{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:32EGYYXZ4UY6T4SHLGILAOZ6H7","short_pith_number":"pith:32EGYYXZ","canonical_record":{"source":{"id":"1809.07225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-09-19T14:48:22Z","cross_cats_sorted":[],"title_canon_sha256":"638f7e71ef6cd059adc9f1ca90955a64e9f5f514a4337310e6582dfcee2a3fb6","abstract_canon_sha256":"ad46b9de75013b484d0de78f3f7c46113324febfe5c7c0e766a59e9ef392c809"},"schema_version":"1.0"},"canonical_sha256":"de886c62f9e531e9f2475990b03b3e3ff84bd32b5f5507e5aa1469b8ad4aa6c2","source":{"kind":"arxiv","id":"1809.07225","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07225","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07225v2","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07225","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"32EGYYXZ4UY6","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"32EGYYXZ4UY6T4SH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"32EGYYXZ","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:32EGYYXZ4UY6T4SHLGILAOZ6H7","target":"record","payload":{"canonical_record":{"source":{"id":"1809.07225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-09-19T14:48:22Z","cross_cats_sorted":[],"title_canon_sha256":"638f7e71ef6cd059adc9f1ca90955a64e9f5f514a4337310e6582dfcee2a3fb6","abstract_canon_sha256":"ad46b9de75013b484d0de78f3f7c46113324febfe5c7c0e766a59e9ef392c809"},"schema_version":"1.0"},"canonical_sha256":"de886c62f9e531e9f2475990b03b3e3ff84bd32b5f5507e5aa1469b8ad4aa6c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:43.001835Z","signature_b64":"x0rHGjX0dt/TroCXDY+ZnB87/BTXQ+Rs1LE49bc4UsYsk8B0IRQ521FP4bBEn+ZKFqC4aTdPHbp33YOHbn0/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de886c62f9e531e9f2475990b03b3e3ff84bd32b5f5507e5aa1469b8ad4aa6c2","last_reissued_at":"2026-05-17T23:42:43.001236Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:43.001236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.07225","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":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hdZlLixcJJkI7jEuTUKWWEQPkAe2fy5g7AruWLY4G/aO0sNBLlB5iBN6pjTLDbcqY3eHr02IU1XGbE3YLEuCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T17:57:16.536525Z"},"content_sha256":"0cf3cff1318e9c97ca95b9947eae70c14f642fcc2656c64f0b190782840ae64f","schema_version":"1.0","event_id":"sha256:0cf3cff1318e9c97ca95b9947eae70c14f642fcc2656c64f0b190782840ae64f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:32EGYYXZ4UY6T4SHLGILAOZ6H7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic limit of temporal difference reinforcement learning for stochastic games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Jonathan F. Donges, J\\\"urgen Kurths, Wolfram Barfuss","submitted_at":"2018-09-19T14:48:22Z","abstract_excerpt":"Reinforcement learning in multiagent systems has been studied in the fields of economic game theory, artificial intelligence and statistical physics by developing an analytical understanding of the learning dynamics (often in relation to the replicator dynamics of evolutionary game theory). However, the majority of these analytical studies focuses on repeated normal form games, which only have a single environmental state. Environmental dynamics, i.e., changes in the state of an environment affecting the agents' payoffs has received less attention, lacking a universal method to obtain determin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07225","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":""},"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":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+IJoCkczh9jBBJ+x26WGb9R+SlHVlnIiKcKg3bzSc/EM/iAPIAUSYuu/NKZpQTQEY3BiVc1dVWCQukEiRhECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T17:57:16.537234Z"},"content_sha256":"e5ffe1039f37e3cd4d988beee8ba0ccbf0d0df7abe17c1f8b5a152a6811d6bb1","schema_version":"1.0","event_id":"sha256:e5ffe1039f37e3cd4d988beee8ba0ccbf0d0df7abe17c1f8b5a152a6811d6bb1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/bundle.json","state_url":"https://pith.science/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/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":"2026-06-05T17:57:16Z","links":{"resolver":"https://pith.science/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7","bundle":"https://pith.science/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/bundle.json","state":"https://pith.science/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32EGYYXZ4UY6T4SHLGILAOZ6H7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:32EGYYXZ4UY6T4SHLGILAOZ6H7","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":"ad46b9de75013b484d0de78f3f7c46113324febfe5c7c0e766a59e9ef392c809","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-09-19T14:48:22Z","title_canon_sha256":"638f7e71ef6cd059adc9f1ca90955a64e9f5f514a4337310e6582dfcee2a3fb6"},"schema_version":"1.0","source":{"id":"1809.07225","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07225","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07225v2","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07225","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"32EGYYXZ4UY6","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"32EGYYXZ4UY6T4SH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"32EGYYXZ","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:e5ffe1039f37e3cd4d988beee8ba0ccbf0d0df7abe17c1f8b5a152a6811d6bb1","target":"graph","created_at":"2026-05-17T23:42:43Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning in multiagent systems has been studied in the fields of economic game theory, artificial intelligence and statistical physics by developing an analytical understanding of the learning dynamics (often in relation to the replicator dynamics of evolutionary game theory). However, the majority of these analytical studies focuses on repeated normal form games, which only have a single environmental state. Environmental dynamics, i.e., changes in the state of an environment affecting the agents' payoffs has received less attention, lacking a universal method to obtain determin","authors_text":"Jonathan F. Donges, J\\\"urgen Kurths, Wolfram Barfuss","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-09-19T14:48:22Z","title":"Deterministic limit of temporal difference reinforcement learning for stochastic games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07225","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":"sha256:0cf3cff1318e9c97ca95b9947eae70c14f642fcc2656c64f0b190782840ae64f","target":"record","created_at":"2026-05-17T23:42:43Z","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":"ad46b9de75013b484d0de78f3f7c46113324febfe5c7c0e766a59e9ef392c809","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-09-19T14:48:22Z","title_canon_sha256":"638f7e71ef6cd059adc9f1ca90955a64e9f5f514a4337310e6582dfcee2a3fb6"},"schema_version":"1.0","source":{"id":"1809.07225","kind":"arxiv","version":2}},"canonical_sha256":"de886c62f9e531e9f2475990b03b3e3ff84bd32b5f5507e5aa1469b8ad4aa6c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de886c62f9e531e9f2475990b03b3e3ff84bd32b5f5507e5aa1469b8ad4aa6c2","first_computed_at":"2026-05-17T23:42:43.001236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:43.001236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x0rHGjX0dt/TroCXDY+ZnB87/BTXQ+Rs1LE49bc4UsYsk8B0IRQ521FP4bBEn+ZKFqC4aTdPHbp33YOHbn0/CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:43.001835Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.07225","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cf3cff1318e9c97ca95b9947eae70c14f642fcc2656c64f0b190782840ae64f","sha256:e5ffe1039f37e3cd4d988beee8ba0ccbf0d0df7abe17c1f8b5a152a6811d6bb1"],"state_sha256":"9a340aa4205442a573e2d4f57a74b2a30e8715cc294cd50f40bc4b698650da43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4yCOYxMez1lK7e1pUt1iy4Z3kBRvXPvoGwIuN8ftLfGv12Gkfxuhz/Gu0Oc0ZVOyWrBpzH5Z5cMzr2MVxykCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T17:57:16.540663Z","bundle_sha256":"a3263c2bd7058722bfcfc535bc9bab169746067086110a59f35de6fd0f3129d1"}}