0","first_computed_at":"2026-07-05T02:08:48.093770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:48.093770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s53V0kklOJgeJNv04y5UmW/9W9u2b+mCcBMJ3F40K7wn24Irx01nv2B4FaG83oGnE94CmCCOE6/6Z6QCkaQhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:48.094255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.00433","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97ba42f8df98986368af5d0a6121d752210a391f2ecf6cb994df1e74d39313d7","sha256:3c5ef8e7595d71b3eb6d31606fa0270eb5d2a31bc0f07992444664783b98b0d6"],"state_sha256":"1f6211ade2cd038a7d9dde668d7cd225bbb89676b89fb3a09922490beb017453"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7w9oFGweCLT+pVpBg0SCyVDRcE8YeApX1kGtKE5QdvuUJm/uygGRKdu8UOqqkRZLQ0c2ACS/LvBGHVPE71/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:59:32.723933Z","bundle_sha256":"8cf3ea27a363d05c8189775876d347f77912b39f5df2d4c1eff16233a847dc7d"}}