{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TCA272DRWXHQBXUB5FI7JOGO3N","short_pith_number":"pith:TCA272DR","canonical_record":{"source":{"id":"2607.01525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","cross_cats_sorted":["cs.LG","cs.MA","math.PR"],"title_canon_sha256":"6e3e58b5ea174a16db2162997c5291f3f819effdcf20b39363baf70651472ef2","abstract_canon_sha256":"b60c021a617a8c1af76d44842b85130e0bde433adad8c4947fb3ce446a22dce7"},"schema_version":"1.0"},"canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","source":{"kind":"arxiv","id":"2607.01525","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01525","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01525v1","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01525","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCA272DRWXHQ","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCA272DRWXHQBXUB","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCA272DR","created_at":"2026-07-03T00:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TCA272DRWXHQBXUB5FI7JOGO3N","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","cross_cats_sorted":["cs.LG","cs.MA","math.PR"],"title_canon_sha256":"6e3e58b5ea174a16db2162997c5291f3f819effdcf20b39363baf70651472ef2","abstract_canon_sha256":"b60c021a617a8c1af76d44842b85130e0bde433adad8c4947fb3ce446a22dce7"},"schema_version":"1.0"},"canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:03.134618Z","signature_b64":"2/pMN0Uk1LIJgJSJJRYj8Z9h6bdwyLPypXapLMsDgxMTAC33fpo7qDSexJALXTdoiRhMDVfJHe+JIv2DFWjzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","last_reissued_at":"2026-07-03T00:17:03.134209Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:03.134209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01525","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":"2026-07-03T00:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/gKMAlsIi767GnvvCZpLUKU0czijj8/DXrWBZDztBK1oGxQfQUQCd0AFj0O3VOYX/sO2iqrsLXtJ8wrlZENAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:16:44.572573Z"},"content_sha256":"2588dd15ca27ec130a484314083773a615491e38062c997d12d86346282ae721","schema_version":"1.0","event_id":"sha256:2588dd15ca27ec130a484314083773a615491e38062c997d12d86346282ae721"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TCA272DRWXHQBXUB5FI7JOGO3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mean Field Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA","math.PR"],"primary_cat":"math.OC","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona","submitted_at":"2026-07-01T22:44:24Z","abstract_excerpt":"This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. Starting from the connection between multi-agent reinforcement learning and mean field control, it develops the probabilistic, mathematical, and control-theoretic framework needed to formulate representative-agent learning problems, analyze their relationship with finite-population systems, and study both general and linear-quadratic models. The presentation includes dynamic pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01525","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/2607.01525/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":"2026-07-03T00:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZPp6gl9bmdYIhdVRpNzbtXHVrKU/G0yFZ1Z10avvMsL4jWXSbjmmxII3Kbs9z+Ck04je2GD4Ce5W3L0/fLgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:16:44.572949Z"},"content_sha256":"065cd20bd5d1bd21a5c8cc9b305cadff5a78caa6f694dbe90280b2425430cb1f","schema_version":"1.0","event_id":"sha256:065cd20bd5d1bd21a5c8cc9b305cadff5a78caa6f694dbe90280b2425430cb1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/bundle.json","state_url":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCA272DRWXHQBXUB5FI7JOGO3N/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":"2026-07-04T18:16:44Z","links":{"resolver":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N","bundle":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/bundle.json","state":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCA272DRWXHQBXUB5FI7JOGO3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TCA272DRWXHQBXUB5FI7JOGO3N","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":"b60c021a617a8c1af76d44842b85130e0bde433adad8c4947fb3ce446a22dce7","cross_cats_sorted":["cs.LG","cs.MA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","title_canon_sha256":"6e3e58b5ea174a16db2162997c5291f3f819effdcf20b39363baf70651472ef2"},"schema_version":"1.0","source":{"id":"2607.01525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01525","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01525v1","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01525","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCA272DRWXHQ","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCA272DRWXHQBXUB","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCA272DR","created_at":"2026-07-03T00:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:065cd20bd5d1bd21a5c8cc9b305cadff5a78caa6f694dbe90280b2425430cb1f","target":"graph","created_at":"2026-07-03T00:17:03Z","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/2607.01525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. Starting from the connection between multi-agent reinforcement learning and mean field control, it develops the probabilistic, mathematical, and control-theoretic framework needed to formulate representative-agent learning problems, analyze their relationship with finite-population systems, and study both general and linear-quadratic models. The presentation includes dynamic pro","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona","cross_cats":["cs.LG","cs.MA","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","title":"Mean Field Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01525","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":"sha256:2588dd15ca27ec130a484314083773a615491e38062c997d12d86346282ae721","target":"record","created_at":"2026-07-03T00:17:03Z","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":"b60c021a617a8c1af76d44842b85130e0bde433adad8c4947fb3ce446a22dce7","cross_cats_sorted":["cs.LG","cs.MA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","title_canon_sha256":"6e3e58b5ea174a16db2162997c5291f3f819effdcf20b39363baf70651472ef2"},"schema_version":"1.0","source":{"id":"2607.01525","kind":"arxiv","version":1}},"canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","first_computed_at":"2026-07-03T00:17:03.134209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:17:03.134209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2/pMN0Uk1LIJgJSJJRYj8Z9h6bdwyLPypXapLMsDgxMTAC33fpo7qDSexJALXTdoiRhMDVfJHe+JIv2DFWjzBw==","signature_status":"signed_v1","signed_at":"2026-07-03T00:17:03.134618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2588dd15ca27ec130a484314083773a615491e38062c997d12d86346282ae721","sha256:065cd20bd5d1bd21a5c8cc9b305cadff5a78caa6f694dbe90280b2425430cb1f"],"state_sha256":"e9d9c7476f075dd5cca92a5de3e2be538dc606bd1d8311f849b4285978c1cafe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0pg/bOrwXJHbO2P8z6gxgzIONOrn10v53lEyepB65SKJgJixrg+SsNwAFY4y1VfbgoSCUdeIVXnG0PY2hrdBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:16:44.574930Z","bundle_sha256":"83da3de122d49a28c649a8f83489b053dfc6eae9bee743317aa8c4bfac5e3b61"}}