{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UR625CEGRQDYHF463LR56FO4UB","short_pith_number":"pith:UR625CEG","schema_version":"1.0","canonical_sha256":"a47dae88868c0783979edae3df15dca0671192c869e17b87ce58714cfc6a3c40","source":{"kind":"arxiv","id":"2404.05101","version":3},"attestation_state":"computed","paper":{"title":"StockGPT: A GenAI Model for Stock Prediction and Trading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-fin.PM","q-fin.PR","q-fin.ST"],"primary_cat":"q-fin.CP","authors_text":"Dat Mai","submitted_at":"2024-04-07T22:53:43Z","abstract_excerpt":"This paper introduces StockGPT, an autoregressive ``number'' model trained and tested on 70 million daily U.S.\\ stock returns over nearly 100 years. Treating each return series as a sequence of tokens, StockGPT automatically learns the hidden patterns predictive of future returns via its attention mechanism. On a held-out test sample from 2001 to 2023, daily and monthly rebalanced long-short portfolios formed from StockGPT predictions yield strong performance. The StockGPT-based portfolios span momentum and long-/short-term reversals, eliminating the need for manually crafted price-based strat"},"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":"2404.05101","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2024-04-07T22:53:43Z","cross_cats_sorted":["cs.AI","q-fin.PM","q-fin.PR","q-fin.ST"],"title_canon_sha256":"3f1c4cf75776b955eb6ea69ac9f520fde2b15e77e8c28425062404d153357580","abstract_canon_sha256":"28e7541403573a24ff43ebdb411cc1b7a029a4c37444facef8f8ac5113a1b476"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:33.701113Z","signature_b64":"wA7IkdwvO7qCuSziT/R5d1Amg7KHUaew9fT4iYNY39gF3hpPAgbThRCrdqlVnAaK7aBQ+ePaQCFG2I/aEkG3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47dae88868c0783979edae3df15dca0671192c869e17b87ce58714cfc6a3c40","last_reissued_at":"2026-07-05T09:24:33.700544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:33.700544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StockGPT: A GenAI Model for Stock Prediction and Trading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-fin.PM","q-fin.PR","q-fin.ST"],"primary_cat":"q-fin.CP","authors_text":"Dat Mai","submitted_at":"2024-04-07T22:53:43Z","abstract_excerpt":"This paper introduces StockGPT, an autoregressive ``number'' model trained and tested on 70 million daily U.S.\\ stock returns over nearly 100 years. Treating each return series as a sequence of tokens, StockGPT automatically learns the hidden patterns predictive of future returns via its attention mechanism. On a held-out test sample from 2001 to 2023, daily and monthly rebalanced long-short portfolios formed from StockGPT predictions yield strong performance. The StockGPT-based portfolios span momentum and long-/short-term reversals, eliminating the need for manually crafted price-based strat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05101","kind":"arxiv","version":3},"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/2404.05101/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":"2404.05101","created_at":"2026-07-05T09:24:33.700610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05101v3","created_at":"2026-07-05T09:24:33.700610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05101","created_at":"2026-07-05T09:24:33.700610+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR625CEGRQDY","created_at":"2026-07-05T09:24:33.700610+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR625CEGRQDYHF46","created_at":"2026-07-05T09:24:33.700610+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR625CEG","created_at":"2026-07-05T09:24:33.700610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08285","citing_title":"Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01954","citing_title":"Moira: Language-driven Hierarchical Reinforcement Learning for Pair Trading","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB","json":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB.json","graph_json":"https://pith.science/api/pith-number/UR625CEGRQDYHF463LR56FO4UB/graph.json","events_json":"https://pith.science/api/pith-number/UR625CEGRQDYHF463LR56FO4UB/events.json","paper":"https://pith.science/paper/UR625CEG"},"agent_actions":{"view_html":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB","download_json":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB.json","view_paper":"https://pith.science/paper/UR625CEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05101&json=true","fetch_graph":"https://pith.science/api/pith-number/UR625CEGRQDYHF463LR56FO4UB/graph.json","fetch_events":"https://pith.science/api/pith-number/UR625CEGRQDYHF463LR56FO4UB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB/action/storage_attestation","attest_author":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB/action/author_attestation","sign_citation":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB/action/citation_signature","submit_replication":"https://pith.science/pith/UR625CEGRQDYHF463LR56FO4UB/action/replication_record"}},"created_at":"2026-07-05T09:24:33.700610+00:00","updated_at":"2026-07-05T09:24:33.700610+00:00"}