{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MAP7RY3C3ITGYXJQSUV7CMAJGC","short_pith_number":"pith:MAP7RY3C","canonical_record":{"source":{"id":"2104.09368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","cross_cats_sorted":["econ.GN","q-fin.EC","stat.ML"],"title_canon_sha256":"b9d6723e74222c1438ab03c6ffbe4dea5e2c978dea26ba2450124dd75d3f4eab","abstract_canon_sha256":"3048a978035519881a1fc668f971389e2401eaa00c8524ffc390edc28b94d3cc"},"schema_version":"1.0"},"canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","source":{"kind":"arxiv","id":"2104.09368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09368","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09368v2","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09368","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_12","alias_value":"MAP7RY3C3ITG","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"MAP7RY3C3ITGYXJQ","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"MAP7RY3C","created_at":"2026-07-05T05:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MAP7RY3C3ITGYXJQSUV7CMAJGC","target":"record","payload":{"canonical_record":{"source":{"id":"2104.09368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","cross_cats_sorted":["econ.GN","q-fin.EC","stat.ML"],"title_canon_sha256":"b9d6723e74222c1438ab03c6ffbe4dea5e2c978dea26ba2450124dd75d3f4eab","abstract_canon_sha256":"3048a978035519881a1fc668f971389e2401eaa00c8524ffc390edc28b94d3cc"},"schema_version":"1.0"},"canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:41.529256Z","signature_b64":"CBF01k+9cYkXSLyUWM8oMekpC4cLSGhgzIKrgL0omKwJSeeViT5vwUybsiioZss8UklNoortmL2j+fSxCqpiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","last_reissued_at":"2026-07-05T05:30:41.528834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:41.528834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.09368","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":"2026-07-05T05:30:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPrqWeTWd6ADRx109fW506I08613LMI5Jqp8KyQ6mmLbqRK7RSu2H2tZYxaQ4vk5aLLjdbPxYW9lKcho7/KZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:40:25.543305Z"},"content_sha256":"44ed773fd84407457928d78114c4fe77b024d8520faadcd4c2961d6236ae70d7","schema_version":"1.0","event_id":"sha256:44ed773fd84407457928d78114c4fe77b024d8520faadcd4c2961d6236ae70d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MAP7RY3C3ITGYXJQSUV7CMAJGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning in a Monetary Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.GN","q-fin.EC","stat.ML"],"primary_cat":"econ.EM","authors_text":"Andreas Joseph, Michael Kumhof, Mingli Chen, Xinlei Pan, Xuan Zhou","submitted_at":"2021-04-19T14:56:44Z","abstract_excerpt":"We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic optimisation problem by interacting with the model environment, of which they have no a priori knowledge. Deep reinforcement learning offers a flexible yet principled way to model bounded rationality within this general class of models. We apply our proposed approach to a classical model from the adaptive learning literature in macroeconomics which looks at the interaction of monetary and fiscal policy. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09368","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/2104.09368/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":"2026-07-05T05:30:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfLln2jRxSdY+j0y0JPLbScjMIayjqf1Vo2vgvXhXlAxa8i9UoGAS0ZG2doJ1E/I7qQ6DwBZcwYifkMVtvjoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:40:25.543859Z"},"content_sha256":"41d049ae60b475d1e8bec79b5a28b1cff8b90ad1ab35e19674ee2d6bd1917e85","schema_version":"1.0","event_id":"sha256:41d049ae60b475d1e8bec79b5a28b1cff8b90ad1ab35e19674ee2d6bd1917e85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/bundle.json","state_url":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/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":"2026-08-11T20:40:25Z","links":{"resolver":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC","bundle":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/bundle.json","state":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MAP7RY3C3ITGYXJQSUV7CMAJGC","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":"3048a978035519881a1fc668f971389e2401eaa00c8524ffc390edc28b94d3cc","cross_cats_sorted":["econ.GN","q-fin.EC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","title_canon_sha256":"b9d6723e74222c1438ab03c6ffbe4dea5e2c978dea26ba2450124dd75d3f4eab"},"schema_version":"1.0","source":{"id":"2104.09368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09368","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09368v2","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09368","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_12","alias_value":"MAP7RY3C3ITG","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"MAP7RY3C3ITGYXJQ","created_at":"2026-07-05T05:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"MAP7RY3C","created_at":"2026-07-05T05:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:41d049ae60b475d1e8bec79b5a28b1cff8b90ad1ab35e19674ee2d6bd1917e85","target":"graph","created_at":"2026-07-05T05:30:41Z","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/2104.09368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic optimisation problem by interacting with the model environment, of which they have no a priori knowledge. Deep reinforcement learning offers a flexible yet principled way to model bounded rationality within this general class of models. We apply our proposed approach to a classical model from the adaptive learning literature in macroeconomics which looks at the interaction of monetary and fiscal policy. W","authors_text":"Andreas Joseph, Michael Kumhof, Mingli Chen, Xinlei Pan, Xuan Zhou","cross_cats":["econ.GN","q-fin.EC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","title":"Deep Reinforcement Learning in a Monetary Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09368","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":"sha256:44ed773fd84407457928d78114c4fe77b024d8520faadcd4c2961d6236ae70d7","target":"record","created_at":"2026-07-05T05:30:41Z","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":"3048a978035519881a1fc668f971389e2401eaa00c8524ffc390edc28b94d3cc","cross_cats_sorted":["econ.GN","q-fin.EC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","title_canon_sha256":"b9d6723e74222c1438ab03c6ffbe4dea5e2c978dea26ba2450124dd75d3f4eab"},"schema_version":"1.0","source":{"id":"2104.09368","kind":"arxiv","version":2}},"canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","first_computed_at":"2026-07-05T05:30:41.528834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:41.528834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CBF01k+9cYkXSLyUWM8oMekpC4cLSGhgzIKrgL0omKwJSeeViT5vwUybsiioZss8UklNoortmL2j+fSxCqpiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:41.529256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44ed773fd84407457928d78114c4fe77b024d8520faadcd4c2961d6236ae70d7","sha256:41d049ae60b475d1e8bec79b5a28b1cff8b90ad1ab35e19674ee2d6bd1917e85"],"state_sha256":"62823c9e05eaea586c6ba95d38ce967b7c94f71a21ad55e47360a55a1f127f56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPisnQ8JzIlZ4uAkiHUueHZOzdz/kGkk4OU++v+1EG8fS7sG2i1oYy1CFkoutUpyLzfVKdTqSXnjrwzwQBECDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:40:25.549807Z","bundle_sha256":"2616cf2a096a18e8de3ef740347730e57ce3e853f7bb4c216656f48b8e216e79"}}