{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6D7RG46CQ6VRRP6FUEDAEOUO2L","short_pith_number":"pith:6D7RG46C","canonical_record":{"source":{"id":"2401.16025","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","cross_cats_sorted":[],"title_canon_sha256":"dbaa649a9567a809b7d8998c57dd5c8ab6100010972577e450b0b482f072af40","abstract_canon_sha256":"b3afd4ea3409e8e86bdfd9e500903077a57d95b5bc1f4b0454cd7596eb980358"},"schema_version":"1.0"},"canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","source":{"kind":"arxiv","id":"2401.16025","version":9},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16025","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16025v9","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16025","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"6D7RG46CQ6VR","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"6D7RG46CQ6VRRP6F","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"6D7RG46C","created_at":"2026-07-05T11:43:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6D7RG46CQ6VRRP6FUEDAEOUO2L","target":"record","payload":{"canonical_record":{"source":{"id":"2401.16025","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","cross_cats_sorted":[],"title_canon_sha256":"dbaa649a9567a809b7d8998c57dd5c8ab6100010972577e450b0b482f072af40","abstract_canon_sha256":"b3afd4ea3409e8e86bdfd9e500903077a57d95b5bc1f4b0454cd7596eb980358"},"schema_version":"1.0"},"canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:27.325644Z","signature_b64":"FcIt0rQzjKFVmy2bLtvAftvvP0nz75vDUgbAQK+aa84+x0wr1bavzU9pM+xdRu2wuuxPYjG6Kd3ul5GLziXaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","last_reissued_at":"2026-07-05T11:43:27.324968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:27.324968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.16025","source_version":9,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNP/KeQUre/RqJSHoliKUNjDve9E9slxPMiACxXUxS+p1A8pCiaOhz/ZpVQ4cZkZ7lu63wCwZxFJSn+g7IFZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:40:49.958763Z"},"content_sha256":"aaf7cab032f7aac096ad26f04676bb4733a86e183416550e91d07ea1d00102c8","schema_version":"1.0","event_id":"sha256:aaf7cab032f7aac096ad26f04676bb4733a86e183416550e91d07ea1d00102c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6D7RG46CQ6VRRP6FUEDAEOUO2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yang, Marco Hutter, Qiang Zhang, Renjing Xu, Zhengpeng Xie","submitted_at":"2024-01-29T10:17:54Z","abstract_excerpt":"Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust region, backed by strong theoretical guarantees. However, its reliance on complex second-order optimization limits its practical efficiency. Proximal Policy Optimization (PPO) addresses this by simplifying TRPO's approach using ratio clipping, improving efficiency but sacrificing some theoretical robustness. This raises a natural question: Can we combine the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16025","kind":"arxiv","version":9},"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/2401.16025/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":"2026-07-05T11:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mk50El0UMWOZWUipuZbaHE3ljR5v8E2dqx9tr7iDpwNjx6Ah4DTODaz9e3+mRwZm8P9mjlODIxx4fuB4hNrtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:40:49.959337Z"},"content_sha256":"ed359a22ab045b23c6b7e5cadfff5e8fdfebbe058c4aa9cde2e6f248c0327147","schema_version":"1.0","event_id":"sha256:ed359a22ab045b23c6b7e5cadfff5e8fdfebbe058c4aa9cde2e6f248c0327147"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/bundle.json","state_url":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/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":"2026-08-06T09:40:49Z","links":{"resolver":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L","bundle":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/bundle.json","state":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6D7RG46CQ6VRRP6FUEDAEOUO2L","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":"b3afd4ea3409e8e86bdfd9e500903077a57d95b5bc1f4b0454cd7596eb980358","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","title_canon_sha256":"dbaa649a9567a809b7d8998c57dd5c8ab6100010972577e450b0b482f072af40"},"schema_version":"1.0","source":{"id":"2401.16025","kind":"arxiv","version":9}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16025","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16025v9","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16025","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"6D7RG46CQ6VR","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"6D7RG46CQ6VRRP6F","created_at":"2026-07-05T11:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"6D7RG46C","created_at":"2026-07-05T11:43:27Z"}],"graph_snapshots":[{"event_id":"sha256:ed359a22ab045b23c6b7e5cadfff5e8fdfebbe058c4aa9cde2e6f248c0327147","target":"graph","created_at":"2026-07-05T11:43:27Z","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/2401.16025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust region, backed by strong theoretical guarantees. However, its reliance on complex second-order optimization limits its practical efficiency. Proximal Policy Optimization (PPO) addresses this by simplifying TRPO's approach using ratio clipping, improving efficiency but sacrificing some theoretical robustness. This raises a natural question: Can we combine the s","authors_text":"Fan Yang, Marco Hutter, Qiang Zhang, Renjing Xu, Zhengpeng Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","title":"Simple Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16025","kind":"arxiv","version":9},"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:aaf7cab032f7aac096ad26f04676bb4733a86e183416550e91d07ea1d00102c8","target":"record","created_at":"2026-07-05T11:43:27Z","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":"b3afd4ea3409e8e86bdfd9e500903077a57d95b5bc1f4b0454cd7596eb980358","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","title_canon_sha256":"dbaa649a9567a809b7d8998c57dd5c8ab6100010972577e450b0b482f072af40"},"schema_version":"1.0","source":{"id":"2401.16025","kind":"arxiv","version":9}},"canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","first_computed_at":"2026-07-05T11:43:27.324968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:27.324968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FcIt0rQzjKFVmy2bLtvAftvvP0nz75vDUgbAQK+aa84+x0wr1bavzU9pM+xdRu2wuuxPYjG6Kd3ul5GLziXaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:27.325644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16025","source_kind":"arxiv","source_version":9}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaf7cab032f7aac096ad26f04676bb4733a86e183416550e91d07ea1d00102c8","sha256:ed359a22ab045b23c6b7e5cadfff5e8fdfebbe058c4aa9cde2e6f248c0327147"],"state_sha256":"1137e18e6bdf4b1a86e86e11404116739587a17aae9a43b0b16835a01ee7f33e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qCY9HScWRNM5tzViVcP7a5VhaCb07xNam1rm8HlljiIrHUsWapTNimjU+m/yHItKcAXB122YiBn48Puhps3AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:40:49.963476Z","bundle_sha256":"a5aff2669fc8d9ff39914b03b58561469f58171556115b9eb60b5137ae85bd0d"}}