{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D4D3JGL5FKSCPR3FJGOD6YU6S5","short_pith_number":"pith:D4D3JGL5","canonical_record":{"source":{"id":"2509.03030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T05:33:46Z","cross_cats_sorted":["cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"50c1a363a6e590a0b9561175a5fdc8a1b79c831af1386984fd1c7c53ee573eb8","abstract_canon_sha256":"abf1c7639e1332b6fd3670d4795f4de6acfd2226e7b2470c5a103b97878ad3e7"},"schema_version":"1.0"},"canonical_sha256":"1f07b4997d2aa427c765499c3f629e9762faf596480602eb1584bb1a50ee1d06","source":{"kind":"arxiv","id":"2509.03030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03030","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03030v1","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03030","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"D4D3JGL5FKSC","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"D4D3JGL5FKSCPR3F","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"D4D3JGL5","created_at":"2026-07-05T12:04:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D4D3JGL5FKSCPR3FJGOD6YU6S5","target":"record","payload":{"canonical_record":{"source":{"id":"2509.03030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T05:33:46Z","cross_cats_sorted":["cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"50c1a363a6e590a0b9561175a5fdc8a1b79c831af1386984fd1c7c53ee573eb8","abstract_canon_sha256":"abf1c7639e1332b6fd3670d4795f4de6acfd2226e7b2470c5a103b97878ad3e7"},"schema_version":"1.0"},"canonical_sha256":"1f07b4997d2aa427c765499c3f629e9762faf596480602eb1584bb1a50ee1d06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:02.406141Z","signature_b64":"VJdoRhGksb7QU2iQcg8gXF7AOLN96jvT9DS1bQnrU51PaLXd78ebM+8hd/hrPgRzm3Ozzxs7EazXoTKXtCP/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f07b4997d2aa427c765499c3f629e9762faf596480602eb1584bb1a50ee1d06","last_reissued_at":"2026-07-05T12:04:02.405693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:02.405693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.03030","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":"2026-07-05T12:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TF9+EJ4Yj3cie0mX1+SoZ2uoyBQ13nwphcoXHcNutFmCovPKa/qgBxLqLs3ze1t1JAdn965/2DjKFWR+ABnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:10:00.064456Z"},"content_sha256":"553d9ebe7151030a73429b8f7b8426389ca01411f1504eac54114ff7e1f7141a","schema_version":"1.0","event_id":"sha256:553d9ebe7151030a73429b8f7b8426389ca01411f1504eac54114ff7e1f7141a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D4D3JGL5FKSCPR3FJGOD6YU6S5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ankur Mehta, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Zida Wu","submitted_at":"2025-09-03T05:33:46Z","abstract_excerpt":"Mean Field Games (MFGs) offer a powerful framework for studying large-scale multi-agent systems. Yet, learning Nash equilibria in MFGs remains a challenging problem, particularly when the initial distribution is unknown or when the population is subject to common noise. In this paper, we introduce an efficient deep reinforcement learning (DRL) algorithm designed to achieve population-dependent Nash equilibria without relying on averaging or historical sampling, inspired by Munchausen RL and Online Mirror Descent. The resulting policy is adaptable to various initial distributions and sources of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03030","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/2509.03030/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":"2026-07-05T12:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8WV4Lr9wIvc9FlfZT22B2iwKLLj3bIlCT9eV9KLcY02/SehXJtGsZd0EWDgukfmZ2QB8Kq4kekhT09KyBTKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:10:00.064991Z"},"content_sha256":"8a3ea28fe559a73e4a86015469ad5d8bfa5f595d1763a8085843bdb9784f1894","schema_version":"1.0","event_id":"sha256:8a3ea28fe559a73e4a86015469ad5d8bfa5f595d1763a8085843bdb9784f1894"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/bundle.json","state_url":"https://pith.science/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/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":"2026-08-18T12:10:00Z","links":{"resolver":"https://pith.science/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5","bundle":"https://pith.science/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/bundle.json","state":"https://pith.science/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4D3JGL5FKSCPR3FJGOD6YU6S5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D4D3JGL5FKSCPR3FJGOD6YU6S5","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":"abf1c7639e1332b6fd3670d4795f4de6acfd2226e7b2470c5a103b97878ad3e7","cross_cats_sorted":["cs.MA","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T05:33:46Z","title_canon_sha256":"50c1a363a6e590a0b9561175a5fdc8a1b79c831af1386984fd1c7c53ee573eb8"},"schema_version":"1.0","source":{"id":"2509.03030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03030","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03030v1","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03030","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"D4D3JGL5FKSC","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"D4D3JGL5FKSCPR3F","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"D4D3JGL5","created_at":"2026-07-05T12:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:8a3ea28fe559a73e4a86015469ad5d8bfa5f595d1763a8085843bdb9784f1894","target":"graph","created_at":"2026-07-05T12:04:02Z","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/2509.03030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mean Field Games (MFGs) offer a powerful framework for studying large-scale multi-agent systems. Yet, learning Nash equilibria in MFGs remains a challenging problem, particularly when the initial distribution is unknown or when the population is subject to common noise. In this paper, we introduce an efficient deep reinforcement learning (DRL) algorithm designed to achieve population-dependent Nash equilibria without relying on averaging or historical sampling, inspired by Munchausen RL and Online Mirror Descent. The resulting policy is adaptable to various initial distributions and sources of","authors_text":"Ankur Mehta, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Zida Wu","cross_cats":["cs.MA","cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T05:33:46Z","title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03030","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":"sha256:553d9ebe7151030a73429b8f7b8426389ca01411f1504eac54114ff7e1f7141a","target":"record","created_at":"2026-07-05T12:04:02Z","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":"abf1c7639e1332b6fd3670d4795f4de6acfd2226e7b2470c5a103b97878ad3e7","cross_cats_sorted":["cs.MA","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T05:33:46Z","title_canon_sha256":"50c1a363a6e590a0b9561175a5fdc8a1b79c831af1386984fd1c7c53ee573eb8"},"schema_version":"1.0","source":{"id":"2509.03030","kind":"arxiv","version":1}},"canonical_sha256":"1f07b4997d2aa427c765499c3f629e9762faf596480602eb1584bb1a50ee1d06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f07b4997d2aa427c765499c3f629e9762faf596480602eb1584bb1a50ee1d06","first_computed_at":"2026-07-05T12:04:02.405693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:02.405693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJdoRhGksb7QU2iQcg8gXF7AOLN96jvT9DS1bQnrU51PaLXd78ebM+8hd/hrPgRzm3Ozzxs7EazXoTKXtCP/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:02.406141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:553d9ebe7151030a73429b8f7b8426389ca01411f1504eac54114ff7e1f7141a","sha256:8a3ea28fe559a73e4a86015469ad5d8bfa5f595d1763a8085843bdb9784f1894"],"state_sha256":"154d6f78160429a62bfe53e3e448688889fae6de6128e40420275f91f025fd33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lzQLUk1BcA2F0jGcIXlPWct5wMPVB5HXk9eDltdLSAJIwcmEYD2yBWKVge+Vhfl/X6+i1ZqZwKuzR6dxeFuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:10:00.069146Z","bundle_sha256":"8841209849c8b0ee9bc92a593fc34ca47ba9b5dd5b98dd66f26f05ee91b78c92"}}