{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LRAN53FVHSXGBAOE32ZYBG6FYH","short_pith_number":"pith:LRAN53FV","schema_version":"1.0","canonical_sha256":"5c40deecb53cae6081c4deb3809bc5c1e4df80fc49fca8171f6aa4a222d58e59","source":{"kind":"arxiv","id":"2607.06482","version":1},"attestation_state":"computed","paper":{"title":"Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Liu, Shailaja Keyur Sampat, So Hasegawa, Wei-Peng Chen","submitted_at":"2026-07-07T16:43:05Z","abstract_excerpt":"Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large multi-tabular datasets, external knowledge integration, and exploratory insight discovery. We introduce DataGovBench, a benchmark derived from governmental open data designed to evaluate LLMs in practical scenarios. The benchmark includes two tasks: Table QA that requires solving complex decomposable questions and producing textual answers or visualizations, and Table Insight that"},"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":"2607.06482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T16:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1dde2335598870e02444d9a76ffc4088a9db920e0294ae7b6dfd3d4a79b3db6b","abstract_canon_sha256":"887982a18c6089cec04bf0fe3a0cd7af42fdf4510cc160bb21dae5b34fce9add"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:27.558614Z","signature_b64":"VroNgm4nxc96epy/qfWl6nRpS582qbt8iSPH5Pn39Az0aV5lJgJxZAT1/NMzf10GcBAPNzMH02JDGTYyJXq+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c40deecb53cae6081c4deb3809bc5c1e4df80fc49fca8171f6aa4a222d58e59","last_reissued_at":"2026-07-08T01:19:27.558169Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:27.558169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Liu, Shailaja Keyur Sampat, So Hasegawa, Wei-Peng Chen","submitted_at":"2026-07-07T16:43:05Z","abstract_excerpt":"Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large multi-tabular datasets, external knowledge integration, and exploratory insight discovery. We introduce DataGovBench, a benchmark derived from governmental open data designed to evaluate LLMs in practical scenarios. The benchmark includes two tasks: Table QA that requires solving complex decomposable questions and producing textual answers or visualizations, and Table Insight that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06482","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/2607.06482/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":"2607.06482","created_at":"2026-07-08T01:19:27.558234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06482v1","created_at":"2026-07-08T01:19:27.558234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06482","created_at":"2026-07-08T01:19:27.558234+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRAN53FVHSXG","created_at":"2026-07-08T01:19:27.558234+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRAN53FVHSXGBAOE","created_at":"2026-07-08T01:19:27.558234+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRAN53FV","created_at":"2026-07-08T01:19:27.558234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH","json":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH.json","graph_json":"https://pith.science/api/pith-number/LRAN53FVHSXGBAOE32ZYBG6FYH/graph.json","events_json":"https://pith.science/api/pith-number/LRAN53FVHSXGBAOE32ZYBG6FYH/events.json","paper":"https://pith.science/paper/LRAN53FV"},"agent_actions":{"view_html":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH","download_json":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH.json","view_paper":"https://pith.science/paper/LRAN53FV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06482&json=true","fetch_graph":"https://pith.science/api/pith-number/LRAN53FVHSXGBAOE32ZYBG6FYH/graph.json","fetch_events":"https://pith.science/api/pith-number/LRAN53FVHSXGBAOE32ZYBG6FYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH/action/storage_attestation","attest_author":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH/action/author_attestation","sign_citation":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH/action/citation_signature","submit_replication":"https://pith.science/pith/LRAN53FVHSXGBAOE32ZYBG6FYH/action/replication_record"}},"created_at":"2026-07-08T01:19:27.558234+00:00","updated_at":"2026-07-08T01:19:27.558234+00:00"}