{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CU3TPNESBX3GX7O3XWYFFDOCEL","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":"e5a1954f4a01add193370b733a91f2c5bbd3cf9e5e06f5d1ec0f450e5d585916","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T05:55:56Z","title_canon_sha256":"91c14ecee8b252cd48cb2247cceb265c33f808b0bc6e3a77e8add2e737c9286f"},"schema_version":"1.0","source":{"id":"1908.01275","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01275","created_at":"2026-07-05T00:02:28Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01275v3","created_at":"2026-07-05T00:02:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01275","created_at":"2026-07-05T00:02:28Z"},{"alias_kind":"pith_short_12","alias_value":"CU3TPNESBX3G","created_at":"2026-07-05T00:02:28Z"},{"alias_kind":"pith_short_16","alias_value":"CU3TPNESBX3GX7O3","created_at":"2026-07-05T00:02:28Z"},{"alias_kind":"pith_short_8","alias_value":"CU3TPNES","created_at":"2026-07-05T00:02:28Z"}],"graph_snapshots":[{"event_id":"sha256:3cbe914c237358e687999a7c8d4f07c864a33f9ff91317b7cc4fca04a59f9faf","target":"graph","created_at":"2026-07-05T00:02:28Z","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/1908.01275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often sequentially aggregated reward, are often inherently reinforcement learning problems and present the opportunity to leverage the recent substantial advances in deep reinforcement learning. However, in some cases, it is not clear why deep reinforcement learning is a good fit for the problem. Sometimes, it does not perform better than the state-of-the-art solutions. And in other cases, random search or greedy algorithms cou","authors_text":"Ameer Haj-Ali, Ion Stoica, Joseph Gonzalez, Krste Asanovic, Nesreen K. Ahmed, Ted Willke","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T05:55:56Z","title":"A View on Deep Reinforcement Learning in System Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01275","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":"sha256:8de4857b50c2760a32574b1b7c4ccac86eef91d1bfb439fd15ee7b40262810a6","target":"record","created_at":"2026-07-05T00:02:28Z","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":"e5a1954f4a01add193370b733a91f2c5bbd3cf9e5e06f5d1ec0f450e5d585916","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T05:55:56Z","title_canon_sha256":"91c14ecee8b252cd48cb2247cceb265c33f808b0bc6e3a77e8add2e737c9286f"},"schema_version":"1.0","source":{"id":"1908.01275","kind":"arxiv","version":3}},"canonical_sha256":"153737b4920df66bfddbbdb0528dc222fe51bc8f660e037e49d9b88aa03688dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"153737b4920df66bfddbbdb0528dc222fe51bc8f660e037e49d9b88aa03688dd","first_computed_at":"2026-07-05T00:02:28.193828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:28.193828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y89qIAxYwb4Vlc9f2sKbchgdCSLdn8qBqWAZKKhkkyNJjjDOtUjAGNxQUImMAXtmkvrAZmQJt+YSJOpaCBROAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:28.194286Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01275","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8de4857b50c2760a32574b1b7c4ccac86eef91d1bfb439fd15ee7b40262810a6","sha256:3cbe914c237358e687999a7c8d4f07c864a33f9ff91317b7cc4fca04a59f9faf"],"state_sha256":"0a9abe50e25a315aa483ac03bf23df3e6ebc111702872ace42d62f74c56e06bf"}