{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZXPN4RRU2I7B3KGFGQIBT6OINO","short_pith_number":"pith:ZXPN4RRU","canonical_record":{"source":{"id":"2112.13521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T05:41:14Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"7b5fa7fbffed5262809a415bb9c5376dfd652e880c260663287f689c4d303a69","abstract_canon_sha256":"95da3b827583f58397612d41c1b6146a02b2b2b07f4dce253f7fcc4467a9671b"},"schema_version":"1.0"},"canonical_sha256":"cddede4634d23e1da8c5341019f9c86b8139a012d76b85bd8a74ce4b9eaa7e1b","source":{"kind":"arxiv","id":"2112.13521","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13521","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13521v1","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13521","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPN4RRU2I7B","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPN4RRU2I7B3KGF","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPN4RRU","created_at":"2026-07-05T03:43:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZXPN4RRU2I7B3KGFGQIBT6OINO","target":"record","payload":{"canonical_record":{"source":{"id":"2112.13521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T05:41:14Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"7b5fa7fbffed5262809a415bb9c5376dfd652e880c260663287f689c4d303a69","abstract_canon_sha256":"95da3b827583f58397612d41c1b6146a02b2b2b07f4dce253f7fcc4467a9671b"},"schema_version":"1.0"},"canonical_sha256":"cddede4634d23e1da8c5341019f9c86b8139a012d76b85bd8a74ce4b9eaa7e1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:54.389237Z","signature_b64":"hf7xM6REJxdS4BiPTGjcfE9Syn+qukW8cc62UHJDfinufOW4KxnYJQlgtnbi/dT7ZqoWms8XoXDUIH8VxE93DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cddede4634d23e1da8c5341019f9c86b8139a012d76b85bd8a74ce4b9eaa7e1b","last_reissued_at":"2026-07-05T03:43:54.388724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:54.388724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.13521","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":"2026-07-05T03:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dhVs2RkgvshwD/zSx4kE0j7X9MwRqIvDxvo/R1EzfFEivjURzWM3+uXBK6KlUPVJ88yj2mE75+usWlqXGu87AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:54:29.327461Z"},"content_sha256":"5aedc768a67849a7cb495a9597af88202c49e275575657bc28c60195156a69f3","schema_version":"1.0","event_id":"sha256:5aedc768a67849a7cb495a9597af88202c49e275575657bc28c60195156a69f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZXPN4RRU2I7B3KGFGQIBT6OINO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","submitted_at":"2021-12-27T05:41:14Z","abstract_excerpt":"We study multi-player general-sum Markov games with one of the players designated as the leader and the other players regarded as followers. In particular, we focus on the class of games where the followers are myopic, i.e., they aim to maximize their instantaneous rewards. For such a game, our goal is to find a Stackelberg-Nash equilibrium (SNE), which is a policy pair $(\\pi^*, \\nu^*)$ such that (i) $\\pi^*$ is the optimal policy for the leader when the followers always play their best response, and (ii) $\\nu^*$ is the best response policy of the followers, which is a Nash equilibrium of the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13521","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/2112.13521/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":"2026-07-05T03:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KyaH+uY4gAXbC2DW/2dJq6DgxBbS8vnTL1mYVYkY/pxSnQz8nuTiXsjZxyH7SSgceZan+qDbXA7W3KYyHL7iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:54:29.327965Z"},"content_sha256":"aff6384c5aec7361efdb68505f75b40f684a829b361492e24cec56a289767ee8","schema_version":"1.0","event_id":"sha256:aff6384c5aec7361efdb68505f75b40f684a829b361492e24cec56a289767ee8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/bundle.json","state_url":"https://pith.science/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/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":"2026-08-08T04:54:29Z","links":{"resolver":"https://pith.science/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO","bundle":"https://pith.science/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/bundle.json","state":"https://pith.science/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXPN4RRU2I7B3KGFGQIBT6OINO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZXPN4RRU2I7B3KGFGQIBT6OINO","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":"95da3b827583f58397612d41c1b6146a02b2b2b07f4dce253f7fcc4467a9671b","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T05:41:14Z","title_canon_sha256":"7b5fa7fbffed5262809a415bb9c5376dfd652e880c260663287f689c4d303a69"},"schema_version":"1.0","source":{"id":"2112.13521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13521","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13521v1","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13521","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPN4RRU2I7B","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPN4RRU2I7B3KGF","created_at":"2026-07-05T03:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPN4RRU","created_at":"2026-07-05T03:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:aff6384c5aec7361efdb68505f75b40f684a829b361492e24cec56a289767ee8","target":"graph","created_at":"2026-07-05T03:43:54Z","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/2112.13521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study multi-player general-sum Markov games with one of the players designated as the leader and the other players regarded as followers. In particular, we focus on the class of games where the followers are myopic, i.e., they aim to maximize their instantaneous rewards. For such a game, our goal is to find a Stackelberg-Nash equilibrium (SNE), which is a policy pair $(\\pi^*, \\nu^*)$ such that (i) $\\pi^*$ is the optimal policy for the leader when the followers always play their best response, and (ii) $\\nu^*$ is the best response policy of the followers, which is a Nash equilibrium of the f","authors_text":"Han Zhong, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T05:41:14Z","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13521","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":"sha256:5aedc768a67849a7cb495a9597af88202c49e275575657bc28c60195156a69f3","target":"record","created_at":"2026-07-05T03:43:54Z","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":"95da3b827583f58397612d41c1b6146a02b2b2b07f4dce253f7fcc4467a9671b","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T05:41:14Z","title_canon_sha256":"7b5fa7fbffed5262809a415bb9c5376dfd652e880c260663287f689c4d303a69"},"schema_version":"1.0","source":{"id":"2112.13521","kind":"arxiv","version":1}},"canonical_sha256":"cddede4634d23e1da8c5341019f9c86b8139a012d76b85bd8a74ce4b9eaa7e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cddede4634d23e1da8c5341019f9c86b8139a012d76b85bd8a74ce4b9eaa7e1b","first_computed_at":"2026-07-05T03:43:54.388724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:54.388724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hf7xM6REJxdS4BiPTGjcfE9Syn+qukW8cc62UHJDfinufOW4KxnYJQlgtnbi/dT7ZqoWms8XoXDUIH8VxE93DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:54.389237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aedc768a67849a7cb495a9597af88202c49e275575657bc28c60195156a69f3","sha256:aff6384c5aec7361efdb68505f75b40f684a829b361492e24cec56a289767ee8"],"state_sha256":"562e6a6f924cc60a254affbfd2191e838190b1769d1a20fb830bd62476288efb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cANMhgGEnyX8TlhG2UUaOx5m6VW6r0MJ98wnaJgFtcgDGP3lOTCJFQvlWC+6GQMb1bwsKPkxwRekAKrmjxJ+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:54:29.331750Z","bundle_sha256":"643e6e0c8065499eb853bea889b443e84986d55ba2136aa692198313d30656b1"}}