{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:B5QA7OYV4GU65EMGC4XG536RCK","short_pith_number":"pith:B5QA7OYV","canonical_record":{"source":{"id":"2202.00079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:26:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f04600e69df9ba64222c04fb2b495e109a0b67a388d50ed7c20529d53744bc4","abstract_canon_sha256":"4f5bdefb6643454d02af375f144e9cdd66dcb6fa8987dff2e7ea4f35859ce71c"},"schema_version":"1.0"},"canonical_sha256":"0f600fbb15e1a9ee9186172e6eefd112a3567adbb6e58f365373e0decf016ad9","source":{"kind":"arxiv","id":"2202.00079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00079","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00079v1","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00079","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"B5QA7OYV4GU6","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"B5QA7OYV4GU65EMG","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"B5QA7OYV","created_at":"2026-07-05T03:53:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:B5QA7OYV4GU65EMGC4XG536RCK","target":"record","payload":{"canonical_record":{"source":{"id":"2202.00079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:26:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f04600e69df9ba64222c04fb2b495e109a0b67a388d50ed7c20529d53744bc4","abstract_canon_sha256":"4f5bdefb6643454d02af375f144e9cdd66dcb6fa8987dff2e7ea4f35859ce71c"},"schema_version":"1.0"},"canonical_sha256":"0f600fbb15e1a9ee9186172e6eefd112a3567adbb6e58f365373e0decf016ad9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:18.291648Z","signature_b64":"ZfDOfeX/anHRsibs7cAf/cMF6JZug7Tu3dBjhbzYgQR3sm7JhhM5ht3fdu0QXNvITTlMx2VIjl8jVx0b97qdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f600fbb15e1a9ee9186172e6eefd112a3567adbb6e58f365373e0decf016ad9","last_reissued_at":"2026-07-05T03:53:18.291163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:18.291163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.00079","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":"2026-07-05T03:53:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UyEArj2Py6H3RLx0pKGMkM3Oq7f2AmjCIPWhgO98SjADonYEVWuKX1ipNaZ7FRHTZ2aA8sQoD2t2H+FVl3BzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:09:04.475886Z"},"content_sha256":"7b5cc3b6e09c6a4d84e15a65495285d70aeacbc0629f81f65b106a62cbcb8d2d","schema_version":"1.0","event_id":"sha256:7b5cc3b6e09c6a4d84e15a65495285d70aeacbc0629f81f65b106a62cbcb8d2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:B5QA7OYV4GU65EMGC4XG536RCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You May Not Need Ratio Clipping in PPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guoqing Liu, Katja Hofmann, Mingfei Sun, Sam Devlin, Shimon Whiteson, Tao Qin, Vitaly Kurin","submitted_at":"2022-01-31T20:26:56Z","abstract_excerpt":"Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. Ratio clipping yields a pessimistic estimate of the original surrogate objective, and has been shown to be crucial for strong performance. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. Instead, one can direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00079","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/2202.00079/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":"2026-07-05T03:53:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIr27TZOL2vZS4A8PAtPPfbs5CjE79aacJgNu1cZXsgkSiIfhxe4EHqzHwxdKyfot97kioQmAsoKty8fBaEiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:09:04.476280Z"},"content_sha256":"86fc4e6203d4ab69096644c6c61d8d56ad49adc9f8cf9565e1ca0145aa883286","schema_version":"1.0","event_id":"sha256:86fc4e6203d4ab69096644c6c61d8d56ad49adc9f8cf9565e1ca0145aa883286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5QA7OYV4GU65EMGC4XG536RCK/bundle.json","state_url":"https://pith.science/pith/B5QA7OYV4GU65EMGC4XG536RCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5QA7OYV4GU65EMGC4XG536RCK/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":"2026-07-05T13:09:04Z","links":{"resolver":"https://pith.science/pith/B5QA7OYV4GU65EMGC4XG536RCK","bundle":"https://pith.science/pith/B5QA7OYV4GU65EMGC4XG536RCK/bundle.json","state":"https://pith.science/pith/B5QA7OYV4GU65EMGC4XG536RCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5QA7OYV4GU65EMGC4XG536RCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B5QA7OYV4GU65EMGC4XG536RCK","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":"4f5bdefb6643454d02af375f144e9cdd66dcb6fa8987dff2e7ea4f35859ce71c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:26:56Z","title_canon_sha256":"3f04600e69df9ba64222c04fb2b495e109a0b67a388d50ed7c20529d53744bc4"},"schema_version":"1.0","source":{"id":"2202.00079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00079","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00079v1","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00079","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"B5QA7OYV4GU6","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"B5QA7OYV4GU65EMG","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"B5QA7OYV","created_at":"2026-07-05T03:53:18Z"}],"graph_snapshots":[{"event_id":"sha256:86fc4e6203d4ab69096644c6c61d8d56ad49adc9f8cf9565e1ca0145aa883286","target":"graph","created_at":"2026-07-05T03:53:18Z","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/2202.00079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. Ratio clipping yields a pessimistic estimate of the original surrogate objective, and has been shown to be crucial for strong performance. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. Instead, one can direc","authors_text":"Guoqing Liu, Katja Hofmann, Mingfei Sun, Sam Devlin, Shimon Whiteson, Tao Qin, Vitaly Kurin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:26:56Z","title":"You May Not Need Ratio Clipping in PPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00079","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":"sha256:7b5cc3b6e09c6a4d84e15a65495285d70aeacbc0629f81f65b106a62cbcb8d2d","target":"record","created_at":"2026-07-05T03:53:18Z","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":"4f5bdefb6643454d02af375f144e9cdd66dcb6fa8987dff2e7ea4f35859ce71c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:26:56Z","title_canon_sha256":"3f04600e69df9ba64222c04fb2b495e109a0b67a388d50ed7c20529d53744bc4"},"schema_version":"1.0","source":{"id":"2202.00079","kind":"arxiv","version":1}},"canonical_sha256":"0f600fbb15e1a9ee9186172e6eefd112a3567adbb6e58f365373e0decf016ad9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f600fbb15e1a9ee9186172e6eefd112a3567adbb6e58f365373e0decf016ad9","first_computed_at":"2026-07-05T03:53:18.291163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:18.291163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZfDOfeX/anHRsibs7cAf/cMF6JZug7Tu3dBjhbzYgQR3sm7JhhM5ht3fdu0QXNvITTlMx2VIjl8jVx0b97qdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:18.291648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b5cc3b6e09c6a4d84e15a65495285d70aeacbc0629f81f65b106a62cbcb8d2d","sha256:86fc4e6203d4ab69096644c6c61d8d56ad49adc9f8cf9565e1ca0145aa883286"],"state_sha256":"07af7db68863c31d7a161550b2bf8108c8a10aa9d65f595956a03d202b5e3f17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7YR0eLM7dHKSWy7DACLgYrJCQWvaYoeQ0ro0itQ+WPcaUSTAERGPvqXgoDFFnAY+FGXkKEQaU3LFk7K3Wi6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:09:04.478740Z","bundle_sha256":"fa49df04ecb655b644b7c434d537d55483057d2a32a8bf0b22ed18a754010a4c"}}