{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XBDUYQUHL3WNAKTNOLMR4ZZMCP","short_pith_number":"pith:XBDUYQUH","canonical_record":{"source":{"id":"1912.00167","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-30T09:44:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca8f69787cc15ce37829861746023530431b0cfaf3ab8291d94d41ed5ae34b29","abstract_canon_sha256":"e53a8adc929807fba033c4c35871fc62c690e84a23aca698a40d3c8852cb5c4a"},"schema_version":"1.0"},"canonical_sha256":"b8474c42875eecd02a6d72d91e672c13dad9caf805fb5442b16f96ae7750d9cf","source":{"kind":"arxiv","id":"1912.00167","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00167","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00167v3","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00167","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"XBDUYQUHL3WN","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_16","alias_value":"XBDUYQUHL3WNAKTN","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_8","alias_value":"XBDUYQUH","created_at":"2026-07-05T00:35:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XBDUYQUHL3WNAKTNOLMR4ZZMCP","target":"record","payload":{"canonical_record":{"source":{"id":"1912.00167","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-30T09:44:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca8f69787cc15ce37829861746023530431b0cfaf3ab8291d94d41ed5ae34b29","abstract_canon_sha256":"e53a8adc929807fba033c4c35871fc62c690e84a23aca698a40d3c8852cb5c4a"},"schema_version":"1.0"},"canonical_sha256":"b8474c42875eecd02a6d72d91e672c13dad9caf805fb5442b16f96ae7750d9cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:10.559401Z","signature_b64":"3D7ciDQ0Vfs9LS5sYgEtriVa8RMNCPiLkUyWJWhTHXTBod3aySvHg3cyEc2fNWVocnym+g9qOGA8WUH3guO+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8474c42875eecd02a6d72d91e672c13dad9caf805fb5442b16f96ae7750d9cf","last_reissued_at":"2026-07-05T00:35:10.558898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:10.558898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.00167","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":"2026-07-05T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPQ0A9vACefXuvAsnTkP8benouA0vfTAp6HLm4ulrYf71yRFz9pzqYvduOOnvWt1XEP58e7cDSd9iaG2ypXDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:46:28.137598Z"},"content_sha256":"70e2d11c0ddfe335a2b9fcf6303064e7ce932b78d6a34ec964e3068df6e32823","schema_version":"1.0","event_id":"sha256:70e2d11c0ddfe335a2b9fcf6303064e7ce932b78d6a34ec964e3068df6e32823"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XBDUYQUHL3WNAKTNOLMR4ZZMCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Liang, Ion Stoica, Jiahao Yao, Michael Luo, Richard Liaw","submitted_at":"2019-11-30T09:44:19Z","abstract_excerpt":"The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learning (RL) often tradeoff between the throughput of samples that an RL agent can learn from (sample throughput) and the quality of learning from each sample (sample efficiency). In these scalable RL architectures, as one increases sample throughput (i.e. increasing parallelization in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00167","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/1912.00167/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":"2026-07-05T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZHrgHCCEB3pcwGOjvgraev2BdIUdL0xekCBJEQp5c8ixvPtin1vi/NExXS2jF+2AsvD4NkhV+uQkSsQ/sYbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:46:28.138156Z"},"content_sha256":"c0e4ec2c8f9e7789cd8ea013d6d7253db07688c789da053d567a2b23c2d05cb0","schema_version":"1.0","event_id":"sha256:c0e4ec2c8f9e7789cd8ea013d6d7253db07688c789da053d567a2b23c2d05cb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/bundle.json","state_url":"https://pith.science/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/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":"2026-08-22T12:46:28Z","links":{"resolver":"https://pith.science/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP","bundle":"https://pith.science/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/bundle.json","state":"https://pith.science/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBDUYQUHL3WNAKTNOLMR4ZZMCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XBDUYQUHL3WNAKTNOLMR4ZZMCP","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":"e53a8adc929807fba033c4c35871fc62c690e84a23aca698a40d3c8852cb5c4a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-30T09:44:19Z","title_canon_sha256":"ca8f69787cc15ce37829861746023530431b0cfaf3ab8291d94d41ed5ae34b29"},"schema_version":"1.0","source":{"id":"1912.00167","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00167","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00167v3","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00167","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"XBDUYQUHL3WN","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_16","alias_value":"XBDUYQUHL3WNAKTN","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_8","alias_value":"XBDUYQUH","created_at":"2026-07-05T00:35:10Z"}],"graph_snapshots":[{"event_id":"sha256:c0e4ec2c8f9e7789cd8ea013d6d7253db07688c789da053d567a2b23c2d05cb0","target":"graph","created_at":"2026-07-05T00:35:10Z","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/1912.00167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learning (RL) often tradeoff between the throughput of samples that an RL agent can learn from (sample throughput) and the quality of learning from each sample (sample efficiency). In these scalable RL architectures, as one increases sample throughput (i.e. increasing parallelization in","authors_text":"Eric Liang, Ion Stoica, Jiahao Yao, Michael Luo, Richard Liaw","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-30T09:44:19Z","title":"IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00167","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":"sha256:70e2d11c0ddfe335a2b9fcf6303064e7ce932b78d6a34ec964e3068df6e32823","target":"record","created_at":"2026-07-05T00:35:10Z","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":"e53a8adc929807fba033c4c35871fc62c690e84a23aca698a40d3c8852cb5c4a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-30T09:44:19Z","title_canon_sha256":"ca8f69787cc15ce37829861746023530431b0cfaf3ab8291d94d41ed5ae34b29"},"schema_version":"1.0","source":{"id":"1912.00167","kind":"arxiv","version":3}},"canonical_sha256":"b8474c42875eecd02a6d72d91e672c13dad9caf805fb5442b16f96ae7750d9cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8474c42875eecd02a6d72d91e672c13dad9caf805fb5442b16f96ae7750d9cf","first_computed_at":"2026-07-05T00:35:10.558898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:10.558898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3D7ciDQ0Vfs9LS5sYgEtriVa8RMNCPiLkUyWJWhTHXTBod3aySvHg3cyEc2fNWVocnym+g9qOGA8WUH3guO+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:10.559401Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00167","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70e2d11c0ddfe335a2b9fcf6303064e7ce932b78d6a34ec964e3068df6e32823","sha256:c0e4ec2c8f9e7789cd8ea013d6d7253db07688c789da053d567a2b23c2d05cb0"],"state_sha256":"ec3c8e9b6e8b1f980d9e5bab0d82074c3eca9fcbe62fab758dc65697778ffaed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOHF8oB8lND5YjLy76ixV6XN7ZzqFmvDwjLGsSj079ncTYsqF2OUCllOCy2JV6BQi5RgtMMdp9IMMqdBSwuRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:46:28.142874Z","bundle_sha256":"d7ea39ac744cabaca106191edd0e64920b1cb8398ae991375b8b0b6058c3ce57"}}