{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W76G6GIWAAZAZIISXGWI3SXNPS","short_pith_number":"pith:W76G6GIW","canonical_record":{"source":{"id":"2502.09780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T21:28:51Z","cross_cats_sorted":["cs.AI","cs.GT","math.OC"],"title_canon_sha256":"91c419fd361187a27cfc448b884555bd85717c730932d82bd5daf8cd28ba9e83","abstract_canon_sha256":"21b6a17dc58674b4af57055ea3f3b5d9675e3994aa487b65dcefd1ca4a46f053"},"schema_version":"1.0"},"canonical_sha256":"b7fc6f191600320ca112b9ac8dcaed7c9337abc73d251fd20dcb5b606d3ae24a","source":{"kind":"arxiv","id":"2502.09780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09780","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09780v1","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09780","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"W76G6GIWAAZA","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"W76G6GIWAAZAZIIS","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"W76G6GIW","created_at":"2026-07-05T10:14:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W76G6GIWAAZAZIISXGWI3SXNPS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T21:28:51Z","cross_cats_sorted":["cs.AI","cs.GT","math.OC"],"title_canon_sha256":"91c419fd361187a27cfc448b884555bd85717c730932d82bd5daf8cd28ba9e83","abstract_canon_sha256":"21b6a17dc58674b4af57055ea3f3b5d9675e3994aa487b65dcefd1ca4a46f053"},"schema_version":"1.0"},"canonical_sha256":"b7fc6f191600320ca112b9ac8dcaed7c9337abc73d251fd20dcb5b606d3ae24a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:11.926186Z","signature_b64":"a1CEcFDJuYzSU8LqrRvHKVtpz8gveZiAHG25CY7LK88uHeTxuSYY2S3IvcjlKSej/wqQU0etjN6W4+UUI98WBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7fc6f191600320ca112b9ac8dcaed7c9337abc73d251fd20dcb5b606d3ae24a","last_reissued_at":"2026-07-05T10:14:11.925699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:11.925699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09780","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":"2026-07-05T10:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nkX6x4jvSOPsEvGq+Jw9FjRKgyWzbkjADwFa5i0tWOMEv25moFT+VX3NHPRUVxxGJa9WaY8/5IkMG1kn+btBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:29:43.753919Z"},"content_sha256":"c7d80b032d1c16b3488d6195ac3b2e619ce1bbf275dc6030ed1e02f4dc74e43f","schema_version":"1.0","event_id":"sha256:c7d80b032d1c16b3488d6195ac3b2e619ce1bbf275dc6030ed1e02f4dc74e43f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W76G6GIWAAZAZIISXGWI3SXNPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Lin Xiao, Tong Yang, Yuejie Chi","submitted_at":"2025-02-13T21:28:51Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) lies at the heart of a plethora of applications involving the interaction of a group of agents in a shared unknown environment. A prominent framework for studying MARL is Markov games, with the goal of finding various notions of equilibria in a sample-efficient manner, such as the Nash equilibrium (NE) and the coarse correlated equilibrium (CCE). However, existing sample-efficient approaches either require tailored uncertainty estimation under function approximation, or careful coordination of the players. In this paper, we propose a novel model-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09780","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/2502.09780/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":"2026-07-05T10:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhbydFwzcF8qw/M/Z5C3qnpELW8pfLFW6ebbi0nzpdOibGGFF4TvanXBA7Wv/9pYHIEgYIzceaTZF++391TrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:29:43.754519Z"},"content_sha256":"0e478322d224e1bdd311957de4e50c8013c50079cf66a1de5ed9ae54df980cf6","schema_version":"1.0","event_id":"sha256:0e478322d224e1bdd311957de4e50c8013c50079cf66a1de5ed9ae54df980cf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W76G6GIWAAZAZIISXGWI3SXNPS/bundle.json","state_url":"https://pith.science/pith/W76G6GIWAAZAZIISXGWI3SXNPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W76G6GIWAAZAZIISXGWI3SXNPS/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":"2026-08-23T06:29:43Z","links":{"resolver":"https://pith.science/pith/W76G6GIWAAZAZIISXGWI3SXNPS","bundle":"https://pith.science/pith/W76G6GIWAAZAZIISXGWI3SXNPS/bundle.json","state":"https://pith.science/pith/W76G6GIWAAZAZIISXGWI3SXNPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W76G6GIWAAZAZIISXGWI3SXNPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W76G6GIWAAZAZIISXGWI3SXNPS","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":"21b6a17dc58674b4af57055ea3f3b5d9675e3994aa487b65dcefd1ca4a46f053","cross_cats_sorted":["cs.AI","cs.GT","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T21:28:51Z","title_canon_sha256":"91c419fd361187a27cfc448b884555bd85717c730932d82bd5daf8cd28ba9e83"},"schema_version":"1.0","source":{"id":"2502.09780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09780","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09780v1","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09780","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"W76G6GIWAAZA","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"W76G6GIWAAZAZIIS","created_at":"2026-07-05T10:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"W76G6GIW","created_at":"2026-07-05T10:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:0e478322d224e1bdd311957de4e50c8013c50079cf66a1de5ed9ae54df980cf6","target":"graph","created_at":"2026-07-05T10:14:11Z","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/2502.09780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) lies at the heart of a plethora of applications involving the interaction of a group of agents in a shared unknown environment. A prominent framework for studying MARL is Markov games, with the goal of finding various notions of equilibria in a sample-efficient manner, such as the Nash equilibrium (NE) and the coarse correlated equilibrium (CCE). However, existing sample-efficient approaches either require tailored uncertainty estimation under function approximation, or careful coordination of the players. In this paper, we propose a novel model-based ","authors_text":"Bo Dai, Lin Xiao, Tong Yang, Yuejie Chi","cross_cats":["cs.AI","cs.GT","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T21:28:51Z","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09780","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:c7d80b032d1c16b3488d6195ac3b2e619ce1bbf275dc6030ed1e02f4dc74e43f","target":"record","created_at":"2026-07-05T10:14:11Z","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":"21b6a17dc58674b4af57055ea3f3b5d9675e3994aa487b65dcefd1ca4a46f053","cross_cats_sorted":["cs.AI","cs.GT","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T21:28:51Z","title_canon_sha256":"91c419fd361187a27cfc448b884555bd85717c730932d82bd5daf8cd28ba9e83"},"schema_version":"1.0","source":{"id":"2502.09780","kind":"arxiv","version":1}},"canonical_sha256":"b7fc6f191600320ca112b9ac8dcaed7c9337abc73d251fd20dcb5b606d3ae24a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7fc6f191600320ca112b9ac8dcaed7c9337abc73d251fd20dcb5b606d3ae24a","first_computed_at":"2026-07-05T10:14:11.925699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:11.925699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1CEcFDJuYzSU8LqrRvHKVtpz8gveZiAHG25CY7LK88uHeTxuSYY2S3IvcjlKSej/wqQU0etjN6W4+UUI98WBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:11.926186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7d80b032d1c16b3488d6195ac3b2e619ce1bbf275dc6030ed1e02f4dc74e43f","sha256:0e478322d224e1bdd311957de4e50c8013c50079cf66a1de5ed9ae54df980cf6"],"state_sha256":"9138fd13e239b11774bb685d32e4f5a1af7c4adaaefa0b7d4b8364447f933e89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTHrf7qRu3pLizjf4ydhvoj36NmTAZhvPIWq0gje6Z71axFldTC32r/IcuLi8OqkoM9TrbboreqIoDe0+RgcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:29:43.759696Z","bundle_sha256":"c3c509cbb121fa7da8b60fdafcede24f4847485314c5ac3df909564aef709f20"}}