{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GWOUSSD6H5JV5WBPMWCZ4BMD5V","short_pith_number":"pith:GWOUSSD6","schema_version":"1.0","canonical_sha256":"359d49487e3f535ed82f65859e0583ed638091cb448e59db7203bf6ee5419175","source":{"kind":"arxiv","id":"2311.14722","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Question Answering over Financial Documents using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chetan Harsha, Karmvir Singh Phogat, Sai Akhil Puranam, Shashishekar Ramakrishna, Sridhar Dasaratha","submitted_at":"2023-11-19T16:23:34Z","abstract_excerpt":"We introduce a large language model (LLM) based approach to answer complex questions requiring multi-hop numerical reasoning over financial reports. While LLMs have exhibited remarkable performance on various natural language and reasoning tasks, complex reasoning problems often rely on few-shot prompts that require carefully crafted examples. In contrast, our approach uses novel zero-shot prompts that guide the LLM to encode the required reasoning into a Python program or a domain specific language. The generated program is then executed by a program interpreter, thus mitigating the limitatio"},"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":"2311.14722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-19T16:23:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"31e5665a7174402f3c09092fad0897fceca354e5411d0526ed24de74b74f6b87","abstract_canon_sha256":"5c9be7788d2ff10ad55218c831f43c68c6ac0381be8084135998265bba87f04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:51.488211Z","signature_b64":"dAOlN8gvN4VOM3l+C/9O1BkRZOxcuTEKt5hUeVTo7fV1fZIzyZWA6f8amncstORxmRhhDWNABmTMRv12n5FHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"359d49487e3f535ed82f65859e0583ed638091cb448e59db7203bf6ee5419175","last_reissued_at":"2026-07-05T07:16:51.487703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:51.487703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Question Answering over Financial Documents using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chetan Harsha, Karmvir Singh Phogat, Sai Akhil Puranam, Shashishekar Ramakrishna, Sridhar Dasaratha","submitted_at":"2023-11-19T16:23:34Z","abstract_excerpt":"We introduce a large language model (LLM) based approach to answer complex questions requiring multi-hop numerical reasoning over financial reports. While LLMs have exhibited remarkable performance on various natural language and reasoning tasks, complex reasoning problems often rely on few-shot prompts that require carefully crafted examples. In contrast, our approach uses novel zero-shot prompts that guide the LLM to encode the required reasoning into a Python program or a domain specific language. The generated program is then executed by a program interpreter, thus mitigating the limitatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14722","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/2311.14722/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":"2311.14722","created_at":"2026-07-05T07:16:51.487760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14722v1","created_at":"2026-07-05T07:16:51.487760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14722","created_at":"2026-07-05T07:16:51.487760+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWOUSSD6H5JV","created_at":"2026-07-05T07:16:51.487760+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWOUSSD6H5JV5WBP","created_at":"2026-07-05T07:16:51.487760+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWOUSSD6","created_at":"2026-07-05T07:16:51.487760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31064","citing_title":"Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05387","citing_title":"Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V","json":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V.json","graph_json":"https://pith.science/api/pith-number/GWOUSSD6H5JV5WBPMWCZ4BMD5V/graph.json","events_json":"https://pith.science/api/pith-number/GWOUSSD6H5JV5WBPMWCZ4BMD5V/events.json","paper":"https://pith.science/paper/GWOUSSD6"},"agent_actions":{"view_html":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V","download_json":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V.json","view_paper":"https://pith.science/paper/GWOUSSD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14722&json=true","fetch_graph":"https://pith.science/api/pith-number/GWOUSSD6H5JV5WBPMWCZ4BMD5V/graph.json","fetch_events":"https://pith.science/api/pith-number/GWOUSSD6H5JV5WBPMWCZ4BMD5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V/action/storage_attestation","attest_author":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V/action/author_attestation","sign_citation":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V/action/citation_signature","submit_replication":"https://pith.science/pith/GWOUSSD6H5JV5WBPMWCZ4BMD5V/action/replication_record"}},"created_at":"2026-07-05T07:16:51.487760+00:00","updated_at":"2026-07-05T07:16:51.487760+00:00"}