{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PDYS4ZM63NURKMSGU3K57DVE65","short_pith_number":"pith:PDYS4ZM6","canonical_record":{"source":{"id":"2310.10810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T20:14:06Z","cross_cats_sorted":[],"title_canon_sha256":"fd86450d5d11d756db84330a414833b8ee226697942d0847e7d6f8500f5ef5b5","abstract_canon_sha256":"03a8517d82d4c8dab24fd589dea94aae0832f12b2effb89819a36b42ea7883b6"},"schema_version":"1.0"},"canonical_sha256":"78f12e659edb69153246a6d5df8ea4f77165692b0a35ce90b4b827b96477f80e","source":{"kind":"arxiv","id":"2310.10810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10810","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10810v1","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10810","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"PDYS4ZM63NUR","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"PDYS4ZM63NURKMSG","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"PDYS4ZM6","created_at":"2026-07-05T07:01:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PDYS4ZM63NURKMSGU3K57DVE65","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T20:14:06Z","cross_cats_sorted":[],"title_canon_sha256":"fd86450d5d11d756db84330a414833b8ee226697942d0847e7d6f8500f5ef5b5","abstract_canon_sha256":"03a8517d82d4c8dab24fd589dea94aae0832f12b2effb89819a36b42ea7883b6"},"schema_version":"1.0"},"canonical_sha256":"78f12e659edb69153246a6d5df8ea4f77165692b0a35ce90b4b827b96477f80e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:28.183489Z","signature_b64":"UZwI9rojomvirEDimUdxFeuHMYJOJrKEclPaiCg0XeP6bHh3mLoDLTri6nb09gzAShC2C7+WqTxEs9mdqusfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f12e659edb69153246a6d5df8ea4f77165692b0a35ce90b4b827b96477f80e","last_reissued_at":"2026-07-05T07:01:28.183017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:28.183017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10810","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":"2026-07-05T07:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3l7WAc1BDhKCPdqvjKaRNbB5fiww4MI7FzMGzqGMEMpCWptbX3KTQrcuN3ieUn53gSys/QZZ9ERYjaPVLMTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:44.248069Z"},"content_sha256":"7c90c0d9398cf70bb739a59287bbbd8b4c8ce69382d82474081204c295978b0a","schema_version":"1.0","event_id":"sha256:7c90c0d9398cf70bb739a59287bbbd8b4c8ce69382d82474081204c295978b0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PDYS4ZM63NURKMSGU3K57DVE65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Bukharin, Chao Zhang, Qingru Zhang, Simiao Zuo, Songan Zhang, Tuo Zhao, Yan Li, Yue Yu, Zhehui Chen","submitted_at":"2023-10-16T20:14:06Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. Despite this promise, MARL policies often lack robustness and are therefore sensitive to small changes in their environment. This presents a serious concern for the real world deployment of MARL algorithms, where the testing environment may slightly differ from the training environment. In this work we show that we can gain robustness by controlling a policy's Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Based on these insights, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10810","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/2310.10810/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":"2026-07-05T07:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VG5kgv+nwqM05eNGORo9IoEjBt1vLCN6c6tpZSAHb1TdrFSqpAVE8hoCIepPtli0UwyJZNgQIxR72FOd+N7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:44.248600Z"},"content_sha256":"8cfa4db138f79572476e442838afc975cabae5b57da78bbefd1566d97b9f125a","schema_version":"1.0","event_id":"sha256:8cfa4db138f79572476e442838afc975cabae5b57da78bbefd1566d97b9f125a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PDYS4ZM63NURKMSGU3K57DVE65/bundle.json","state_url":"https://pith.science/pith/PDYS4ZM63NURKMSGU3K57DVE65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PDYS4ZM63NURKMSGU3K57DVE65/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":"2026-08-08T06:25:44Z","links":{"resolver":"https://pith.science/pith/PDYS4ZM63NURKMSGU3K57DVE65","bundle":"https://pith.science/pith/PDYS4ZM63NURKMSGU3K57DVE65/bundle.json","state":"https://pith.science/pith/PDYS4ZM63NURKMSGU3K57DVE65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PDYS4ZM63NURKMSGU3K57DVE65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PDYS4ZM63NURKMSGU3K57DVE65","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":"03a8517d82d4c8dab24fd589dea94aae0832f12b2effb89819a36b42ea7883b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T20:14:06Z","title_canon_sha256":"fd86450d5d11d756db84330a414833b8ee226697942d0847e7d6f8500f5ef5b5"},"schema_version":"1.0","source":{"id":"2310.10810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10810","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10810v1","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10810","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"PDYS4ZM63NUR","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"PDYS4ZM63NURKMSG","created_at":"2026-07-05T07:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"PDYS4ZM6","created_at":"2026-07-05T07:01:28Z"}],"graph_snapshots":[{"event_id":"sha256:8cfa4db138f79572476e442838afc975cabae5b57da78bbefd1566d97b9f125a","target":"graph","created_at":"2026-07-05T07:01:28Z","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/2310.10810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. Despite this promise, MARL policies often lack robustness and are therefore sensitive to small changes in their environment. This presents a serious concern for the real world deployment of MARL algorithms, where the testing environment may slightly differ from the training environment. In this work we show that we can gain robustness by controlling a policy's Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Based on these insights, we ","authors_text":"Alexander Bukharin, Chao Zhang, Qingru Zhang, Simiao Zuo, Songan Zhang, Tuo Zhao, Yan Li, Yue Yu, Zhehui Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T20:14:06Z","title":"Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10810","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":"sha256:7c90c0d9398cf70bb739a59287bbbd8b4c8ce69382d82474081204c295978b0a","target":"record","created_at":"2026-07-05T07:01:28Z","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":"03a8517d82d4c8dab24fd589dea94aae0832f12b2effb89819a36b42ea7883b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T20:14:06Z","title_canon_sha256":"fd86450d5d11d756db84330a414833b8ee226697942d0847e7d6f8500f5ef5b5"},"schema_version":"1.0","source":{"id":"2310.10810","kind":"arxiv","version":1}},"canonical_sha256":"78f12e659edb69153246a6d5df8ea4f77165692b0a35ce90b4b827b96477f80e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78f12e659edb69153246a6d5df8ea4f77165692b0a35ce90b4b827b96477f80e","first_computed_at":"2026-07-05T07:01:28.183017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:28.183017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZwI9rojomvirEDimUdxFeuHMYJOJrKEclPaiCg0XeP6bHh3mLoDLTri6nb09gzAShC2C7+WqTxEs9mdqusfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:28.183489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c90c0d9398cf70bb739a59287bbbd8b4c8ce69382d82474081204c295978b0a","sha256:8cfa4db138f79572476e442838afc975cabae5b57da78bbefd1566d97b9f125a"],"state_sha256":"eb4983a511f106bfccf02789f6c99d089def334120374045b6d2d2ba818384d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPTcZfDVnNXVJSXYyCzB8En3MKFpW1C6lCnfz8hJx27TExr8fU7gbSXenm55omuX+wudHslOU5wXPMVywuR4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:25:44.252514Z","bundle_sha256":"49c941f9bffda57a367c04efab4c357eaef423e9300208622eac1007499e748c"}}