{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AAXVO6HLEROV6HPHK3TNR6KZE2","short_pith_number":"pith:AAXVO6HL","canonical_record":{"source":{"id":"2304.01547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-04T05:45:42Z","cross_cats_sorted":[],"title_canon_sha256":"7f69ee441a60fbdadc3d98a4f4d26b622621176ed419a0d1fed0368e43e72b8b","abstract_canon_sha256":"316a52e2afeeb46f43a6c264aab35e9531b7f8891358c89eb3af8d6c3a1619c8"},"schema_version":"1.0"},"canonical_sha256":"002f5778eb245d5f1de756e6d8f95926b23e9aefbf913b064f3706e2c96c2370","source":{"kind":"arxiv","id":"2304.01547","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.01547","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.01547v2","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01547","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"AAXVO6HLEROV","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"AAXVO6HLEROV6HPH","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"AAXVO6HL","created_at":"2026-07-05T06:00:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AAXVO6HLEROV6HPHK3TNR6KZE2","target":"record","payload":{"canonical_record":{"source":{"id":"2304.01547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-04T05:45:42Z","cross_cats_sorted":[],"title_canon_sha256":"7f69ee441a60fbdadc3d98a4f4d26b622621176ed419a0d1fed0368e43e72b8b","abstract_canon_sha256":"316a52e2afeeb46f43a6c264aab35e9531b7f8891358c89eb3af8d6c3a1619c8"},"schema_version":"1.0"},"canonical_sha256":"002f5778eb245d5f1de756e6d8f95926b23e9aefbf913b064f3706e2c96c2370","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:37.218795Z","signature_b64":"DKd2pB2cKSweCixzQ3+oe4RbGkEy7Xv5nzSMV4M2jEz4u5kKE+ok3cWPJoJmLBxrSC6PBIgUR0si/xw6oj9ICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"002f5778eb245d5f1de756e6d8f95926b23e9aefbf913b064f3706e2c96c2370","last_reissued_at":"2026-07-05T06:00:37.218382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:37.218382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.01547","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqV3yyz9zDf/D2vQ6Re27KgWEKPsEi0SREt4wO6hVWBolHjCGurkQHlVAUXIjQ984jF1wb4aVHUQNdNEszBMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:30:01.624132Z"},"content_sha256":"01178c18e36cf321667ab43885aa511e4821a4938d37be05a66b58ed8837606c","schema_version":"1.0","event_id":"sha256:01178c18e36cf321667ab43885aa511e4821a4938d37be05a66b58ed8837606c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AAXVO6HLEROV6HPHK3TNR6KZE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularization of the policy updates for stabilizing Mean Field Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hakim Hacid, Martin Takac, Merouane Debbah, Reda Alami, Ruben Solozabal, Talal Algumaei","submitted_at":"2023-04-04T05:45:42Z","abstract_excerpt":"This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01547","kind":"arxiv","version":2},"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/2304.01547/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":"2026-07-05T06:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZazoV+OUfsOzpJlk/gVzu5d1CZrns+onM1gVCxv2Wa/FTEfbKfYPAPiBvUJCYlZtsNP0MQweR+TXKOvwof3QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:30:01.624627Z"},"content_sha256":"3e0ae4011404f2174181ccac3b3022df72ab5fe3f69366d74720e6b7e2f5d534","schema_version":"1.0","event_id":"sha256:3e0ae4011404f2174181ccac3b3022df72ab5fe3f69366d74720e6b7e2f5d534"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/bundle.json","state_url":"https://pith.science/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/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":"2026-08-20T12:30:01Z","links":{"resolver":"https://pith.science/pith/AAXVO6HLEROV6HPHK3TNR6KZE2","bundle":"https://pith.science/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/bundle.json","state":"https://pith.science/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAXVO6HLEROV6HPHK3TNR6KZE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AAXVO6HLEROV6HPHK3TNR6KZE2","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":"316a52e2afeeb46f43a6c264aab35e9531b7f8891358c89eb3af8d6c3a1619c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-04T05:45:42Z","title_canon_sha256":"7f69ee441a60fbdadc3d98a4f4d26b622621176ed419a0d1fed0368e43e72b8b"},"schema_version":"1.0","source":{"id":"2304.01547","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.01547","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.01547v2","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01547","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"AAXVO6HLEROV","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"AAXVO6HLEROV6HPH","created_at":"2026-07-05T06:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"AAXVO6HL","created_at":"2026-07-05T06:00:37Z"}],"graph_snapshots":[{"event_id":"sha256:3e0ae4011404f2174181ccac3b3022df72ab5fe3f69366d74720e6b7e2f5d534","target":"graph","created_at":"2026-07-05T06:00:37Z","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/2304.01547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing","authors_text":"Hakim Hacid, Martin Takac, Merouane Debbah, Reda Alami, Ruben Solozabal, Talal Algumaei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-04T05:45:42Z","title":"Regularization of the policy updates for stabilizing Mean Field Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01547","kind":"arxiv","version":2},"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":"sha256:01178c18e36cf321667ab43885aa511e4821a4938d37be05a66b58ed8837606c","target":"record","created_at":"2026-07-05T06:00:37Z","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":"316a52e2afeeb46f43a6c264aab35e9531b7f8891358c89eb3af8d6c3a1619c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-04T05:45:42Z","title_canon_sha256":"7f69ee441a60fbdadc3d98a4f4d26b622621176ed419a0d1fed0368e43e72b8b"},"schema_version":"1.0","source":{"id":"2304.01547","kind":"arxiv","version":2}},"canonical_sha256":"002f5778eb245d5f1de756e6d8f95926b23e9aefbf913b064f3706e2c96c2370","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"002f5778eb245d5f1de756e6d8f95926b23e9aefbf913b064f3706e2c96c2370","first_computed_at":"2026-07-05T06:00:37.218382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:37.218382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DKd2pB2cKSweCixzQ3+oe4RbGkEy7Xv5nzSMV4M2jEz4u5kKE+ok3cWPJoJmLBxrSC6PBIgUR0si/xw6oj9ICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:37.218795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.01547","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01178c18e36cf321667ab43885aa511e4821a4938d37be05a66b58ed8837606c","sha256:3e0ae4011404f2174181ccac3b3022df72ab5fe3f69366d74720e6b7e2f5d534"],"state_sha256":"bb8625046f7c6041b0acec19efe200fe587e8d629c49a9dd264e876d6c0d8099"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLTMuVJtZ4Z058NEa3rRFZFev7pA9hNX1QcHLsEA2SEG/jqdQ9ezCPi5DfxzOGvWMblpL0iM0LWxqrbFY5nLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:30:01.628417Z","bundle_sha256":"e1ee5c3d2842bdaf336180dbff9158813090e7d8265402c9f581d01ba95ad45b"}}