{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CPRIHQ563DX3SO6LFHIRMWY5MJ","short_pith_number":"pith:CPRIHQ56","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"},"canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","source":{"kind":"arxiv","id":"2502.02619","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02619","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02619v1","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02619","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"CPRIHQ563DX3","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"CPRIHQ563DX3SO6L","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"CPRIHQ56","created_at":"2026-07-05T10:09:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CPRIHQ563DX3SO6LFHIRMWY5MJ","target":"record","payload":{"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"},"canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","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"},"source_kind":"arxiv","source_id":"2502.02619","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":"2026-07-05T10:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJLJdZdOY9eyeCw7UjaKjng83byzk/6iDUhYPNQfJHs/rFpMyZWBNMLosdWQLLMWenOBNHPzxvLdEyVaKjr4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:40:35.756919Z"},"content_sha256":"8f917461cf64ee3888de24b99044574e64ece371f18510a16bd57b2f16fcc484","schema_version":"1.0","event_id":"sha256:8f917461cf64ee3888de24b99044574e64ece371f18510a16bd57b2f16fcc484"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CPRIHQ563DX3SO6LFHIRMWY5MJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DRltQV5tzGxcJnBdZceP0uAqPEmVeP/6Fnl1kTQPiYoWOFvZzYm5SxMAjhlNT6IL5TdXrZ3/1XaB/p8M7OxWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:40:35.757445Z"},"content_sha256":"c2e512cf75e554b64bd907c232127f2e22063ceffa304bba2bcf921bd8f17abe","schema_version":"1.0","event_id":"sha256:c2e512cf75e554b64bd907c232127f2e22063ceffa304bba2bcf921bd8f17abe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/bundle.json","state_url":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/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":"2026-08-21T13:40:35Z","links":{"resolver":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ","bundle":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/bundle.json","state":"https://pith.science/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPRIHQ563DX3SO6LFHIRMWY5MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CPRIHQ563DX3SO6LFHIRMWY5MJ","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":"899b251416e40610d85291baec170dd818f2ed2ad66a502dc276b54adea1b143","cross_cats_sorted":["cs.LG","q-fin.RM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2025-02-04T11:45:59Z","title_canon_sha256":"814f5c184225a7671e04fe128121cb5326b5b9e8389176dbe2b573982025e86f"},"schema_version":"1.0","source":{"id":"2502.02619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02619","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02619v1","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02619","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"CPRIHQ563DX3","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"CPRIHQ563DX3SO6L","created_at":"2026-07-05T10:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"CPRIHQ56","created_at":"2026-07-05T10:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:c2e512cf75e554b64bd907c232127f2e22063ceffa304bba2bcf921bd8f17abe","target":"graph","created_at":"2026-07-05T10:09:31Z","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/2502.02619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caglar Gulcehre, Daniil Karzanov, Marcin Detyniecki, Mikhail Terekhov, Rub\\'en Garz\\'on, Thomas Raffinot","cross_cats":["cs.LG","q-fin.RM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2025-02-04T11:45:59Z","title":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02619","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":"sha256:8f917461cf64ee3888de24b99044574e64ece371f18510a16bd57b2f16fcc484","target":"record","created_at":"2026-07-05T10:09:31Z","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":"899b251416e40610d85291baec170dd818f2ed2ad66a502dc276b54adea1b143","cross_cats_sorted":["cs.LG","q-fin.RM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2025-02-04T11:45:59Z","title_canon_sha256":"814f5c184225a7671e04fe128121cb5326b5b9e8389176dbe2b573982025e86f"},"schema_version":"1.0","source":{"id":"2502.02619","kind":"arxiv","version":1}},"canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13e283c3bed8efb93bcb29d1165b1d6270e06bf1f6390780c9ed0a77e0a41210","first_computed_at":"2026-07-05T10:09:31.811725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:31.811725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oPxlApATMbaPsVgP7dQywJfp2Qo+PJ2SZY4CCbr45O8zANYEqA7uywR2RLzbFrRRrisWW1O2bLx7hnPUbBppCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:31.812143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f917461cf64ee3888de24b99044574e64ece371f18510a16bd57b2f16fcc484","sha256:c2e512cf75e554b64bd907c232127f2e22063ceffa304bba2bcf921bd8f17abe"],"state_sha256":"c7351fdf7dab2faa3fa8b312190ad2566e79d325ff42fd10b401852e0afebabd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+HP5/6VMswXAE0N1Jqia3HnLqFXXZQYI0dZGjGVKA7gDXdJRFEnqIHCeKp82zswWSd1SakFfyOs14hR4QKkiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:40:35.761825Z","bundle_sha256":"47340257233429a1f6fcb31d755f3aa4f93a33cefa193b4bd3051ad62db4c60c"}}