{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZS5AEWUD74WM457Y2WJMHHBMSX","short_pith_number":"pith:ZS5AEWUD","schema_version":"1.0","canonical_sha256":"ccba025a83ff2cce77f8d592c39c2c95e31d09b67f4d968d12b0307c8291791e","source":{"kind":"arxiv","id":"2504.00042","version":2},"attestation_state":"computed","paper":{"title":"Beyond the Reported Cutoff: Where Large Language Models Fall Short on Financial Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agam Shah, Liqin Ye, Sebastian Jaskowski, Sudheer Chava, Wei Xu","submitted_at":"2025-03-30T19:43:20Z","abstract_excerpt":"Large Language Models (LLMs) are frequently utilized as sources of knowledge for question-answering. While it is known that LLMs may lack access to real-time data or newer data produced after the model's cutoff date, it is less clear how their knowledge spans across historical information. In this study, we assess the breadth of LLMs' knowledge using financial data of U.S. publicly traded companies by evaluating more than 197k questions and comparing model responses to factual data. We further explore the impact of company characteristics, such as size, retail investment, institutional attenti"},"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":"2504.00042","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-30T19:43:20Z","cross_cats_sorted":[],"title_canon_sha256":"cc1aebb9afc2c3094aba525b02f6b8904f00bd556d38a315ab35a8f7bf216916","abstract_canon_sha256":"5cffbfd13a05c0d27d4d85944ffdb2ea7ff9b583e25ee24b0d19e24f1a06a2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:47.318481Z","signature_b64":"Piv8gBhetNlyTwL34y8Cj379SvDB6R9wPb4xgBizRhIkjxGa5Zk8mMmB7B3L0DJLC0PjtGVjWFBJCRh4w/R7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccba025a83ff2cce77f8d592c39c2c95e31d09b67f4d968d12b0307c8291791e","last_reissued_at":"2026-07-05T11:44:47.317902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:47.317902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Reported Cutoff: Where Large Language Models Fall Short on Financial Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agam Shah, Liqin Ye, Sebastian Jaskowski, Sudheer Chava, Wei Xu","submitted_at":"2025-03-30T19:43:20Z","abstract_excerpt":"Large Language Models (LLMs) are frequently utilized as sources of knowledge for question-answering. While it is known that LLMs may lack access to real-time data or newer data produced after the model's cutoff date, it is less clear how their knowledge spans across historical information. In this study, we assess the breadth of LLMs' knowledge using financial data of U.S. publicly traded companies by evaluating more than 197k questions and comparing model responses to factual data. We further explore the impact of company characteristics, such as size, retail investment, institutional attenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00042","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/2504.00042/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":"2504.00042","created_at":"2026-07-05T11:44:47.317994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00042v2","created_at":"2026-07-05T11:44:47.317994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00042","created_at":"2026-07-05T11:44:47.317994+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZS5AEWUD74WM","created_at":"2026-07-05T11:44:47.317994+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZS5AEWUD74WM457Y","created_at":"2026-07-05T11:44:47.317994+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZS5AEWUD","created_at":"2026-07-05T11:44:47.317994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28714","citing_title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16895","citing_title":"The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08519","citing_title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX","json":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX.json","graph_json":"https://pith.science/api/pith-number/ZS5AEWUD74WM457Y2WJMHHBMSX/graph.json","events_json":"https://pith.science/api/pith-number/ZS5AEWUD74WM457Y2WJMHHBMSX/events.json","paper":"https://pith.science/paper/ZS5AEWUD"},"agent_actions":{"view_html":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX","download_json":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX.json","view_paper":"https://pith.science/paper/ZS5AEWUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00042&json=true","fetch_graph":"https://pith.science/api/pith-number/ZS5AEWUD74WM457Y2WJMHHBMSX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZS5AEWUD74WM457Y2WJMHHBMSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX/action/storage_attestation","attest_author":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX/action/author_attestation","sign_citation":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX/action/citation_signature","submit_replication":"https://pith.science/pith/ZS5AEWUD74WM457Y2WJMHHBMSX/action/replication_record"}},"created_at":"2026-07-05T11:44:47.317994+00:00","updated_at":"2026-07-05T11:44:47.317994+00:00"}