{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HYRE7SUSSLT43B3IRTVTUKZID5","short_pith_number":"pith:HYRE7SUS","canonical_record":{"source":{"id":"2010.04404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2020-10-09T07:25:55Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"62b93d0e324608e773e30e71f98b0d0bd4ba32af5c32d8dbcaaf5a8f685c758f","abstract_canon_sha256":"ec971122c9b4c3d03024013af029c3e5d9218132d99c7d87cf368ef39151f0a0"},"schema_version":"1.0"},"canonical_sha256":"3e224fca9292e7cd87688ceb3a2b281f4ec784bd9e222a048244fe22dc8b087b","source":{"kind":"arxiv","id":"2010.04404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04404","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04404v1","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04404","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"HYRE7SUSSLT4","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_16","alias_value":"HYRE7SUSSLT43B3I","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_8","alias_value":"HYRE7SUS","created_at":"2026-07-05T01:41:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HYRE7SUSSLT43B3IRTVTUKZID5","target":"record","payload":{"canonical_record":{"source":{"id":"2010.04404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2020-10-09T07:25:55Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"62b93d0e324608e773e30e71f98b0d0bd4ba32af5c32d8dbcaaf5a8f685c758f","abstract_canon_sha256":"ec971122c9b4c3d03024013af029c3e5d9218132d99c7d87cf368ef39151f0a0"},"schema_version":"1.0"},"canonical_sha256":"3e224fca9292e7cd87688ceb3a2b281f4ec784bd9e222a048244fe22dc8b087b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:36.914570Z","signature_b64":"XkCZ1PkX80vy2hl5FGqiArz+GuqGq6hXieQAX6Y6O0xm9b8FkZvmcyHdAelREd2+ynx5m6jaxul+k8g9dVD1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e224fca9292e7cd87688ceb3a2b281f4ec784bd9e222a048244fe22dc8b087b","last_reissued_at":"2026-07-05T01:41:36.914052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:36.914052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.04404","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":"2026-07-05T01:41:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3xGZWeimlq/65CFtBClEBYZtpSsFqAF8jeuDhEVxTIgHfH5m4xN8dBuwHv3bOQEdlRKp1TTjAeJ4R8L/aLbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:56:57.299250Z"},"content_sha256":"31a744458b2ad2e6cd908e211be77c1c136845fec45ce996c756b30c1bf44e62","schema_version":"1.0","event_id":"sha256:31a744458b2ad2e6cd908e211be77c1c136845fec45ce996c756b30c1bf44e62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HYRE7SUSSLT43B3IRTVTUKZID5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Asset Allocation in US Equities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"q-fin.PM","authors_text":"Miquel Noguer i Alonso, Sonam Srivastava","submitted_at":"2020-10-09T07:25:55Z","abstract_excerpt":"Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. It is first a prediction problem for expected returns and covariance matrix and then an opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04404","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/2010.04404/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":"2026-07-05T01:41:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gd0EHLT8otvGn2Ascg2PT78todVZj+Y7YFx/f7vzTNLhtEOaMEFPJtC+e4WQU175iViMLGqTVE6AYQi1/93bAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:56:57.299764Z"},"content_sha256":"55a96d6c79e03bebdc1b58f3860fa711eff81cee11fbbff714dfae55da923ee9","schema_version":"1.0","event_id":"sha256:55a96d6c79e03bebdc1b58f3860fa711eff81cee11fbbff714dfae55da923ee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYRE7SUSSLT43B3IRTVTUKZID5/bundle.json","state_url":"https://pith.science/pith/HYRE7SUSSLT43B3IRTVTUKZID5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYRE7SUSSLT43B3IRTVTUKZID5/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":"2026-08-21T16:56:57Z","links":{"resolver":"https://pith.science/pith/HYRE7SUSSLT43B3IRTVTUKZID5","bundle":"https://pith.science/pith/HYRE7SUSSLT43B3IRTVTUKZID5/bundle.json","state":"https://pith.science/pith/HYRE7SUSSLT43B3IRTVTUKZID5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYRE7SUSSLT43B3IRTVTUKZID5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HYRE7SUSSLT43B3IRTVTUKZID5","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":"ec971122c9b4c3d03024013af029c3e5d9218132d99c7d87cf368ef39151f0a0","cross_cats_sorted":["q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2020-10-09T07:25:55Z","title_canon_sha256":"62b93d0e324608e773e30e71f98b0d0bd4ba32af5c32d8dbcaaf5a8f685c758f"},"schema_version":"1.0","source":{"id":"2010.04404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04404","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04404v1","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04404","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"HYRE7SUSSLT4","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_16","alias_value":"HYRE7SUSSLT43B3I","created_at":"2026-07-05T01:41:36Z"},{"alias_kind":"pith_short_8","alias_value":"HYRE7SUS","created_at":"2026-07-05T01:41:36Z"}],"graph_snapshots":[{"event_id":"sha256:55a96d6c79e03bebdc1b58f3860fa711eff81cee11fbbff714dfae55da923ee9","target":"graph","created_at":"2026-07-05T01:41:36Z","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/2010.04404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. It is first a prediction problem for expected returns and covariance matrix and then an opt","authors_text":"Miquel Noguer i Alonso, Sonam Srivastava","cross_cats":["q-fin.CP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2020-10-09T07:25:55Z","title":"Deep Reinforcement Learning for Asset Allocation in US Equities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04404","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":"sha256:31a744458b2ad2e6cd908e211be77c1c136845fec45ce996c756b30c1bf44e62","target":"record","created_at":"2026-07-05T01:41:36Z","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":"ec971122c9b4c3d03024013af029c3e5d9218132d99c7d87cf368ef39151f0a0","cross_cats_sorted":["q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2020-10-09T07:25:55Z","title_canon_sha256":"62b93d0e324608e773e30e71f98b0d0bd4ba32af5c32d8dbcaaf5a8f685c758f"},"schema_version":"1.0","source":{"id":"2010.04404","kind":"arxiv","version":1}},"canonical_sha256":"3e224fca9292e7cd87688ceb3a2b281f4ec784bd9e222a048244fe22dc8b087b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e224fca9292e7cd87688ceb3a2b281f4ec784bd9e222a048244fe22dc8b087b","first_computed_at":"2026-07-05T01:41:36.914052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:36.914052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XkCZ1PkX80vy2hl5FGqiArz+GuqGq6hXieQAX6Y6O0xm9b8FkZvmcyHdAelREd2+ynx5m6jaxul+k8g9dVD1BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:36.914570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a744458b2ad2e6cd908e211be77c1c136845fec45ce996c756b30c1bf44e62","sha256:55a96d6c79e03bebdc1b58f3860fa711eff81cee11fbbff714dfae55da923ee9"],"state_sha256":"0c4554801ce2d5cf45336943cf275ccacd90a73ca6ac9299ea2cd3c80df8f003"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Cm8xozDgsMEeetMx7aMEh9kzSiV++Sd2NzyLi2fPcIbXpD5I6qHzekSS0YXMqAGLaj+GXzgGnMxVkrsl91XCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T16:56:57.304811Z","bundle_sha256":"0a8c8461e7ee47cce42db9a2d8a4b99676cf8d95237ffd82b44cb46c175b4263"}}