{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:V7GUTC5DB76BSGFBK2CIZGHY7O","short_pith_number":"pith:V7GUTC5D","canonical_record":{"source":{"id":"2302.06205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"838e5c6e19fdb4cc489a509db4920b64e8b7a5d296b8f9307aeaafe584f3b347","abstract_canon_sha256":"7ab24e7417f00f0034561238e9caf7b92f9699564859eb74c385bee1a5640ca0"},"schema_version":"1.0"},"canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","source":{"kind":"arxiv","id":"2302.06205","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06205","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06205v2","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06205","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"V7GUTC5DB76B","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"V7GUTC5DB76BSGFB","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"V7GUTC5D","created_at":"2026-07-05T05:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:V7GUTC5DB76BSGFBK2CIZGHY7O","target":"record","payload":{"canonical_record":{"source":{"id":"2302.06205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"838e5c6e19fdb4cc489a509db4920b64e8b7a5d296b8f9307aeaafe584f3b347","abstract_canon_sha256":"7ab24e7417f00f0034561238e9caf7b92f9699564859eb74c385bee1a5640ca0"},"schema_version":"1.0"},"canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:38.695489Z","signature_b64":"shTa6uQzWFIAF34HAIw7yL8YvWBX/dbkRYnzyKG/FpTmdnAR5tjkyHCY5BEVLwhqGTKN5bzuLtZA8IDEOGszBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","last_reissued_at":"2026-07-05T05:45:38.695001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:38.695001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.06205","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":"2026-07-05T05:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vuYqM3YpsB4EKpQE1qHDgw0jtsj6KoA/+qK7J6kXvhGmgaHsCpU9aW1ny2V4ulTYUs/dl6A6Nimm0lng4V2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:35:08.646583Z"},"content_sha256":"46c91c7b1c9ebe6e256229f0c768bb958afc1217c12ae633669132c79ecb929b","schema_version":"1.0","event_id":"sha256:46c91c7b1c9ebe6e256229f0c768bb958afc1217c12ae633669132c79ecb929b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:V7GUTC5DB76BSGFBK2CIZGHY7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Order Matters: Agent-by-agent Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jun Wang, Weinan Zhang, Xihuai Wang, Ying Wen, Zheng Tian, Ziyu Wan","submitted_at":"2023-02-13T09:24:34Z","abstract_excerpt":"While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent provides another perspective and shows strong performance. However, sample inefficiency and lack of monotonic improvement guarantees for each agent are still the two significant challenges for the sequential scheme. In this paper, we propose the \\textbf{A}gent-by-\\textbf{a}gent \\textbf{P}olicy \\textbf{O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06205","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/2302.06205/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":"2026-07-05T05:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMZod9BR/h2WiHkojO4shhNtqRoIy1hTSe0IUj8kf2tvorePgB/qJM3wDuyVMU5Euujjqdw9mTqPD7z/XJLlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:35:08.646975Z"},"content_sha256":"1b9178a4b0efb9f49feafa8df2fa841606f8fcf8abe507a5dab7408aa964651c","schema_version":"1.0","event_id":"sha256:1b9178a4b0efb9f49feafa8df2fa841606f8fcf8abe507a5dab7408aa964651c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/bundle.json","state_url":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/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":"2026-08-18T11:35:08Z","links":{"resolver":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O","bundle":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/bundle.json","state":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V7GUTC5DB76BSGFBK2CIZGHY7O","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":"7ab24e7417f00f0034561238e9caf7b92f9699564859eb74c385bee1a5640ca0","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","title_canon_sha256":"838e5c6e19fdb4cc489a509db4920b64e8b7a5d296b8f9307aeaafe584f3b347"},"schema_version":"1.0","source":{"id":"2302.06205","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06205","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06205v2","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06205","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"V7GUTC5DB76B","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"V7GUTC5DB76BSGFB","created_at":"2026-07-05T05:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"V7GUTC5D","created_at":"2026-07-05T05:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:1b9178a4b0efb9f49feafa8df2fa841606f8fcf8abe507a5dab7408aa964651c","target":"graph","created_at":"2026-07-05T05:45:38Z","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/2302.06205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent provides another perspective and shows strong performance. However, sample inefficiency and lack of monotonic improvement guarantees for each agent are still the two significant challenges for the sequential scheme. In this paper, we propose the \\textbf{A}gent-by-\\textbf{a}gent \\textbf{P}olicy \\textbf{O","authors_text":"Jun Wang, Weinan Zhang, Xihuai Wang, Ying Wen, Zheng Tian, Ziyu Wan","cross_cats":["cs.GT","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","title":"Order Matters: Agent-by-agent Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06205","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":"sha256:46c91c7b1c9ebe6e256229f0c768bb958afc1217c12ae633669132c79ecb929b","target":"record","created_at":"2026-07-05T05:45:38Z","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":"7ab24e7417f00f0034561238e9caf7b92f9699564859eb74c385bee1a5640ca0","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","title_canon_sha256":"838e5c6e19fdb4cc489a509db4920b64e8b7a5d296b8f9307aeaafe584f3b347"},"schema_version":"1.0","source":{"id":"2302.06205","kind":"arxiv","version":2}},"canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","first_computed_at":"2026-07-05T05:45:38.695001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:38.695001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"shTa6uQzWFIAF34HAIw7yL8YvWBX/dbkRYnzyKG/FpTmdnAR5tjkyHCY5BEVLwhqGTKN5bzuLtZA8IDEOGszBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:38.695489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06205","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46c91c7b1c9ebe6e256229f0c768bb958afc1217c12ae633669132c79ecb929b","sha256:1b9178a4b0efb9f49feafa8df2fa841606f8fcf8abe507a5dab7408aa964651c"],"state_sha256":"e266218764908fb88950f9d94376c111f1170f6e4420dcd17672719e58f4490a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbNqXgtV4yZnVB2Wx2rmcECBJWjJRvaR4555E+JIxEsEWMEMkMOtNdAS6JNTjNhxK0V9EhiNU0Qgd2XbTE7pCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:35:08.650382Z","bundle_sha256":"a7c7e5c87640f6ad332e30bc3178847d170ce4d295dab3b5c342163f88ef60c5"}}