{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HE3X3BFG5R4TKONO7567RULYDH","short_pith_number":"pith:HE3X3BFG","schema_version":"1.0","canonical_sha256":"39377d84a6ec793539aeff7df8d17819f308a438bd4136d99df72bec122e18c0","source":{"kind":"arxiv","id":"2412.15386","version":1},"attestation_state":"computed","paper":{"title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lavanya Gupta, Saket Sharma, Yiyun Zhao","submitted_at":"2024-12-19T20:26:55Z","abstract_excerpt":"Long-context large language models (LC LLMs) promise to increase reliability of LLMs in real-world tasks requiring processing and understanding of long input documents. However, this ability of LC LLMs to reliably utilize their growing context windows remains under investigation. In this work, we evaluate the performance of state-of-the-art GPT-4 suite of LC LLMs in solving a series of progressively challenging tasks, as a function of factors such as context length, task difficulty, and position of key information by creating a real world financial news dataset. Our findings indicate that LC L"},"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":"2412.15386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T20:26:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0922f2b64c5a888807a691a4e0fb8f66b17194818e326ed92feacee1a4e60334","abstract_canon_sha256":"15a5a73ffa02950b92d1bb2e391ec96412eb9c16eb2111487878abc7a785ba62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:22.359490Z","signature_b64":"g6ELnTtM724UkCQb/BgkSHgUvXUma8RQoynpvmmBSklPXXVixkZ/hsU+la4XAO9buev+0E/f2Wkddtinw7j5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39377d84a6ec793539aeff7df8d17819f308a438bd4136d99df72bec122e18c0","last_reissued_at":"2026-07-05T09:52:22.358442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:22.358442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lavanya Gupta, Saket Sharma, Yiyun Zhao","submitted_at":"2024-12-19T20:26:55Z","abstract_excerpt":"Long-context large language models (LC LLMs) promise to increase reliability of LLMs in real-world tasks requiring processing and understanding of long input documents. However, this ability of LC LLMs to reliably utilize their growing context windows remains under investigation. In this work, we evaluate the performance of state-of-the-art GPT-4 suite of LC LLMs in solving a series of progressively challenging tasks, as a function of factors such as context length, task difficulty, and position of key information by creating a real world financial news dataset. Our findings indicate that LC L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15386","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/2412.15386/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":"2412.15386","created_at":"2026-07-05T09:52:22.359020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15386v1","created_at":"2026-07-05T09:52:22.359020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15386","created_at":"2026-07-05T09:52:22.359020+00:00"},{"alias_kind":"pith_short_12","alias_value":"HE3X3BFG5R4T","created_at":"2026-07-05T09:52:22.359020+00:00"},{"alias_kind":"pith_short_16","alias_value":"HE3X3BFG5R4TKONO","created_at":"2026-07-05T09:52:22.359020+00:00"},{"alias_kind":"pith_short_8","alias_value":"HE3X3BFG","created_at":"2026-07-05T09:52:22.359020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04290","citing_title":"Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH","json":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH.json","graph_json":"https://pith.science/api/pith-number/HE3X3BFG5R4TKONO7567RULYDH/graph.json","events_json":"https://pith.science/api/pith-number/HE3X3BFG5R4TKONO7567RULYDH/events.json","paper":"https://pith.science/paper/HE3X3BFG"},"agent_actions":{"view_html":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH","download_json":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH.json","view_paper":"https://pith.science/paper/HE3X3BFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15386&json=true","fetch_graph":"https://pith.science/api/pith-number/HE3X3BFG5R4TKONO7567RULYDH/graph.json","fetch_events":"https://pith.science/api/pith-number/HE3X3BFG5R4TKONO7567RULYDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH/action/storage_attestation","attest_author":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH/action/author_attestation","sign_citation":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH/action/citation_signature","submit_replication":"https://pith.science/pith/HE3X3BFG5R4TKONO7567RULYDH/action/replication_record"}},"created_at":"2026-07-05T09:52:22.359020+00:00","updated_at":"2026-07-05T09:52:22.359020+00:00"}