{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MBXQASGDISW4ZDSFKKR45WO3NN","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":"edeedce99e127960f674cd8ab615e6fbafc8b0dad5ef447fcff08a69c16e99d0","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-25T16:24:59Z","title_canon_sha256":"cb1f00c1e5dc8378790e6426e735fe837141644fa5b1db39c8f848bc14a13bc5"},"schema_version":"1.0","source":{"id":"2005.12729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.12729","created_at":"2026-07-05T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2005.12729v1","created_at":"2026-07-05T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.12729","created_at":"2026-07-05T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"MBXQASGDISW4","created_at":"2026-07-05T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"MBXQASGDISW4ZDSF","created_at":"2026-07-05T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"MBXQASGD","created_at":"2026-07-05T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:d49cebad4d2cd34851de7f46e4417eaf5223bc4a4a142a84d381ebc55cd277cb","target":"graph","created_at":"2026-07-05T01:05:56Z","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/2005.12729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO). Specifically, we investigate the consequences of \"code-level optimizations:\" algorithm augmentations found only in implementations or described as auxiliary details to the core algorithm. Seemingly of secondary importance, such optimizations turn out to have a major impact on agent behavior. Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO,","authors_text":"Aleksander Madry, Andrew Ilyas, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Logan Engstrom, Shibani Santurkar","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-25T16:24:59Z","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.12729","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":"sha256:258b186f64f0548896e83a9a89034e20349cecfda3647dac9fb5d67092a938f5","target":"record","created_at":"2026-07-05T01:05:56Z","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":"edeedce99e127960f674cd8ab615e6fbafc8b0dad5ef447fcff08a69c16e99d0","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-25T16:24:59Z","title_canon_sha256":"cb1f00c1e5dc8378790e6426e735fe837141644fa5b1db39c8f848bc14a13bc5"},"schema_version":"1.0","source":{"id":"2005.12729","kind":"arxiv","version":1}},"canonical_sha256":"606f0048c344adcc8e4552a3ced9db6b78d6cd700fb2e96b1f1acec5a3c75ac5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"606f0048c344adcc8e4552a3ced9db6b78d6cd700fb2e96b1f1acec5a3c75ac5","first_computed_at":"2026-07-05T01:05:56.920631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:56.920631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RdLi93YgU313kUEBGx4X+N0RPNVUnWZjmAHSv/w8cbT2dUaV79iz5vhANMq8N8juuAE/EJ1pUkNvQIMQaBxQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:56.921157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.12729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:258b186f64f0548896e83a9a89034e20349cecfda3647dac9fb5d67092a938f5","sha256:d49cebad4d2cd34851de7f46e4417eaf5223bc4a4a142a84d381ebc55cd277cb"],"state_sha256":"36189d3dda5d27ff25e382c9c7c46385ee912c5977ffb6bd16f71f1fbad283ec"}