{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PS7K46XDGJDESXX5QFL53ROGTO","short_pith_number":"pith:PS7K46XD","schema_version":"1.0","canonical_sha256":"7cbeae7ae33246495efd8157ddc5c69b994ab6eccd3315826dd6090d11d0617b","source":{"kind":"arxiv","id":"2412.19245","version":1},"attestation_state":"computed","paper":{"title":"Sentiment trading with large language models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","q-fin.PM","q-fin.TR"],"primary_cat":"q-fin.CP","authors_text":"Guido Germano, Kemal Kirtac","submitted_at":"2024-12-26T15:01:24Z","abstract_excerpt":"We investigate the efficacy of large language models (LLMs) in sentiment analysis of U.S. financial news and their potential in predicting stock market returns. We analyze a dataset comprising 965,375 news articles that span from January 1, 2010, to June 30, 2023; we focus on the performance of various LLMs, including BERT, OPT, FINBERT, and the traditional Loughran-McDonald dictionary model, which has been a dominant methodology in the finance literature. The study documents a significant association between LLM scores and subsequent daily stock returns. Specifically, OPT, which is a GPT-3 ba"},"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":"2412.19245","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"q-fin.CP","submitted_at":"2024-12-26T15:01:24Z","cross_cats_sorted":["cs.LG","econ.EM","q-fin.PM","q-fin.TR"],"title_canon_sha256":"80eb116a77f0acf8cc1368aa80e93b1efddd8bb0ec18e166920f78d7465ff3a5","abstract_canon_sha256":"730b2c4de8310b7295e6936467ac26eab8f0fc2d0dab5f652d02fe9a0e5af80a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:32.760087Z","signature_b64":"1gjCeUgvcUEQGKEWoY2zvo0AMjtjbjpHQjXVuopG6AxzVnsmfSIqPwLcNNqskTvGaMGXkEhznbA4hSHEFlgwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cbeae7ae33246495efd8157ddc5c69b994ab6eccd3315826dd6090d11d0617b","last_reissued_at":"2026-07-05T09:54:32.759650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:32.759650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentiment trading with large language models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","q-fin.PM","q-fin.TR"],"primary_cat":"q-fin.CP","authors_text":"Guido Germano, Kemal Kirtac","submitted_at":"2024-12-26T15:01:24Z","abstract_excerpt":"We investigate the efficacy of large language models (LLMs) in sentiment analysis of U.S. financial news and their potential in predicting stock market returns. We analyze a dataset comprising 965,375 news articles that span from January 1, 2010, to June 30, 2023; we focus on the performance of various LLMs, including BERT, OPT, FINBERT, and the traditional Loughran-McDonald dictionary model, which has been a dominant methodology in the finance literature. The study documents a significant association between LLM scores and subsequent daily stock returns. Specifically, OPT, which is a GPT-3 ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19245","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/2412.19245/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":"2412.19245","created_at":"2026-07-05T09:54:32.759707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19245v1","created_at":"2026-07-05T09:54:32.759707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19245","created_at":"2026-07-05T09:54:32.759707+00:00"},{"alias_kind":"pith_short_12","alias_value":"PS7K46XDGJDE","created_at":"2026-07-05T09:54:32.759707+00:00"},{"alias_kind":"pith_short_16","alias_value":"PS7K46XDGJDESXX5","created_at":"2026-07-05T09:54:32.759707+00:00"},{"alias_kind":"pith_short_8","alias_value":"PS7K46XD","created_at":"2026-07-05T09:54:32.759707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO","json":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO.json","graph_json":"https://pith.science/api/pith-number/PS7K46XDGJDESXX5QFL53ROGTO/graph.json","events_json":"https://pith.science/api/pith-number/PS7K46XDGJDESXX5QFL53ROGTO/events.json","paper":"https://pith.science/paper/PS7K46XD"},"agent_actions":{"view_html":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO","download_json":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO.json","view_paper":"https://pith.science/paper/PS7K46XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19245&json=true","fetch_graph":"https://pith.science/api/pith-number/PS7K46XDGJDESXX5QFL53ROGTO/graph.json","fetch_events":"https://pith.science/api/pith-number/PS7K46XDGJDESXX5QFL53ROGTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO/action/storage_attestation","attest_author":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO/action/author_attestation","sign_citation":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO/action/citation_signature","submit_replication":"https://pith.science/pith/PS7K46XDGJDESXX5QFL53ROGTO/action/replication_record"}},"created_at":"2026-07-05T09:54:32.759707+00:00","updated_at":"2026-07-05T09:54:32.759707+00:00"}