{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GI4U7WOGCK23BE3Q5YH2UVIBYG","short_pith_number":"pith:GI4U7WOG","schema_version":"1.0","canonical_sha256":"32394fd9c612b5b09370ee0faa5501c1b2fd89282c87140b93a588e54975bc9a","source":{"kind":"arxiv","id":"2311.09721","version":1},"attestation_state":"computed","paper":{"title":"On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Ellen Zhang, Linyong Nan, Weijin Zou, Wenfei Zhou, Yilun Zhao","submitted_at":"2023-11-16T09:55:07Z","abstract_excerpt":"This study introduces a new long-form database question answering dataset designed to evaluate how Large Language Models (LLMs) interact with a SQL interpreter. The task necessitates LLMs to strategically generate multiple SQL queries to retrieve sufficient data from a database, to reason with the acquired context, and to synthesize them into a comprehensive analytical narrative. Our findings highlight that this task poses great challenges even for the state-of-the-art GPT-4 model. We propose and evaluate two interaction strategies, and provide a fine-grained analysis of the individual stages "},"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":"2311.09721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:55:07Z","cross_cats_sorted":[],"title_canon_sha256":"83c025523cc71eb293127526951b21b130dde362ee5432970c1e69c3fbfe0d55","abstract_canon_sha256":"6494842a99bfa04a2d5ad570f3e21c862d76109a0c9ee9f5445884137b30eafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:32.009737Z","signature_b64":"BvzY9stfo2RC68oG9xoF0XpjM/oMJIzbE5it/Vau4G+T198y8vNNg/y77q1sU/ULwSGRr38pitLAs+8V/n5tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32394fd9c612b5b09370ee0faa5501c1b2fd89282c87140b93a588e54975bc9a","last_reissued_at":"2026-07-05T07:13:32.008281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:32.008281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Ellen Zhang, Linyong Nan, Weijin Zou, Wenfei Zhou, Yilun Zhao","submitted_at":"2023-11-16T09:55:07Z","abstract_excerpt":"This study introduces a new long-form database question answering dataset designed to evaluate how Large Language Models (LLMs) interact with a SQL interpreter. The task necessitates LLMs to strategically generate multiple SQL queries to retrieve sufficient data from a database, to reason with the acquired context, and to synthesize them into a comprehensive analytical narrative. Our findings highlight that this task poses great challenges even for the state-of-the-art GPT-4 model. We propose and evaluate two interaction strategies, and provide a fine-grained analysis of the individual stages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09721","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/2311.09721/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":"2311.09721","created_at":"2026-07-05T07:13:32.009241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09721v1","created_at":"2026-07-05T07:13:32.009241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09721","created_at":"2026-07-05T07:13:32.009241+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI4U7WOGCK23","created_at":"2026-07-05T07:13:32.009241+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI4U7WOGCK23BE3Q","created_at":"2026-07-05T07:13:32.009241+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI4U7WOG","created_at":"2026-07-05T07:13:32.009241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG","json":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG.json","graph_json":"https://pith.science/api/pith-number/GI4U7WOGCK23BE3Q5YH2UVIBYG/graph.json","events_json":"https://pith.science/api/pith-number/GI4U7WOGCK23BE3Q5YH2UVIBYG/events.json","paper":"https://pith.science/paper/GI4U7WOG"},"agent_actions":{"view_html":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG","download_json":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG.json","view_paper":"https://pith.science/paper/GI4U7WOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09721&json=true","fetch_graph":"https://pith.science/api/pith-number/GI4U7WOGCK23BE3Q5YH2UVIBYG/graph.json","fetch_events":"https://pith.science/api/pith-number/GI4U7WOGCK23BE3Q5YH2UVIBYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG/action/storage_attestation","attest_author":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG/action/author_attestation","sign_citation":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG/action/citation_signature","submit_replication":"https://pith.science/pith/GI4U7WOGCK23BE3Q5YH2UVIBYG/action/replication_record"}},"created_at":"2026-07-05T07:13:32.009241+00:00","updated_at":"2026-07-05T07:13:32.009241+00:00"}