{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TJTI3C7GXKFTTZXGNKP5EWHIG3","short_pith_number":"pith:TJTI3C7G","canonical_record":{"source":{"id":"2111.04051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T11:14:19Z","cross_cats_sorted":[],"title_canon_sha256":"c2a70eefdd99b3c6606294d277a4f245ff88be422d7124e23b77ac7298241258","abstract_canon_sha256":"a5b2dbf1cb58c96eedb6b626c9a332e3bf055975145f386b9a5a22cf9408e559"},"schema_version":"1.0"},"canonical_sha256":"9a668d8be6ba8b39e6e66a9fd258e836ed7aa9a05425f555174472ab80e4e605","source":{"kind":"arxiv","id":"2111.04051","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04051","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04051v1","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04051","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"TJTI3C7GXKFT","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"TJTI3C7GXKFTTZXG","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"TJTI3C7G","created_at":"2026-07-05T03:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TJTI3C7GXKFTTZXGNKP5EWHIG3","target":"record","payload":{"canonical_record":{"source":{"id":"2111.04051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T11:14:19Z","cross_cats_sorted":[],"title_canon_sha256":"c2a70eefdd99b3c6606294d277a4f245ff88be422d7124e23b77ac7298241258","abstract_canon_sha256":"a5b2dbf1cb58c96eedb6b626c9a332e3bf055975145f386b9a5a22cf9408e559"},"schema_version":"1.0"},"canonical_sha256":"9a668d8be6ba8b39e6e66a9fd258e836ed7aa9a05425f555174472ab80e4e605","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:55.122158Z","signature_b64":"aWWfgxECTT09cSBtyeWbO9CjHO5Cl/qWOTV85lw+p4ZxriEyfSKWE/NJpcKUq+cHgpq93nmGEhzPIvJxm/SGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a668d8be6ba8b39e6e66a9fd258e836ed7aa9a05425f555174472ab80e4e605","last_reissued_at":"2026-07-05T03:29:55.121702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:55.121702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.04051","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":"2026-07-05T03:29:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXL32qklCLoBfSyqPiOMWZVXcKC3xeWruj+k/5CyD/0N91zXEkL8NXa4UqbA6p+jcTmn6irFCQgtNVWZIOJ4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:23:02.684313Z"},"content_sha256":"6d281503df3e456432f87375c12300fcf829fe73f2a4ae1e01302d92ac11f08c","schema_version":"1.0","event_id":"sha256:6d281503df3e456432f87375c12300fcf829fe73f2a4ae1e01302d92ac11f08c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TJTI3C7GXKFTTZXGNKP5EWHIG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coordinated Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Yu, Deheng Ye, Haiyin Piao, Hankz Hankui Zhuo, Junge Zhang, Zifan Wu","submitted_at":"2021-11-07T11:14:19Z","abstract_excerpt":"We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monotonicity of policy improvement when optimizing a theoretically-grounded joint objective, and derive a simplified optimization objective based on a set of approximations. We then interpret that such an objective in CoPPO can achieve dynamic credit assignment among agents, thereby alleviating the high va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04051","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/2111.04051/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":"2026-07-05T03:29:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2AjJ7tq3ZBlxqrW327qMthG+se/Z7qcrP7dwV5hap8e7Hgq8dZLRCZfY1T+B+YxeK1u2zEWwoQe+HGzEuSdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:23:02.684683Z"},"content_sha256":"7f4badaf1e1b604cab3d9f395a5b313c1df12fff53df35462f2797e967763fde","schema_version":"1.0","event_id":"sha256:7f4badaf1e1b604cab3d9f395a5b313c1df12fff53df35462f2797e967763fde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/bundle.json","state_url":"https://pith.science/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/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":"2026-08-04T08:23:02Z","links":{"resolver":"https://pith.science/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3","bundle":"https://pith.science/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/bundle.json","state":"https://pith.science/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJTI3C7GXKFTTZXGNKP5EWHIG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TJTI3C7GXKFTTZXGNKP5EWHIG3","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":"a5b2dbf1cb58c96eedb6b626c9a332e3bf055975145f386b9a5a22cf9408e559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T11:14:19Z","title_canon_sha256":"c2a70eefdd99b3c6606294d277a4f245ff88be422d7124e23b77ac7298241258"},"schema_version":"1.0","source":{"id":"2111.04051","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04051","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04051v1","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04051","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"TJTI3C7GXKFT","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"TJTI3C7GXKFTTZXG","created_at":"2026-07-05T03:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"TJTI3C7G","created_at":"2026-07-05T03:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:7f4badaf1e1b604cab3d9f395a5b313c1df12fff53df35462f2797e967763fde","target":"graph","created_at":"2026-07-05T03:29:55Z","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/2111.04051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monotonicity of policy improvement when optimizing a theoretically-grounded joint objective, and derive a simplified optimization objective based on a set of approximations. We then interpret that such an objective in CoPPO can achieve dynamic credit assignment among agents, thereby alleviating the high va","authors_text":"Chao Yu, Deheng Ye, Haiyin Piao, Hankz Hankui Zhuo, Junge Zhang, Zifan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T11:14:19Z","title":"Coordinated Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04051","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":"sha256:6d281503df3e456432f87375c12300fcf829fe73f2a4ae1e01302d92ac11f08c","target":"record","created_at":"2026-07-05T03:29:55Z","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":"a5b2dbf1cb58c96eedb6b626c9a332e3bf055975145f386b9a5a22cf9408e559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T11:14:19Z","title_canon_sha256":"c2a70eefdd99b3c6606294d277a4f245ff88be422d7124e23b77ac7298241258"},"schema_version":"1.0","source":{"id":"2111.04051","kind":"arxiv","version":1}},"canonical_sha256":"9a668d8be6ba8b39e6e66a9fd258e836ed7aa9a05425f555174472ab80e4e605","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a668d8be6ba8b39e6e66a9fd258e836ed7aa9a05425f555174472ab80e4e605","first_computed_at":"2026-07-05T03:29:55.121702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:55.121702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aWWfgxECTT09cSBtyeWbO9CjHO5Cl/qWOTV85lw+p4ZxriEyfSKWE/NJpcKUq+cHgpq93nmGEhzPIvJxm/SGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:55.122158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.04051","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d281503df3e456432f87375c12300fcf829fe73f2a4ae1e01302d92ac11f08c","sha256:7f4badaf1e1b604cab3d9f395a5b313c1df12fff53df35462f2797e967763fde"],"state_sha256":"7cba4b0158cdfb8da7f7f12c5cc18ea2a0a5c6c07c05c969d79e915f637cb186"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4KVzqsrs6fgCp4IQfYgJN1EcHjqx1FwPg5NBninc1OKEsrz5ipE8RtJtU9YEQVjGHw6K/gN7VR3eTTyUH6eAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:23:02.687343Z","bundle_sha256":"1a30aaf558a9cf602c789de8bf5b9d01290dc850ea92b7b68a5d4da65c94c3a0"}}