{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UFS4R5JTXRIKFYGNRRF36KVIYE","short_pith_number":"pith:UFS4R5JT","canonical_record":{"source":{"id":"1908.03263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T20:35:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6de4ea29bbf608813e346ab7bb0b5033f92517d785e3f76f027f3353d874f970","abstract_canon_sha256":"1f670f85a8c4956af7ec60f8844b868636830246e556732ed55378d56c800acc"},"schema_version":"1.0"},"canonical_sha256":"a165c8f533bc50a2e0cd8c4bbf2aa8c131d152b2f79692e3fbc70b0dc7d6b79f","source":{"kind":"arxiv","id":"1908.03263","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03263","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03263v1","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03263","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"UFS4R5JTXRIK","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_16","alias_value":"UFS4R5JTXRIKFYGN","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_8","alias_value":"UFS4R5JT","created_at":"2026-07-04T23:52:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UFS4R5JTXRIKFYGNRRF36KVIYE","target":"record","payload":{"canonical_record":{"source":{"id":"1908.03263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T20:35:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6de4ea29bbf608813e346ab7bb0b5033f92517d785e3f76f027f3353d874f970","abstract_canon_sha256":"1f670f85a8c4956af7ec60f8844b868636830246e556732ed55378d56c800acc"},"schema_version":"1.0"},"canonical_sha256":"a165c8f533bc50a2e0cd8c4bbf2aa8c131d152b2f79692e3fbc70b0dc7d6b79f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:37.945183Z","signature_b64":"BNaR+hC6yUlR4HTDE2V/4gkR6j6ntw9fPZM/A/4gEUSALr1aIAlEoVfa19DyOMBCJC1F5gXAIxcFsjfX+PhsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a165c8f533bc50a2e0cd8c4bbf2aa8c131d152b2f79692e3fbc70b0dc7d6b79f","last_reissued_at":"2026-07-04T23:52:37.944823Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:37.944823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.03263","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":"2026-07-04T23:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iNsf806MiFoPluQ9rkVeJlaH+t7gkFEx5m0Ei0qHbkkny17o6xvEFa/jUEAT1g1lX7t4CCr1e/Bin7qTEiJoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:17:09.994808Z"},"content_sha256":"5f215cb36cd9e1e095266765e10aa902c425ea48330c70615eea796bdf94612f","schema_version":"1.0","event_id":"sha256:5f215cb36cd9e1e095266765e10aa902c425ea48330c70615eea796bdf94612f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UFS4R5JTXRIKFYGNRRF36KVIYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Ching-An Cheng, Xinyan Yan","submitted_at":"2019-08-08T20:35:53Z","abstract_excerpt":"Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods are also notoriously sample inefficient. This can be attributed, at least in part, to the high variance in estimating the gradient of the task objective with Monte Carlo methods. Previous research has endeavored to contend with this problem by studying control variates (CVs) that can reduce the variance of estimates without introducing bias, including the early use of baselines, state dependent CVs, and the more recent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03263","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/1908.03263/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":"2026-07-04T23:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYzw0FvhSq11iZnr+XL1K0R72X3zObjTSnc1nNsuoWEgIw3ClCX2vZGKfXoPQ4yZmPdbaIFrgB0UeeD2iXNLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:17:09.995312Z"},"content_sha256":"fcd6a955854205c6140c38188d27a2d479b9ddf38ecbd6bbabd0305085b62cff","schema_version":"1.0","event_id":"sha256:fcd6a955854205c6140c38188d27a2d479b9ddf38ecbd6bbabd0305085b62cff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/bundle.json","state_url":"https://pith.science/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/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":"2026-08-16T10:17:09Z","links":{"resolver":"https://pith.science/pith/UFS4R5JTXRIKFYGNRRF36KVIYE","bundle":"https://pith.science/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/bundle.json","state":"https://pith.science/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFS4R5JTXRIKFYGNRRF36KVIYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UFS4R5JTXRIKFYGNRRF36KVIYE","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":"1f670f85a8c4956af7ec60f8844b868636830246e556732ed55378d56c800acc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T20:35:53Z","title_canon_sha256":"6de4ea29bbf608813e346ab7bb0b5033f92517d785e3f76f027f3353d874f970"},"schema_version":"1.0","source":{"id":"1908.03263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03263","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03263v1","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03263","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"UFS4R5JTXRIK","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_16","alias_value":"UFS4R5JTXRIKFYGN","created_at":"2026-07-04T23:52:37Z"},{"alias_kind":"pith_short_8","alias_value":"UFS4R5JT","created_at":"2026-07-04T23:52:37Z"}],"graph_snapshots":[{"event_id":"sha256:fcd6a955854205c6140c38188d27a2d479b9ddf38ecbd6bbabd0305085b62cff","target":"graph","created_at":"2026-07-04T23:52:37Z","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/1908.03263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods are also notoriously sample inefficient. This can be attributed, at least in part, to the high variance in estimating the gradient of the task objective with Monte Carlo methods. Previous research has endeavored to contend with this problem by studying control variates (CVs) that can reduce the variance of estimates without introducing bias, including the early use of baselines, state dependent CVs, and the more recent","authors_text":"Byron Boots, Ching-An Cheng, Xinyan Yan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T20:35:53Z","title":"Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03263","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":"sha256:5f215cb36cd9e1e095266765e10aa902c425ea48330c70615eea796bdf94612f","target":"record","created_at":"2026-07-04T23:52:37Z","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":"1f670f85a8c4956af7ec60f8844b868636830246e556732ed55378d56c800acc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T20:35:53Z","title_canon_sha256":"6de4ea29bbf608813e346ab7bb0b5033f92517d785e3f76f027f3353d874f970"},"schema_version":"1.0","source":{"id":"1908.03263","kind":"arxiv","version":1}},"canonical_sha256":"a165c8f533bc50a2e0cd8c4bbf2aa8c131d152b2f79692e3fbc70b0dc7d6b79f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a165c8f533bc50a2e0cd8c4bbf2aa8c131d152b2f79692e3fbc70b0dc7d6b79f","first_computed_at":"2026-07-04T23:52:37.944823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:52:37.944823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNaR+hC6yUlR4HTDE2V/4gkR6j6ntw9fPZM/A/4gEUSALr1aIAlEoVfa19DyOMBCJC1F5gXAIxcFsjfX+PhsBQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:52:37.945183Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f215cb36cd9e1e095266765e10aa902c425ea48330c70615eea796bdf94612f","sha256:fcd6a955854205c6140c38188d27a2d479b9ddf38ecbd6bbabd0305085b62cff"],"state_sha256":"9656001b515b622e4a8648f8bc3ac2892667c763dc74a19a7f93650fd97cfb3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KlfB1rNBAn2KROmfWgPkwOmGxLtG1010xGMmtCcgzITBuatlfzC8RSfWqne6vhrH6lL6NO0hkVmTXM7lkAUqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:17:09.999294Z","bundle_sha256":"211d65557d000e2a3f49d0d9070453914b2c1f23b8aa3ff814f970a16b726607"}}