{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPRIHQ563DX3SO6LFHIRMWY5MJ","short_pith_number":"pith:CPRIHQ56","schema_version":"1.0","canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","source":{"kind":"arxiv","id":"2502.02619","version":1},"attestation_state":"computed","paper":{"title":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.RM"],"primary_cat":"q-fin.PM","authors_text":"Caglar Gulcehre, Daniil Karzanov, Marcin Detyniecki, Mikhail Terekhov, Rub\\'en Garz\\'on, Thomas Raffinot","submitted_at":"2025-02-04T11:45:59Z","abstract_excerpt":"This paper introduces a novel agent-based approach for enhancing existing portfolio strategies using Proximal Policy Optimization (PPO). Rather than focusing solely on traditional portfolio construction, our approach aims to improve an already high-performing strategy through dynamic rebalancing driven by PPO and Oracle agents. Our target is to enhance the traditional 60/40 benchmark (60% stocks, 40% bonds) by employing the Regret-based Sharpe reward function. To address the impact of transaction fee frictions and prevent signal loss, we develop a transaction cost scheduler. We introduce a fut"},"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":"2502.02619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2025-02-04T11:45:59Z","cross_cats_sorted":["cs.LG","q-fin.RM"],"title_canon_sha256":"814f5c184225a7671e04fe128121cb5326b5b9e8389176dbe2b573982025e86f","abstract_canon_sha256":"899b251416e40610d85291baec170dd818f2ed2ad66a502dc276b54adea1b143"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:31.812143Z","signature_b64":"oPxlApATMbaPsVgP7dQywJfp2Qo+PJ2SZY4CCbr45O8zANYEqA7uywR2RLzbFrRRrisWW1O2bLx7hnPUbBppCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","last_reissued_at":"2026-07-05T10:09:31.811725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:31.811725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.RM"],"primary_cat":"q-fin.PM","authors_text":"Caglar Gulcehre, Daniil Karzanov, Marcin Detyniecki, Mikhail Terekhov, Rub\\'en Garz\\'on, Thomas Raffinot","submitted_at":"2025-02-04T11:45:59Z","abstract_excerpt":"This paper introduces a novel agent-based approach for enhancing existing portfolio strategies using Proximal Policy Optimization (PPO). Rather than focusing solely on traditional portfolio construction, our approach aims to improve an already high-performing strategy through dynamic rebalancing driven by PPO and Oracle agents. Our target is to enhance the traditional 60/40 benchmark (60% stocks, 40% bonds) by employing the Regret-based Sharpe reward function. To address the impact of transaction fee frictions and prevent signal loss, we develop a transaction cost scheduler. We introduce a fut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02619","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/2502.02619/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":"2502.02619","created_at":"2026-07-05T10:09:31.811783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02619v1","created_at":"2026-07-05T10:09:31.811783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02619","created_at":"2026-07-05T10:09:31.811783+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPRIHQ563DX3","created_at":"2026-07-05T10:09:31.811783+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPRIHQ563DX3SO6L","created_at":"2026-07-05T10:09:31.811783+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPRIHQ56","created_at":"2026-07-05T10:09:31.811783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ","json":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ.json","graph_json":"https://pith.science/api/pith-number/CPRIHQ563DX3SO6LFHIRMWY5MJ/graph.json","events_json":"https://pith.science/api/pith-number/CPRIHQ563DX3SO6LFHIRMWY5MJ/events.json","paper":"https://pith.science/paper/CPRIHQ56"},"agent_actions":{"view_html":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ","download_json":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ.json","view_paper":"https://pith.science/paper/CPRIHQ56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02619&json=true","fetch_graph":"https://pith.science/api/pith-number/CPRIHQ563DX3SO6LFHIRMWY5MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CPRIHQ563DX3SO6LFHIRMWY5MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/action/storage_attestation","attest_author":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/action/author_attestation","sign_citation":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/action/citation_signature","submit_replication":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/action/replication_record"}},"created_at":"2026-07-05T10:09:31.811783+00:00","updated_at":"2026-07-05T10:09:31.811783+00:00"}