{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZOMOHONRI57DMLUZ5L7U2YNMEF","short_pith_number":"pith:ZOMOHONR","canonical_record":{"source":{"id":"2412.19873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d014264d83a047ec5f5a8b1d86c1aa6c154c4498d5423f9579b16178b5a99977","abstract_canon_sha256":"ad5c1ef5b77e349d58ba15906d2b4be842973bedf97ece6569b3f40bb5b1530c"},"schema_version":"1.0"},"canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","source":{"kind":"arxiv","id":"2412.19873","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19873","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19873v1","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19873","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZOMOHONRI57D","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZOMOHONRI57DMLUZ","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZOMOHONR","created_at":"2026-07-05T09:54:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZOMOHONRI57DMLUZ5L7U2YNMEF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d014264d83a047ec5f5a8b1d86c1aa6c154c4498d5423f9579b16178b5a99977","abstract_canon_sha256":"ad5c1ef5b77e349d58ba15906d2b4be842973bedf97ece6569b3f40bb5b1530c"},"schema_version":"1.0"},"canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:50.916137Z","signature_b64":"ClmqEOQRdyYxHi+zS6PK+bEXYavl/LiA2EZQf0BcasBKRViPUVkmSEHSxfL6Zxnrwe9IzckjFefQr3KFuXmYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","last_reissued_at":"2026-07-05T09:54:50.915656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:50.915656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19873","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":"2026-07-05T09:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZV5Xu/wt6/D53hkON9cPsmS7/vxqtVJ7TTbVUddZ1wEFONIm4kal22F4SDCnZt8MVQTGfp/iHH/zAjRUp7bAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:02:20.144327Z"},"content_sha256":"94354fce7fc77fe3156d69a2894421a67c5091a0998156708f4a712e21b464b3","schema_version":"1.0","event_id":"sha256:94354fce7fc77fe3156d69a2894421a67c5091a0998156708f4a712e21b464b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZOMOHONRI57DMLUZ5L7U2YNMEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2024-12-27T16:37:33Z","abstract_excerpt":"Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems. However, existing results on sample complexity in RMGs suffer from at least one of three obstacles: restrictive range of uncertainty level or accuracy, the curse of multiple agents, and the barrier of long horizons, all of which cause existing results to significantly exceed the information-theoretic lower bound. To close this gap, we extend the Q-FTRL algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19873","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/2412.19873/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":"2026-07-05T09:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrouDsdTOtLyqp3bw9GqSukjbFqVsR/ED40vfTBSwV5Qx+1RQBKJm13gqw9yuqD16Gc0vcyUOd3rwx3Fly2RAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:02:20.144832Z"},"content_sha256":"e56dcfa6a01586dca05675c8e8ed28e203e562fe0e48a092f7fb8251445a4f7a","schema_version":"1.0","event_id":"sha256:e56dcfa6a01586dca05675c8e8ed28e203e562fe0e48a092f7fb8251445a4f7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/bundle.json","state_url":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/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":"2026-08-11T21:02:20Z","links":{"resolver":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF","bundle":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/bundle.json","state":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZOMOHONRI57DMLUZ5L7U2YNMEF","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":"ad5c1ef5b77e349d58ba15906d2b4be842973bedf97ece6569b3f40bb5b1530c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","title_canon_sha256":"d014264d83a047ec5f5a8b1d86c1aa6c154c4498d5423f9579b16178b5a99977"},"schema_version":"1.0","source":{"id":"2412.19873","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19873","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19873v1","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19873","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZOMOHONRI57D","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZOMOHONRI57DMLUZ","created_at":"2026-07-05T09:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZOMOHONR","created_at":"2026-07-05T09:54:50Z"}],"graph_snapshots":[{"event_id":"sha256:e56dcfa6a01586dca05675c8e8ed28e203e562fe0e48a092f7fb8251445a4f7a","target":"graph","created_at":"2026-07-05T09:54:50Z","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/2412.19873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems. However, existing results on sample complexity in RMGs suffer from at least one of three obstacles: restrictive range of uncertainty level or accuracy, the curse of multiple agents, and the barrier of long horizons, all of which cause existing results to significantly exceed the information-theoretic lower bound. To close this gap, we extend the Q-FTRL algo","authors_text":"Gen Li, Yuchen Jiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19873","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":"sha256:94354fce7fc77fe3156d69a2894421a67c5091a0998156708f4a712e21b464b3","target":"record","created_at":"2026-07-05T09:54:50Z","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":"ad5c1ef5b77e349d58ba15906d2b4be842973bedf97ece6569b3f40bb5b1530c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","title_canon_sha256":"d014264d83a047ec5f5a8b1d86c1aa6c154c4498d5423f9579b16178b5a99977"},"schema_version":"1.0","source":{"id":"2412.19873","kind":"arxiv","version":1}},"canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","first_computed_at":"2026-07-05T09:54:50.915656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:50.915656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ClmqEOQRdyYxHi+zS6PK+bEXYavl/LiA2EZQf0BcasBKRViPUVkmSEHSxfL6Zxnrwe9IzckjFefQr3KFuXmYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:50.916137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19873","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94354fce7fc77fe3156d69a2894421a67c5091a0998156708f4a712e21b464b3","sha256:e56dcfa6a01586dca05675c8e8ed28e203e562fe0e48a092f7fb8251445a4f7a"],"state_sha256":"cfdc728e3b17df50d64e20b89a5d33ee76e659a676b73f64af26a9f228b82b9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3GYSvTGBOwwnL4//rBsFOjKCrSeDtgA6IqU8PvxfAtU7VGrofYs6lMYiTQ9vdUSKNarEQY6RuAKB6+eAJPnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:02:20.148281Z","bundle_sha256":"586a34cb852f920700ddea5d62f3f65591511dae15448df8733cc45e0ed16794"}}