{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XFOAG5VCARBEALT6DML4QOGBBV","short_pith_number":"pith:XFOAG5VC","schema_version":"1.0","canonical_sha256":"b95c0376a20442402e7e1b17c838c10d78e77578ab5094d613a8cee2043a2ed9","source":{"kind":"arxiv","id":"2111.09170","version":1},"attestation_state":"computed","paper":{"title":"A Universal End-to-End Approach to Portfolio Optimization via Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.PM","authors_text":"Chao Zhang, Mihai Cucuringu, Stefan Zohren, Zihao Zhang","submitted_at":"2021-11-17T15:01:53Z","abstract_excerpt":"We propose a universal end-to-end framework for portfolio optimization where asset distributions are directly obtained. The designed framework circumvents the traditional forecasting step and avoids the estimation of the covariance matrix, lifting the bottleneck for generalizing to a large amount of instruments. Our framework has the flexibility of optimizing various objective functions including Sharpe ratio, mean-variance trade-off etc. Further, we allow for short selling and study several constraints attached to objective functions. In particular, we consider cardinality, maximum position f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.09170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.PM","submitted_at":"2021-11-17T15:01:53Z","cross_cats_sorted":[],"title_canon_sha256":"72bd97ed4b464d8d28435e9c50ef96907f44ca447f454cef1d13d9f8df4b4187","abstract_canon_sha256":"8502d6dd267db5f06ddb0386cddcf5217a8a104f64e6a96bd9c19725aa171d76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:58.490490Z","signature_b64":"umCrmSMKQ8ZG144hyHNG9oOE4agH0Me4xXwfTMAnyUnOPozwzyVDiSr6LiLF/BrtBipyPnXP6s4OBbxuo3Z9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95c0376a20442402e7e1b17c838c10d78e77578ab5094d613a8cee2043a2ed9","last_reissued_at":"2026-07-05T03:32:58.489973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:58.489973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Universal End-to-End Approach to Portfolio Optimization via Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.PM","authors_text":"Chao Zhang, Mihai Cucuringu, Stefan Zohren, Zihao Zhang","submitted_at":"2021-11-17T15:01:53Z","abstract_excerpt":"We propose a universal end-to-end framework for portfolio optimization where asset distributions are directly obtained. The designed framework circumvents the traditional forecasting step and avoids the estimation of the covariance matrix, lifting the bottleneck for generalizing to a large amount of instruments. Our framework has the flexibility of optimizing various objective functions including Sharpe ratio, mean-variance trade-off etc. Further, we allow for short selling and study several constraints attached to objective functions. In particular, we consider cardinality, maximum position f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09170","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/2111.09170/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.09170","created_at":"2026-07-05T03:32:58.490032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09170v1","created_at":"2026-07-05T03:32:58.490032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09170","created_at":"2026-07-05T03:32:58.490032+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFOAG5VCARBE","created_at":"2026-07-05T03:32:58.490032+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFOAG5VCARBEALT6","created_at":"2026-07-05T03:32:58.490032+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFOAG5VC","created_at":"2026-07-05T03:32:58.490032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25808","citing_title":"Generating Input Distributions for Explaining Portfolio Optimization Pipelines","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00475","citing_title":"End-to-End Parametric Portfolio Policies for Cross-Asset Futures Timing: When Do AI Models Beat Simple Rules?","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27610","citing_title":"A Systematic Review of Recent Advancements in PINN Augmented Deep Learning and Mathematical Modeling for Efficient Portfolio Management","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV","json":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV.json","graph_json":"https://pith.science/api/pith-number/XFOAG5VCARBEALT6DML4QOGBBV/graph.json","events_json":"https://pith.science/api/pith-number/XFOAG5VCARBEALT6DML4QOGBBV/events.json","paper":"https://pith.science/paper/XFOAG5VC"},"agent_actions":{"view_html":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV","download_json":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV.json","view_paper":"https://pith.science/paper/XFOAG5VC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09170&json=true","fetch_graph":"https://pith.science/api/pith-number/XFOAG5VCARBEALT6DML4QOGBBV/graph.json","fetch_events":"https://pith.science/api/pith-number/XFOAG5VCARBEALT6DML4QOGBBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV/action/storage_attestation","attest_author":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV/action/author_attestation","sign_citation":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV/action/citation_signature","submit_replication":"https://pith.science/pith/XFOAG5VCARBEALT6DML4QOGBBV/action/replication_record"}},"created_at":"2026-07-05T03:32:58.490032+00:00","updated_at":"2026-07-05T03:32:58.490032+00:00"}