{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GSLY4BOHURVMPRR6WXATTZYH7D","short_pith_number":"pith:GSLY4BOH","schema_version":"1.0","canonical_sha256":"34978e05c7a46ac7c63eb5c139e707f8e92e03754f2244faefd84fc68ed56a2c","source":{"kind":"arxiv","id":"2411.07264","version":1},"attestation_state":"computed","paper":{"title":"Multi-Document Financial Question Answering using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ramasubbu Venkatesh, Shalin Shah, Srikanth Ryali","submitted_at":"2024-11-08T21:03:54Z","abstract_excerpt":"We propose two new methods for multi-document financial question answering. First, a method that uses semantic tagging, and then, queries the index to get the context (RAG_SEM). And second, a Knowledge Graph (KG_RAG) based method that uses semantic tagging, and, retrieves knowledge graph triples from a graph database, as context. KG_RAG uses knowledge graphs constructed using a small model that is fine-tuned using knowledge distillation using a large teacher model. The data consists of 18 10K reports of Apple, Microsoft, Alphabet, NVIDIA, Amazon and Tesla for the years 2021, 2022 and 2023. The"},"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":"2411.07264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-08T21:03:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4129c14d85db85a22452d5fe50cc0020836ebfeef638736348ed85bfe860c9a0","abstract_canon_sha256":"5ecbe6eadd70701684ce3a9cc209b1251a1ebb3a4b30d0f319b1bf692110567e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:00.867501Z","signature_b64":"xaB6gr4hOUJQqOGFAqnpCFMeyden+bEfuao6f0QkA4cHyAhhr5/7hSVdatLJW9agqoGGDJxpThH7iTbRoTqADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34978e05c7a46ac7c63eb5c139e707f8e92e03754f2244faefd84fc68ed56a2c","last_reissued_at":"2026-07-05T09:34:00.867007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:00.867007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Document Financial Question Answering using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ramasubbu Venkatesh, Shalin Shah, Srikanth Ryali","submitted_at":"2024-11-08T21:03:54Z","abstract_excerpt":"We propose two new methods for multi-document financial question answering. First, a method that uses semantic tagging, and then, queries the index to get the context (RAG_SEM). And second, a Knowledge Graph (KG_RAG) based method that uses semantic tagging, and, retrieves knowledge graph triples from a graph database, as context. KG_RAG uses knowledge graphs constructed using a small model that is fine-tuned using knowledge distillation using a large teacher model. The data consists of 18 10K reports of Apple, Microsoft, Alphabet, NVIDIA, Amazon and Tesla for the years 2021, 2022 and 2023. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07264","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/2411.07264/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":"2411.07264","created_at":"2026-07-05T09:34:00.867080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07264v1","created_at":"2026-07-05T09:34:00.867080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07264","created_at":"2026-07-05T09:34:00.867080+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSLY4BOHURVM","created_at":"2026-07-05T09:34:00.867080+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSLY4BOHURVMPRR6","created_at":"2026-07-05T09:34:00.867080+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSLY4BOH","created_at":"2026-07-05T09:34:00.867080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D","json":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D.json","graph_json":"https://pith.science/api/pith-number/GSLY4BOHURVMPRR6WXATTZYH7D/graph.json","events_json":"https://pith.science/api/pith-number/GSLY4BOHURVMPRR6WXATTZYH7D/events.json","paper":"https://pith.science/paper/GSLY4BOH"},"agent_actions":{"view_html":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D","download_json":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D.json","view_paper":"https://pith.science/paper/GSLY4BOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07264&json=true","fetch_graph":"https://pith.science/api/pith-number/GSLY4BOHURVMPRR6WXATTZYH7D/graph.json","fetch_events":"https://pith.science/api/pith-number/GSLY4BOHURVMPRR6WXATTZYH7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D/action/storage_attestation","attest_author":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D/action/author_attestation","sign_citation":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D/action/citation_signature","submit_replication":"https://pith.science/pith/GSLY4BOHURVMPRR6WXATTZYH7D/action/replication_record"}},"created_at":"2026-07-05T09:34:00.867080+00:00","updated_at":"2026-07-05T09:34:00.867080+00:00"}