{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IQAUTTQIAPXLGP3SVU6ETKLXK6","short_pith_number":"pith:IQAUTTQI","canonical_record":{"source":{"id":"2506.04358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T18:19:48Z","cross_cats_sorted":[],"title_canon_sha256":"6efffc7680057d49aac9452afbeaa83b7a6872e7a832cff58bd9dd5f119b4e7f","abstract_canon_sha256":"0299dc6d42468087b5096935350663d920a0c96eb902c55e5a9771b35153429e"},"schema_version":"1.0"},"canonical_sha256":"440149ce0803eeb33f72ad3c49a977579a0c6432cbc0b55f2dd26311ee62470e","source":{"kind":"arxiv","id":"2506.04358","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04358","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04358v1","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04358","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"IQAUTTQIAPXL","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"IQAUTTQIAPXLGP3S","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"IQAUTTQI","created_at":"2026-07-05T11:16:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IQAUTTQIAPXLGP3SVU6ETKLXK6","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T18:19:48Z","cross_cats_sorted":[],"title_canon_sha256":"6efffc7680057d49aac9452afbeaa83b7a6872e7a832cff58bd9dd5f119b4e7f","abstract_canon_sha256":"0299dc6d42468087b5096935350663d920a0c96eb902c55e5a9771b35153429e"},"schema_version":"1.0"},"canonical_sha256":"440149ce0803eeb33f72ad3c49a977579a0c6432cbc0b55f2dd26311ee62470e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:13.195898Z","signature_b64":"D5SNvE39F+mVuHPvYBwDD+6IKJ6ztGNdylRVl0UGy2dLCkhhXjgRXDoLN6JhasII6QFtQWULfL2ySG/Z2P6BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"440149ce0803eeb33f72ad3c49a977579a0c6432cbc0b55f2dd26311ee62470e","last_reissued_at":"2026-07-05T11:16:13.195412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:13.195412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04358","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":"2026-07-05T11:16:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGZ+HqsEEnEueWyXT+HCZElYUjEpXBu8Eog5c5hH5oxAoh7WOF/j8brSyHkjlktCxsu3QQTSz1h6MMON8yGcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:03:35.425029Z"},"content_sha256":"080709d8cce978c6df565b543714b91da3f50c946ea2293ebf88cab855cf0a07","schema_version":"1.0","event_id":"sha256:080709d8cce978c6df565b543714b91da3f50c946ea2293ebf88cab855cf0a07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IQAUTTQIAPXLGP3SVU6ETKLXK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Risk-Aware Reinforcement Learning Reward for Financial Trading","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shaurya Singh, Shivam Aryan, Uditansh Srivastava","submitted_at":"2025-06-04T18:19:48Z","abstract_excerpt":"We propose a novel composite reward function for reinforcement learning in financial trading that balances return and risk using four differentiable terms: annualized return downside risk differential return and the Treynor ratio\n  Unlike single metric objectives for example the Sharpe ratio our formulation is modular and parameterized by weights w1 w2 w3 and w4 enabling practitioners to encode diverse investor preferences\n  We tune these weights via grid search to target specific risk return profiles\n  We derive closed form gradients for each term to facilitate gradient based training and ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04358","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/2506.04358/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":"2026-07-05T11:16:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Qjp8CCDQ+rSNcPfCsXlcQa7Lv5SR2PW1lW2/owYRisKYz9VpjpDA7AjJzTasdAxb85A7TOkCl/BnL37x1bzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:03:35.425555Z"},"content_sha256":"3fb0f86d917331f8e2ec37c0f02bcbb7a1859d52a143026b31cafa89d3762c13","schema_version":"1.0","event_id":"sha256:3fb0f86d917331f8e2ec37c0f02bcbb7a1859d52a143026b31cafa89d3762c13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/bundle.json","state_url":"https://pith.science/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/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":"2026-08-08T19:03:35Z","links":{"resolver":"https://pith.science/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6","bundle":"https://pith.science/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/bundle.json","state":"https://pith.science/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQAUTTQIAPXLGP3SVU6ETKLXK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IQAUTTQIAPXLGP3SVU6ETKLXK6","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":"0299dc6d42468087b5096935350663d920a0c96eb902c55e5a9771b35153429e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T18:19:48Z","title_canon_sha256":"6efffc7680057d49aac9452afbeaa83b7a6872e7a832cff58bd9dd5f119b4e7f"},"schema_version":"1.0","source":{"id":"2506.04358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04358","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04358v1","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04358","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"IQAUTTQIAPXL","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"IQAUTTQIAPXLGP3S","created_at":"2026-07-05T11:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"IQAUTTQI","created_at":"2026-07-05T11:16:13Z"}],"graph_snapshots":[{"event_id":"sha256:3fb0f86d917331f8e2ec37c0f02bcbb7a1859d52a143026b31cafa89d3762c13","target":"graph","created_at":"2026-07-05T11:16:13Z","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/2506.04358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel composite reward function for reinforcement learning in financial trading that balances return and risk using four differentiable terms: annualized return downside risk differential return and the Treynor ratio\n  Unlike single metric objectives for example the Sharpe ratio our formulation is modular and parameterized by weights w1 w2 w3 and w4 enabling practitioners to encode diverse investor preferences\n  We tune these weights via grid search to target specific risk return profiles\n  We derive closed form gradients for each term to facilitate gradient based training and ana","authors_text":"Shaurya Singh, Shivam Aryan, Uditansh Srivastava","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T18:19:48Z","title":"A Risk-Aware Reinforcement Learning Reward for Financial Trading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04358","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":"sha256:080709d8cce978c6df565b543714b91da3f50c946ea2293ebf88cab855cf0a07","target":"record","created_at":"2026-07-05T11:16:13Z","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":"0299dc6d42468087b5096935350663d920a0c96eb902c55e5a9771b35153429e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T18:19:48Z","title_canon_sha256":"6efffc7680057d49aac9452afbeaa83b7a6872e7a832cff58bd9dd5f119b4e7f"},"schema_version":"1.0","source":{"id":"2506.04358","kind":"arxiv","version":1}},"canonical_sha256":"440149ce0803eeb33f72ad3c49a977579a0c6432cbc0b55f2dd26311ee62470e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"440149ce0803eeb33f72ad3c49a977579a0c6432cbc0b55f2dd26311ee62470e","first_computed_at":"2026-07-05T11:16:13.195412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:13.195412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D5SNvE39F+mVuHPvYBwDD+6IKJ6ztGNdylRVl0UGy2dLCkhhXjgRXDoLN6JhasII6QFtQWULfL2ySG/Z2P6BBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:13.195898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:080709d8cce978c6df565b543714b91da3f50c946ea2293ebf88cab855cf0a07","sha256:3fb0f86d917331f8e2ec37c0f02bcbb7a1859d52a143026b31cafa89d3762c13"],"state_sha256":"c388f74bb99a2564a0da74c60d03793a06bb5554a51fb7d283f343e233ee6b4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIIyw1Fh3ivo9LwPeZl4uT4I/3KS4Z5qgVWraV0CcwHTVmdy2Fyt0O7dKwrEnnMh4olnrc5P9B2KR+w4+qHjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:03:35.431234Z","bundle_sha256":"ac98eb4e3a1504b5301e915f3f3b682c532e5f8b8b7c54daa65e6c6e5972f88d"}}