{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2QMQPERVUHBOUGULEJVBZTDPLG","short_pith_number":"pith:2QMQPERV","canonical_record":{"source":{"id":"2306.10587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T15:50:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f34a058f9dc0cef2f21b5328b5c9ad501fcd7e62249b7653a31e346f20b1e20d","abstract_canon_sha256":"4c911a975bd9642daf43c74a76b2250b93c468a7ab5743f48ea2bdaa0e33b09f"},"schema_version":"1.0"},"canonical_sha256":"d419079235a1c2ea1a8b226a1ccc6f598abe4094daa99a1ea94c5f3f01b51929","source":{"kind":"arxiv","id":"2306.10587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10587","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10587v2","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10587","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"2QMQPERVUHBO","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"2QMQPERVUHBOUGUL","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"2QMQPERV","created_at":"2026-07-05T06:48:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2QMQPERVUHBOUGULEJVBZTDPLG","target":"record","payload":{"canonical_record":{"source":{"id":"2306.10587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T15:50:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f34a058f9dc0cef2f21b5328b5c9ad501fcd7e62249b7653a31e346f20b1e20d","abstract_canon_sha256":"4c911a975bd9642daf43c74a76b2250b93c468a7ab5743f48ea2bdaa0e33b09f"},"schema_version":"1.0"},"canonical_sha256":"d419079235a1c2ea1a8b226a1ccc6f598abe4094daa99a1ea94c5f3f01b51929","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:09.036341Z","signature_b64":"HKpSqXCz+QdVQXFn4N+6mcc2x98DoB4cff+So+/fd5FIFNwjZWllEjstbXG8y+W3eCL8JLkDMs7IxUUUgCGDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d419079235a1c2ea1a8b226a1ccc6f598abe4094daa99a1ea94c5f3f01b51929","last_reissued_at":"2026-07-05T06:48:09.035902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:09.035902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.10587","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYb9h/H3I41eC28glu1foIcjrDCOidbWaoZCJv7jOAilWmFlMcDPZYF9Fp6CmTKkpz4sdqvwe5hSj9MT5d7aBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:44:52.870441Z"},"content_sha256":"cf7ad94dcf4f7be2d20607f2b3a5ebb85a31948185372a94f2b097397dfe23fd","schema_version":"1.0","event_id":"sha256:cf7ad94dcf4f7be2d20607f2b3a5ebb85a31948185372a94f2b097397dfe23fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2QMQPERVUHBOUGULEJVBZTDPLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Acceleration in Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Guez, Doina Precup, Sebastian Flennerhag, Tom Zahavy, Veronica Chelu","submitted_at":"2023-06-18T15:50:57Z","abstract_excerpt":"We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates. Leveraging the connection between policy iteration and policy gradient methods, we view policy optimization algorithms as iteratively solving a sequence of surrogate objectives, local lower bounds on the original objective. We define optimism as predictive modelling of the future behavior of a policy, and adaptivity as taking immediate and anticipatory corrective actions to mitigate accumulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10587","kind":"arxiv","version":2},"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/2306.10587/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":"2026-07-05T06:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urxf8YpzLkZ7XrUWKHjgD0By+fQk4WPTcJJveC89//aF4WSeyvpoQYOeSvtfb7UDzHOzoZ8XOxQTmtv8cS5mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:44:52.871074Z"},"content_sha256":"ab361d158af0ed40294ab3e3064b1ac802bb5abe88d5795e4fa7de8fc102afea","schema_version":"1.0","event_id":"sha256:ab361d158af0ed40294ab3e3064b1ac802bb5abe88d5795e4fa7de8fc102afea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QMQPERVUHBOUGULEJVBZTDPLG/bundle.json","state_url":"https://pith.science/pith/2QMQPERVUHBOUGULEJVBZTDPLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QMQPERVUHBOUGULEJVBZTDPLG/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":"2026-08-06T05:44:52Z","links":{"resolver":"https://pith.science/pith/2QMQPERVUHBOUGULEJVBZTDPLG","bundle":"https://pith.science/pith/2QMQPERVUHBOUGULEJVBZTDPLG/bundle.json","state":"https://pith.science/pith/2QMQPERVUHBOUGULEJVBZTDPLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QMQPERVUHBOUGULEJVBZTDPLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2QMQPERVUHBOUGULEJVBZTDPLG","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":"4c911a975bd9642daf43c74a76b2250b93c468a7ab5743f48ea2bdaa0e33b09f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T15:50:57Z","title_canon_sha256":"f34a058f9dc0cef2f21b5328b5c9ad501fcd7e62249b7653a31e346f20b1e20d"},"schema_version":"1.0","source":{"id":"2306.10587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10587","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10587v2","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10587","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"2QMQPERVUHBO","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"2QMQPERVUHBOUGUL","created_at":"2026-07-05T06:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"2QMQPERV","created_at":"2026-07-05T06:48:09Z"}],"graph_snapshots":[{"event_id":"sha256:ab361d158af0ed40294ab3e3064b1ac802bb5abe88d5795e4fa7de8fc102afea","target":"graph","created_at":"2026-07-05T06:48:09Z","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/2306.10587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates. Leveraging the connection between policy iteration and policy gradient methods, we view policy optimization algorithms as iteratively solving a sequence of surrogate objectives, local lower bounds on the original objective. We define optimism as predictive modelling of the future behavior of a policy, and adaptivity as taking immediate and anticipatory corrective actions to mitigate accumulat","authors_text":"Arthur Guez, Doina Precup, Sebastian Flennerhag, Tom Zahavy, Veronica Chelu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T15:50:57Z","title":"Acceleration in Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10587","kind":"arxiv","version":2},"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:cf7ad94dcf4f7be2d20607f2b3a5ebb85a31948185372a94f2b097397dfe23fd","target":"record","created_at":"2026-07-05T06:48:09Z","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":"4c911a975bd9642daf43c74a76b2250b93c468a7ab5743f48ea2bdaa0e33b09f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T15:50:57Z","title_canon_sha256":"f34a058f9dc0cef2f21b5328b5c9ad501fcd7e62249b7653a31e346f20b1e20d"},"schema_version":"1.0","source":{"id":"2306.10587","kind":"arxiv","version":2}},"canonical_sha256":"d419079235a1c2ea1a8b226a1ccc6f598abe4094daa99a1ea94c5f3f01b51929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d419079235a1c2ea1a8b226a1ccc6f598abe4094daa99a1ea94c5f3f01b51929","first_computed_at":"2026-07-05T06:48:09.035902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:09.035902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKpSqXCz+QdVQXFn4N+6mcc2x98DoB4cff+So+/fd5FIFNwjZWllEjstbXG8y+W3eCL8JLkDMs7IxUUUgCGDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:09.036341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf7ad94dcf4f7be2d20607f2b3a5ebb85a31948185372a94f2b097397dfe23fd","sha256:ab361d158af0ed40294ab3e3064b1ac802bb5abe88d5795e4fa7de8fc102afea"],"state_sha256":"8348319b9cea36bf6b09ec3ed2bcc25c0d813467d64ec4877086c4e9798cf3e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZoxjc6jf+UL64oDRivXx9VpjouACZpL+Xogk5iSB6l60ZJUGCBY0byRQyM7kd/ZMVfCq5ZaXHslfiDK5K9tAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:44:52.876487Z","bundle_sha256":"9ec46538ca84bc02363fa3b96d96df588720895ed92d47d29150c4763318301e"}}