{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OFGYNOHP65MGO2NXFEFJVHUZAX","short_pith_number":"pith:OFGYNOHP","canonical_record":{"source":{"id":"1901.08740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15c2ff075a32244abff1f0cd0bef7b1991f8a4fdf1881b84cccfb1070d2ab34d","abstract_canon_sha256":"f72521bc5482cda7b9baf227912b59f5a87b7a5b5171a97d9cb1c1d9b7c6b522"},"schema_version":"1.0"},"canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","source":{"kind":"arxiv","id":"1901.08740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08740","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08740v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08740","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"OFGYNOHP65MG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OFGYNOHP65MGO2NX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OFGYNOHP","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OFGYNOHP65MGO2NXFEFJVHUZAX","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15c2ff075a32244abff1f0cd0bef7b1991f8a4fdf1881b84cccfb1070d2ab34d","abstract_canon_sha256":"f72521bc5482cda7b9baf227912b59f5a87b7a5b5171a97d9cb1c1d9b7c6b522"},"schema_version":"1.0"},"canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:33.247668Z","signature_b64":"g80owO3DHYD6+WP/VqhOUUzx4kGjNUhNZ9vN4w0dvNQ88VL98RZQFbPKu+BbZ0vCp2l71js3P9niWeZPP733AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","last_reissued_at":"2026-05-17T23:55:33.247212Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:33.247212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08740","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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ej7Tx2SYAOZXGNYCpC+/mVEa9M+1827FhGNWX3/8v2b2mZDS5pvQfBia4izvL3Et/C/tBk5bUbNo3qP2VUHfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:23:14.069374Z"},"content_sha256":"ca372d69f9d442501a80d9d1c3a931aa2116427c5beda9e331dc849bac73ec70","schema_version":"1.0","event_id":"sha256:ca372d69f9d442501a80d9d1c3a931aa2116427c5beda9e331dc849bac73ec70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OFGYNOHP65MGO2NXFEFJVHUZAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilya Kulyatin, Joon Sern Lee, Pengqian Yu, Sakyasingha Dasgupta, Zekun Shi","submitted_at":"2019-01-25T04:55:02Z","abstract_excerpt":"Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architecture with an autonomous trading agent such that, investment decisions and actions are made periodically, based on a global objective, with autonomy. In particular, without relying on a purely model-free RL agent, we train our trading agent using a novel RL architecture consisting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08740","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":""},"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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ffu+ai4qh3ycV2hReGBnd5rkKVox1RWW2Ufkk00TVBk4T0fLCWGcTEbPlFWPVsAS+0Jdxj9yaoSr5P8B/b5UDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:23:14.069730Z"},"content_sha256":"9047f917b17e85eb8e2ba27cdd3434ad624b5e675e5f9c353bde1fdd9df7eb9c","schema_version":"1.0","event_id":"sha256:9047f917b17e85eb8e2ba27cdd3434ad624b5e675e5f9c353bde1fdd9df7eb9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/bundle.json","state_url":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/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":"2026-06-02T23:23:14Z","links":{"resolver":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX","bundle":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/bundle.json","state":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OFGYNOHP65MGO2NXFEFJVHUZAX","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":"f72521bc5482cda7b9baf227912b59f5a87b7a5b5171a97d9cb1c1d9b7c6b522","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","title_canon_sha256":"15c2ff075a32244abff1f0cd0bef7b1991f8a4fdf1881b84cccfb1070d2ab34d"},"schema_version":"1.0","source":{"id":"1901.08740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08740","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08740v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08740","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"OFGYNOHP65MG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OFGYNOHP65MGO2NX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OFGYNOHP","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:9047f917b17e85eb8e2ba27cdd3434ad624b5e675e5f9c353bde1fdd9df7eb9c","target":"graph","created_at":"2026-05-17T23:55:33Z","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":"Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architecture with an autonomous trading agent such that, investment decisions and actions are made periodically, based on a global objective, with autonomy. In particular, without relying on a purely model-free RL agent, we train our trading agent using a novel RL architecture consisting","authors_text":"Ilya Kulyatin, Joon Sern Lee, Pengqian Yu, Sakyasingha Dasgupta, Zekun Shi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08740","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:ca372d69f9d442501a80d9d1c3a931aa2116427c5beda9e331dc849bac73ec70","target":"record","created_at":"2026-05-17T23:55:33Z","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":"f72521bc5482cda7b9baf227912b59f5a87b7a5b5171a97d9cb1c1d9b7c6b522","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","title_canon_sha256":"15c2ff075a32244abff1f0cd0bef7b1991f8a4fdf1881b84cccfb1070d2ab34d"},"schema_version":"1.0","source":{"id":"1901.08740","kind":"arxiv","version":1}},"canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","first_computed_at":"2026-05-17T23:55:33.247212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:33.247212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g80owO3DHYD6+WP/VqhOUUzx4kGjNUhNZ9vN4w0dvNQ88VL98RZQFbPKu+BbZ0vCp2l71js3P9niWeZPP733AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:33.247668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca372d69f9d442501a80d9d1c3a931aa2116427c5beda9e331dc849bac73ec70","sha256:9047f917b17e85eb8e2ba27cdd3434ad624b5e675e5f9c353bde1fdd9df7eb9c"],"state_sha256":"889d4b6ced3ff58a502a51e2ab632a719470dd29bcbb359e2fa4dcf1b1b231c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ui95pXUkbVh4vxKpqpP2wV++JPeDbmUMe1PWNOUsfueOD6gX5BrqsIo1dhVdR7POMoGQevulhz+4mOc2dnWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:23:14.071736Z","bundle_sha256":"6d5b9caad12f82351ced0c3b15cfc6feade2cc034f776d827641c9e5e779df11"}}