{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5QUCBLSYR4GWEBBWQKH2EOFYNG","short_pith_number":"pith:5QUCBLSY","canonical_record":{"source":{"id":"2505.19247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:54:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c1775c24a12cdc5209b4b50ca356995a6cbf3d5ddce2a80e7d5d63e8cf515c03","abstract_canon_sha256":"8b76a3a31a175323e3a58db9ce50fa6f66c19f0fe6ae32b0a8ccbb11d06eb2ed"},"schema_version":"1.0"},"canonical_sha256":"ec2820ae588f0d620436828fa238b869ab1b5c19336024b8bf1a05c73f609228","source":{"kind":"arxiv","id":"2505.19247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19247","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19247v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19247","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"5QUCBLSYR4GW","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"5QUCBLSYR4GWEBBW","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"5QUCBLSY","created_at":"2026-07-05T11:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5QUCBLSYR4GWEBBWQKH2EOFYNG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:54:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c1775c24a12cdc5209b4b50ca356995a6cbf3d5ddce2a80e7d5d63e8cf515c03","abstract_canon_sha256":"8b76a3a31a175323e3a58db9ce50fa6f66c19f0fe6ae32b0a8ccbb11d06eb2ed"},"schema_version":"1.0"},"canonical_sha256":"ec2820ae588f0d620436828fa238b869ab1b5c19336024b8bf1a05c73f609228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.043475Z","signature_b64":"jmShmaiCOd/M6Op6bjDYpX5L3xrUaB4Obyq+tIPkI0z+gj1iNvtiaJuiKt4QEZAJu0Zl+F3MnMkPFWqOY3dyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2820ae588f0d620436828fa238b869ab1b5c19336024b8bf1a05c73f609228","last_reissued_at":"2026-07-05T11:09:27.042945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.042945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19247","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hu/LP4hqqP0OJZC56aw1oOeps36QRoDR+N7ZpVauggRI0lu16Fey9Cox10xNU7tCuyuu2x7JptKCBeS3AZfSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:59:37.741681Z"},"content_sha256":"c5c3f1a891bc8e9be97ea983e2df05ac283f8cdc0fac831da74e0fcfacf4c060","schema_version":"1.0","event_id":"sha256:c5c3f1a891bc8e9be97ea983e2df05ac283f8cdc0fac831da74e0fcfacf4c060"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5QUCBLSYR4GWEBBWQKH2EOFYNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ruipeng Zhang, Sicun Gao, Tao Wang","submitted_at":"2025-05-25T17:54:32Z","abstract_excerpt":"Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show that the more critical factor is the enhanced value estimation accuracy from more value update steps in each iteration. To demonstrate, we show that by simply increasing the number of value update steps per iteration, vanilla policy gradient itself can achieve performance comparable to or better than PPO in all the standard continuous control benchmark environm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19247","kind":"arxiv","version":1},"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/2505.19247/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":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxfNi+uAjdsbZbbvrVH74vPgepVnmKUlXr/rFGkWs9rgZ9ZiC4obqiwKitYFuTzlF6jpjrI2+dw2UEAsjAQhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:59:37.742291Z"},"content_sha256":"05fca45923c9a76d3cc6860029a2f786be9db7d97a406c918121fd3d0c3ada2f","schema_version":"1.0","event_id":"sha256:05fca45923c9a76d3cc6860029a2f786be9db7d97a406c918121fd3d0c3ada2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/bundle.json","state_url":"https://pith.science/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/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":"2026-08-06T19:59:37Z","links":{"resolver":"https://pith.science/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG","bundle":"https://pith.science/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/bundle.json","state":"https://pith.science/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QUCBLSYR4GWEBBWQKH2EOFYNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QUCBLSYR4GWEBBWQKH2EOFYNG","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":"8b76a3a31a175323e3a58db9ce50fa6f66c19f0fe6ae32b0a8ccbb11d06eb2ed","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:54:32Z","title_canon_sha256":"c1775c24a12cdc5209b4b50ca356995a6cbf3d5ddce2a80e7d5d63e8cf515c03"},"schema_version":"1.0","source":{"id":"2505.19247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19247","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19247v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19247","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"5QUCBLSYR4GW","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"5QUCBLSYR4GWEBBW","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"5QUCBLSY","created_at":"2026-07-05T11:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:05fca45923c9a76d3cc6860029a2f786be9db7d97a406c918121fd3d0c3ada2f","target":"graph","created_at":"2026-07-05T11:09:27Z","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/2505.19247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show that the more critical factor is the enhanced value estimation accuracy from more value update steps in each iteration. To demonstrate, we show that by simply increasing the number of value update steps per iteration, vanilla policy gradient itself can achieve performance comparable to or better than PPO in all the standard continuous control benchmark environm","authors_text":"Ruipeng Zhang, Sicun Gao, Tao Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:54:32Z","title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19247","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:c5c3f1a891bc8e9be97ea983e2df05ac283f8cdc0fac831da74e0fcfacf4c060","target":"record","created_at":"2026-07-05T11:09:27Z","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":"8b76a3a31a175323e3a58db9ce50fa6f66c19f0fe6ae32b0a8ccbb11d06eb2ed","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:54:32Z","title_canon_sha256":"c1775c24a12cdc5209b4b50ca356995a6cbf3d5ddce2a80e7d5d63e8cf515c03"},"schema_version":"1.0","source":{"id":"2505.19247","kind":"arxiv","version":1}},"canonical_sha256":"ec2820ae588f0d620436828fa238b869ab1b5c19336024b8bf1a05c73f609228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec2820ae588f0d620436828fa238b869ab1b5c19336024b8bf1a05c73f609228","first_computed_at":"2026-07-05T11:09:27.042945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:27.042945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jmShmaiCOd/M6Op6bjDYpX5L3xrUaB4Obyq+tIPkI0z+gj1iNvtiaJuiKt4QEZAJu0Zl+F3MnMkPFWqOY3dyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:27.043475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5c3f1a891bc8e9be97ea983e2df05ac283f8cdc0fac831da74e0fcfacf4c060","sha256:05fca45923c9a76d3cc6860029a2f786be9db7d97a406c918121fd3d0c3ada2f"],"state_sha256":"97a294444d0fba9c75a8edf71e922ddbdc4e3b2819cccec5cf2427aedd691ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZbUoCaLLKHOocO+0B544M2nm8JKa0Auj63mikAGnXcZbqwhilJV0RrOKH0fa7P+AD3Jkfb1Gs8FWz+5z9bMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:59:37.749658Z","bundle_sha256":"e1617f824d6c69345037d5d6808f0df3138fe955165a9f2be73d149028caa714"}}