{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZOHIWXOBMN7WIPLBR7BUMRFCWP","short_pith_number":"pith:ZOHIWXOB","canonical_record":{"source":{"id":"2009.04416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T16:52:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"123b1dc2c8c2c270105147b87ff84315904c0bae2e4b75451e43aae34a6aa8cc","abstract_canon_sha256":"f02331fe566670dc8016d99485fca13c40e476c67e9ccb3cf2e13f58e714462e"},"schema_version":"1.0"},"canonical_sha256":"cb8e8b5dc1637f643d618fc34644a2b3f5ff0aeaa163dc5cf17619184c8e49e4","source":{"kind":"arxiv","id":"2009.04416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04416","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04416v1","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04416","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZOHIWXOBMN7W","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZOHIWXOBMN7WIPLB","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZOHIWXOB","created_at":"2026-07-05T01:34:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZOHIWXOBMN7WIPLBR7BUMRFCWP","target":"record","payload":{"canonical_record":{"source":{"id":"2009.04416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T16:52:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"123b1dc2c8c2c270105147b87ff84315904c0bae2e4b75451e43aae34a6aa8cc","abstract_canon_sha256":"f02331fe566670dc8016d99485fca13c40e476c67e9ccb3cf2e13f58e714462e"},"schema_version":"1.0"},"canonical_sha256":"cb8e8b5dc1637f643d618fc34644a2b3f5ff0aeaa163dc5cf17619184c8e49e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:18.162243Z","signature_b64":"7raTlfod2IumRf212spohpIY3qIv4hjAaKikR9I3DsTxpec8QilfJG0oToVXfbllSUf0HfLXo5sknsD3fCiGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb8e8b5dc1637f643d618fc34644a2b3f5ff0aeaa163dc5cf17619184c8e49e4","last_reissued_at":"2026-07-05T01:34:18.161765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:18.161765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.04416","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":"2026-07-05T01:34:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ROnwx85HlPd9/N678iSHba3a4Eog/IOJKq7Acfm92uNPvKhfzgXfQcezvPkYPFayHpJCMdMCNXvPAXwwO5H+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:25:51.198387Z"},"content_sha256":"f18f7b0ad4d7a0c08e6c0cebfe5e199b8a2a7fff84db3594cdbc7bee0d1eb956","schema_version":"1.0","event_id":"sha256:f18f7b0ad4d7a0c08e6c0cebfe5e199b8a2a7fff84db3594cdbc7bee0d1eb956"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZOHIWXOBMN7WIPLBR7BUMRFCWP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phasic Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Hilton, John Schulman, Karl Cobbe, Oleg Klimov","submitted_at":"2020-09-09T16:52:53Z","abstract_excerpt":"We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework which modifies traditional on-policy actor-critic methods by separating policy and value function training into distinct phases. In prior methods, one must choose between using a shared network or separate networks to represent the policy and value function. Using separate networks avoids interference between objectives, while using a shared network allows useful features to be shared. PPG is able to achieve the best of both worlds by splitting optimization into two phases, one that advances training and one that dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04416","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/2009.04416/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":"2026-07-05T01:34:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyelA7aLTXzjYTqdM5BykHWzwiWWYoiVpZKcOqbSQXRSuUiNMjMKb6jWD1i4ys5iazeiiTyEXq/N6IWBzemoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:25:51.198830Z"},"content_sha256":"4a9aef33dd96b033b9124a35dc87a5a3ea0ffcf8f2fa21a5914ff9368b88def0","schema_version":"1.0","event_id":"sha256:4a9aef33dd96b033b9124a35dc87a5a3ea0ffcf8f2fa21a5914ff9368b88def0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/bundle.json","state_url":"https://pith.science/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/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":"2026-08-17T14:25:51Z","links":{"resolver":"https://pith.science/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP","bundle":"https://pith.science/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/bundle.json","state":"https://pith.science/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOHIWXOBMN7WIPLBR7BUMRFCWP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZOHIWXOBMN7WIPLBR7BUMRFCWP","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":"f02331fe566670dc8016d99485fca13c40e476c67e9ccb3cf2e13f58e714462e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T16:52:53Z","title_canon_sha256":"123b1dc2c8c2c270105147b87ff84315904c0bae2e4b75451e43aae34a6aa8cc"},"schema_version":"1.0","source":{"id":"2009.04416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04416","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04416v1","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04416","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZOHIWXOBMN7W","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZOHIWXOBMN7WIPLB","created_at":"2026-07-05T01:34:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZOHIWXOB","created_at":"2026-07-05T01:34:18Z"}],"graph_snapshots":[{"event_id":"sha256:4a9aef33dd96b033b9124a35dc87a5a3ea0ffcf8f2fa21a5914ff9368b88def0","target":"graph","created_at":"2026-07-05T01:34:18Z","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/2009.04416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework which modifies traditional on-policy actor-critic methods by separating policy and value function training into distinct phases. In prior methods, one must choose between using a shared network or separate networks to represent the policy and value function. Using separate networks avoids interference between objectives, while using a shared network allows useful features to be shared. PPG is able to achieve the best of both worlds by splitting optimization into two phases, one that advances training and one that dis","authors_text":"Jacob Hilton, John Schulman, Karl Cobbe, Oleg Klimov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T16:52:53Z","title":"Phasic Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04416","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:f18f7b0ad4d7a0c08e6c0cebfe5e199b8a2a7fff84db3594cdbc7bee0d1eb956","target":"record","created_at":"2026-07-05T01:34:18Z","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":"f02331fe566670dc8016d99485fca13c40e476c67e9ccb3cf2e13f58e714462e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-09T16:52:53Z","title_canon_sha256":"123b1dc2c8c2c270105147b87ff84315904c0bae2e4b75451e43aae34a6aa8cc"},"schema_version":"1.0","source":{"id":"2009.04416","kind":"arxiv","version":1}},"canonical_sha256":"cb8e8b5dc1637f643d618fc34644a2b3f5ff0aeaa163dc5cf17619184c8e49e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb8e8b5dc1637f643d618fc34644a2b3f5ff0aeaa163dc5cf17619184c8e49e4","first_computed_at":"2026-07-05T01:34:18.161765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:18.161765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7raTlfod2IumRf212spohpIY3qIv4hjAaKikR9I3DsTxpec8QilfJG0oToVXfbllSUf0HfLXo5sknsD3fCiGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:18.162243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.04416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f18f7b0ad4d7a0c08e6c0cebfe5e199b8a2a7fff84db3594cdbc7bee0d1eb956","sha256:4a9aef33dd96b033b9124a35dc87a5a3ea0ffcf8f2fa21a5914ff9368b88def0"],"state_sha256":"eb036314c8c6a88d9fe38d575bd8b1d360c775a600461f8715892518afe17555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJNZ9wzjMldRqfJWutYUxQDPnMd6XjX6+o8ITS6ByZzUtiM/zPiryTRj2lmUNDRyFV4CMu+zIuLQ1fwX0lRGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:25:51.201696Z","bundle_sha256":"bebd1f002c24c5c45678c0f9bc2733958622b7c5c2ba44a2f3962749d17652ca"}}