{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C3QKGJNM7CNACABCBQFQQNJ6SE","short_pith_number":"pith:C3QKGJNM","schema_version":"1.0","canonical_sha256":"16e0a325acf89a0100220c0b08353e9137727ed347ac1e83aa9069cf78b7b760","source":{"kind":"arxiv","id":"2606.08450","version":1},"attestation_state":"computed","paper":{"title":"GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyi Zhang, Chang Liu, Dexu Yu, Hanwen Du, Hao Zeng, Jiacheng Liu, Jining Luan, Meiqi Zhang, Xinyu Fang, Yanlin Liu, Yanyan Wu, Yongxin Ni, Youhua Li","submitted_at":"2026-06-07T04:45:19Z","abstract_excerpt":"Financial portfolio trading is naturally formulated as a reinforcement learning problem, where an agent sequentially rebalances assets under changing market conditions to balance return, risk, and transaction costs. Yet in non-stationary markets, raw OHLCV states and short-horizon return rewards often provide an under-specified learning interface, motivating large language models as a way to inject financial knowledge into state and reward design while constraining open-ended generation. To this end, we propose GIFT, an LLM-guided framework for state-reward interface design in PPO-based financ"},"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":"2606.08450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T04:45:19Z","cross_cats_sorted":[],"title_canon_sha256":"785fa0afc2c14d8bcc8ad4c20aa63a7de3814049dc0b64b66c9f07a93ed4660b","abstract_canon_sha256":"b4bd375d0ee6e7b7840994a011e042dfd2e399bedc80db95602da4ebd0c416dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:36.983653Z","signature_b64":"P1D6MScycmMUzbMHXAm3Y9ZAcsA0l2ao1IXoGl/qeoZTG2dffgM0DXejyvRqOxUnF1kMQWtb3seS1gEN/kPeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e0a325acf89a0100220c0b08353e9137727ed347ac1e83aa9069cf78b7b760","last_reissued_at":"2026-06-09T01:05:36.983190Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:36.983190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyi Zhang, Chang Liu, Dexu Yu, Hanwen Du, Hao Zeng, Jiacheng Liu, Jining Luan, Meiqi Zhang, Xinyu Fang, Yanlin Liu, Yanyan Wu, Yongxin Ni, Youhua Li","submitted_at":"2026-06-07T04:45:19Z","abstract_excerpt":"Financial portfolio trading is naturally formulated as a reinforcement learning problem, where an agent sequentially rebalances assets under changing market conditions to balance return, risk, and transaction costs. Yet in non-stationary markets, raw OHLCV states and short-horizon return rewards often provide an under-specified learning interface, motivating large language models as a way to inject financial knowledge into state and reward design while constraining open-ended generation. To this end, we propose GIFT, an LLM-guided framework for state-reward interface design in PPO-based financ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08450","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/2606.08450/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":"2606.08450","created_at":"2026-06-09T01:05:36.983250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08450v1","created_at":"2026-06-09T01:05:36.983250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08450","created_at":"2026-06-09T01:05:36.983250+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3QKGJNM7CNA","created_at":"2026-06-09T01:05:36.983250+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3QKGJNM7CNACABC","created_at":"2026-06-09T01:05:36.983250+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3QKGJNM","created_at":"2026-06-09T01:05:36.983250+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/C3QKGJNM7CNACABCBQFQQNJ6SE","json":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE.json","graph_json":"https://pith.science/api/pith-number/C3QKGJNM7CNACABCBQFQQNJ6SE/graph.json","events_json":"https://pith.science/api/pith-number/C3QKGJNM7CNACABCBQFQQNJ6SE/events.json","paper":"https://pith.science/paper/C3QKGJNM"},"agent_actions":{"view_html":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE","download_json":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE.json","view_paper":"https://pith.science/paper/C3QKGJNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08450&json=true","fetch_graph":"https://pith.science/api/pith-number/C3QKGJNM7CNACABCBQFQQNJ6SE/graph.json","fetch_events":"https://pith.science/api/pith-number/C3QKGJNM7CNACABCBQFQQNJ6SE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE/action/storage_attestation","attest_author":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE/action/author_attestation","sign_citation":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE/action/citation_signature","submit_replication":"https://pith.science/pith/C3QKGJNM7CNACABCBQFQQNJ6SE/action/replication_record"}},"created_at":"2026-06-09T01:05:36.983250+00:00","updated_at":"2026-06-09T01:05:36.983250+00:00"}