{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ARYQAGATGB5PZIEGHZY3REBGST","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":"7dd21ef21d9defef4260312166ef5e25d632b57dfafea1c9f470ba2076ad9be0","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T13:10:51Z","title_canon_sha256":"5d2be998b95f94f4d50dfce008b075889c80977cd5134e929c2b362c2af6dcfb"},"schema_version":"1.0","source":{"id":"2408.04691","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04691","created_at":"2026-07-05T09:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04691v4","created_at":"2026-07-05T09:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04691","created_at":"2026-07-05T09:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"ARYQAGATGB5P","created_at":"2026-07-05T09:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"ARYQAGATGB5PZIEG","created_at":"2026-07-05T09:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"ARYQAGAT","created_at":"2026-07-05T09:31:06Z"}],"graph_snapshots":[{"event_id":"sha256:14395216275020a9466fb58d2a3eb1c63a839796f8c4d65e4c07870acb63230b","target":"graph","created_at":"2026-07-05T09:31:06Z","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/2408.04691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relational databases often suffer from uninformative descriptors of table contents, such as ambiguous columns and hard-to-interpret values, impacting both human users and text-to-SQL models. In this paper, we explore the use of large language models (LLMs) to automatically generate detailed natural language descriptions for SQL database columns, aiming to improve text-to-SQL performance and automate metadata creation. We create a dataset of gold column descriptions based on the BIRD-Bench benchmark, manually refining its column descriptions and creating a taxonomy for categorizing column diffi","authors_text":"Axel Wiks\\\"ater, Erik Larsson, Fredrik Heintz, Hjalmar \\\"Ohman, Martin Forsberg, Martin S\\\"orme, Niklas Wretblad, Oscar S\\\"oderlund, Oskar Holmstr\\\"om, Ture Pont\\'en","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T13:10:51Z","title":"Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04691","kind":"arxiv","version":4},"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":"sha256:2725f4767cc6704f9a4e8fff0bb10a9dded5b8f4ad2fbd35ab82826819af6ef9","target":"record","created_at":"2026-07-05T09:31:06Z","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":"7dd21ef21d9defef4260312166ef5e25d632b57dfafea1c9f470ba2076ad9be0","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T13:10:51Z","title_canon_sha256":"5d2be998b95f94f4d50dfce008b075889c80977cd5134e929c2b362c2af6dcfb"},"schema_version":"1.0","source":{"id":"2408.04691","kind":"arxiv","version":4}},"canonical_sha256":"0471001813307afca0863e71b8902694cf379597876e8ef024bb4c1b30666cdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0471001813307afca0863e71b8902694cf379597876e8ef024bb4c1b30666cdc","first_computed_at":"2026-07-05T09:31:06.638693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:06.638693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LzM2qTePuey1hc1YpswOJAWmEZhM0QQ+JOmyaU9tC4eajKUJb+CEzfFruCEHsrH44memfFnEKEX0MbkY4emuDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:06.639198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04691","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2725f4767cc6704f9a4e8fff0bb10a9dded5b8f4ad2fbd35ab82826819af6ef9","sha256:14395216275020a9466fb58d2a3eb1c63a839796f8c4d65e4c07870acb63230b"],"state_sha256":"76bf67127c60dd0a0cf6d2bb1f4db2998b42244cadba83ca01a17a5650c17482"}