{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRAN53FVHSXGBAOE32ZYBG6FYH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"887982a18c6089cec04bf0fe3a0cd7af42fdf4510cc160bb21dae5b34fce9add","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T16:43:05Z","title_canon_sha256":"1dde2335598870e02444d9a76ffc4088a9db920e0294ae7b6dfd3d4a79b3db6b"},"schema_version":"1.0","source":{"id":"2607.06482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06482","created_at":"2026-07-08T01:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06482v1","created_at":"2026-07-08T01:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06482","created_at":"2026-07-08T01:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"LRAN53FVHSXG","created_at":"2026-07-08T01:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"LRAN53FVHSXGBAOE","created_at":"2026-07-08T01:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"LRAN53FV","created_at":"2026-07-08T01:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:8c4230d9c55ed60e79b998014e93d8ea512eb1e3612901de93fe8077138380d7","target":"graph","created_at":"2026-07-08T01:19:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.06482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lei Liu, Shailaja Keyur Sampat, So Hasegawa, Wei-Peng Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T16:43:05Z","title":"Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06482","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab4db65bc3fb06da87897be61af4e77df9dbf961edab8774a66745b636892045","target":"record","created_at":"2026-07-08T01:19:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"887982a18c6089cec04bf0fe3a0cd7af42fdf4510cc160bb21dae5b34fce9add","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T16:43:05Z","title_canon_sha256":"1dde2335598870e02444d9a76ffc4088a9db920e0294ae7b6dfd3d4a79b3db6b"},"schema_version":"1.0","source":{"id":"2607.06482","kind":"arxiv","version":1}},"canonical_sha256":"5c40deecb53cae6081c4deb3809bc5c1e4df80fc49fca8171f6aa4a222d58e59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c40deecb53cae6081c4deb3809bc5c1e4df80fc49fca8171f6aa4a222d58e59","first_computed_at":"2026-07-08T01:19:27.558169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:27.558169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VroNgm4nxc96epy/qfWl6nRpS582qbt8iSPH5Pn39Az0aV5lJgJxZAT1/NMzf10GcBAPNzMH02JDGTYyJXq+AQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:27.558614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab4db65bc3fb06da87897be61af4e77df9dbf961edab8774a66745b636892045","sha256:8c4230d9c55ed60e79b998014e93d8ea512eb1e3612901de93fe8077138380d7"],"state_sha256":"bd1aba254e40b590c1e1c6f9e541a0a13276cccd51c6d44585bd4c60e76d0f3a"}