{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E6BYIPQHSQZTEAIV36Z5KB34V5","short_pith_number":"pith:E6BYIPQH","schema_version":"1.0","canonical_sha256":"2783843e079433320115dfb3d5077caf4052b89ad8053902ededbcc79e47a358","source":{"kind":"arxiv","id":"2505.06408","version":2},"attestation_state":"computed","paper":{"title":"A New DAPO Algorithm for Stock Trading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Bojun Liu, Ruijian Zha","submitted_at":"2025-05-09T20:12:59Z","abstract_excerpt":"Recent advances in reinforcement learning, such as Dynamic Sampling Policy Optimization (DAPO), show strong performance when paired with large language models (LLMs). Motivated by this success, we ask whether similar gains can be realized in financial trading. We design a trading agent that combines an improved Group Relative Policy Optimization (GRPO) algorithm, augmented with ideas from DAPO, with LLM-based risk and sentiment signals extracted from financial news. On the NASDAQ-100 index (FNSPID dataset), our agent attains a cumulative return of 230.49 percent and an information ratio of 0.3"},"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":"2505.06408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2025-05-09T20:12:59Z","cross_cats_sorted":[],"title_canon_sha256":"faa3d579dc295596ce4bd772d26f39345655f60348e96a716bb0eec37649bcfb","abstract_canon_sha256":"40db46a95db56af8d65c537e609b0a662fe52515cbfd8b6dc20c2af23447d095"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:13.018784Z","signature_b64":"FcfOMmnnxzFgBJYZfrXaTIfwDDf/ESCc0H7lwPfdYkAJXh9eVrap8+kUNUhYXs++Mn3Kv8aoOsJ5peGwV1xhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2783843e079433320115dfb3d5077caf4052b89ad8053902ededbcc79e47a358","last_reissued_at":"2026-07-05T11:09:13.018281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:13.018281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New DAPO Algorithm for Stock Trading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Bojun Liu, Ruijian Zha","submitted_at":"2025-05-09T20:12:59Z","abstract_excerpt":"Recent advances in reinforcement learning, such as Dynamic Sampling Policy Optimization (DAPO), show strong performance when paired with large language models (LLMs). Motivated by this success, we ask whether similar gains can be realized in financial trading. We design a trading agent that combines an improved Group Relative Policy Optimization (GRPO) algorithm, augmented with ideas from DAPO, with LLM-based risk and sentiment signals extracted from financial news. On the NASDAQ-100 index (FNSPID dataset), our agent attains a cumulative return of 230.49 percent and an information ratio of 0.3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06408","kind":"arxiv","version":2},"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/2505.06408/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":"2505.06408","created_at":"2026-07-05T11:09:13.018348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06408v2","created_at":"2026-07-05T11:09:13.018348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06408","created_at":"2026-07-05T11:09:13.018348+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6BYIPQHSQZT","created_at":"2026-07-05T11:09:13.018348+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6BYIPQHSQZTEAIV","created_at":"2026-07-05T11:09:13.018348+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6BYIPQH","created_at":"2026-07-05T11:09:13.018348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09880","citing_title":"Financial Numerical Prediction and Allocation as Token Generation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5","json":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5.json","graph_json":"https://pith.science/api/pith-number/E6BYIPQHSQZTEAIV36Z5KB34V5/graph.json","events_json":"https://pith.science/api/pith-number/E6BYIPQHSQZTEAIV36Z5KB34V5/events.json","paper":"https://pith.science/paper/E6BYIPQH"},"agent_actions":{"view_html":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5","download_json":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5.json","view_paper":"https://pith.science/paper/E6BYIPQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06408&json=true","fetch_graph":"https://pith.science/api/pith-number/E6BYIPQHSQZTEAIV36Z5KB34V5/graph.json","fetch_events":"https://pith.science/api/pith-number/E6BYIPQHSQZTEAIV36Z5KB34V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5/action/storage_attestation","attest_author":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5/action/author_attestation","sign_citation":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5/action/citation_signature","submit_replication":"https://pith.science/pith/E6BYIPQHSQZTEAIV36Z5KB34V5/action/replication_record"}},"created_at":"2026-07-05T11:09:13.018348+00:00","updated_at":"2026-07-05T11:09:13.018348+00:00"}