{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KJ6HYHT67BJP76NQUMKT4X344K","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":"74d4ee2db386446f7cc7749987f9cf1d5a0fc36fcb055f3655eea5fcf9a1a72b","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T04:50:05Z","title_canon_sha256":"663d9550f94f1fec978ab0f75795cbcc4b337705a71ef6d7dd80e8363d3e7282"},"schema_version":"1.0","source":{"id":"2012.04210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04210","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04210v1","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04210","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"KJ6HYHT67BJP","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"KJ6HYHT67BJP76NQ","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"KJ6HYHT6","created_at":"2026-07-05T01:58:01Z"}],"graph_snapshots":[{"event_id":"sha256:96a8d19e86091167856cc21a26e2ab6343d09cfd7ce536c19c14c9dd01cd9b03","target":"graph","created_at":"2026-07-05T01:58:01Z","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/2012.04210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With deep reinforcement learning (RL) methods achieving results that exceed human capabilities in games, robotics, and simulated environments, continued scaling of RL training is crucial to its deployment in solving complex real-world problems. However, improving the performance scalability and power efficiency of RL training through understanding the architectural implications of CPU-GPU systems remains an open problem. In this work we investigate and improve the performance and power efficiency of distributed RL training on CPU-GPU systems by approaching the problem not solely from the GPU m","authors_text":"Ahmet Inci, David Nellans, Diana Marculescu, Evgeny Bolotin, Gal Dalal, Shie Mannor, Yaosheng Fu","cross_cats":["cs.AR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T04:50:05Z","title":"The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04210","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":"sha256:2daca5de731e5eafdc278bc9b14d50f760b76f8a5572075a36a34d011023e6b0","target":"record","created_at":"2026-07-05T01:58:01Z","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":"74d4ee2db386446f7cc7749987f9cf1d5a0fc36fcb055f3655eea5fcf9a1a72b","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T04:50:05Z","title_canon_sha256":"663d9550f94f1fec978ab0f75795cbcc4b337705a71ef6d7dd80e8363d3e7282"},"schema_version":"1.0","source":{"id":"2012.04210","kind":"arxiv","version":1}},"canonical_sha256":"527c7c1e7ef852fff9b0a3153e5f7ce2a04b2a7830957b8e6b9f8dd57172454f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527c7c1e7ef852fff9b0a3153e5f7ce2a04b2a7830957b8e6b9f8dd57172454f","first_computed_at":"2026-07-05T01:58:01.948628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:01.948628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LaZrVlZHeRcE/I0L3JyMPW9S11a0HNRS0ja9tp7BJydvDXqec/GamnT2NhZnxbfpltOOfQVVa8QlcFh6KzBCDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:01.948951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2daca5de731e5eafdc278bc9b14d50f760b76f8a5572075a36a34d011023e6b0","sha256:96a8d19e86091167856cc21a26e2ab6343d09cfd7ce536c19c14c9dd01cd9b03"],"state_sha256":"2558ab31713c5e63a50b65b9871dd328cd134b1eb6eb6fe144442f56a571d312"}