{"as_of":"2026-08-10T09:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc315e804b122362685b85f719981c818818b49b31aee2cc7a3462d35a6fb251","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:38:16.438426Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.07423/citation-record","integrity":"/paper/2506.07423/integrity","json":"/paper/2506.07423/citation-record.json","paper":"/paper/2506.07423"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.13629","last_updated":"2022-08-29T14:24:13Z","snapshot_observed_at":"2026-08-06T16:43:08.520905Z","submitted_at":"2022-08-29T14:24:13Z","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.13629","snapshot_observed_at":"2026-08-07T05:38:16.274292Z","title":"A survey on text-to-sql parsing: Concepts, methods, and future directions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.274292Z"},"links":{"cited_paper":"/paper/2208.13629","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:869db235b7684f33ac8aeb92b1d8ce0b87449cd90dd83f6a56abb38fb6385ba3","observation_id":"9a15fa4b-a223-44c1-a142-83cdbb1ab41d","resolution":{"observed_at":"2026-08-07T05:38:16.274292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15186","last_updated":"2025-06-03T14:40:01Z","snapshot_observed_at":"2026-08-08T00:42:14.053796Z","submitted_at":"2024-07-21T14:48:23Z","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.15186","snapshot_observed_at":"2026-08-07T05:38:16.278842Z","title":"A survey on employing large language models for text-to-sql tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.278842Z"},"links":{"cited_paper":"/paper/2407.15186","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:2012aa393d6e0ba81c13ceadad6ef9d0ca3145bf5b5498cf8e227d09a614ba96","observation_id":"5fd2ee94-8e8d-40df-ae95-99809a23204d","resolution":{"observed_at":"2026-08-07T05:38:16.278842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.282748Z","title":"Next-generation database interfaces: A survey of llm-based text-to-sql,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.282748Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:fa356f68828b44c75725619be829e89fc368f7c650fe7a5394e495f004755d53","observation_id":"1df1ebd8-571c-498e-bbff-1ef986f682e8","resolution":{"observed_at":"2026-08-07T05:38:16.282748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.00103","last_updated":"2017-11-09T23:06:14Z","snapshot_observed_at":"2026-08-03T05:45:09.122112Z","submitted_at":"2017-08-31T23:12:15Z","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.00103","snapshot_observed_at":"2026-08-07T05:38:16.286614Z","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.286614Z"},"links":{"cited_paper":"/paper/1709.00103","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:cb32fdc270c68d9c6dfa28d6240664cd24d5dc6d955e548adebd4e922bf9ec11","observation_id":"7711d878-ff5b-4f4c-955f-8dcccb80674d","resolution":{"observed_at":"2026-08-07T05:38:16.286614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:19.425157Z","title":"Spider: A large- scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task,","venue":null,"work_id":"dd807861-c048-4a53-b551-d7eed4a200cb","year":2018},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.290777Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:743e3d5901f7de8a08c81b587a94da6bb59c9036c6ffd51d012c8b7fdc2e7109","observation_id":"db8a74eb-3fd3-4d74-8ce4-afa39e2f8364","resolution":{"observed_at":"2026-08-07T05:38:19.536547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:19.240921Z","title":"Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls,","venue":null,"work_id":"6592748c-8488-43b4-b5b0-9621468fdaf5","year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.294750Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:751110384b708c0c34d2cb05403c4bb59e736cfd64298cd6a913e95e952297e1","observation_id":"8362539b-63ed-467f-9e2f-229af9511526","resolution":{"observed_at":"2026-08-07T05:38:19.346249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:18.973744Z","title":"Chase-sql: Multi-path reasoning and preference optimized candidate selection in text-to-sql,","venue":null,"work_id":"47afae47-a87b-4ab1-bef7-9c2a2bf41d55","year":null},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.298649Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:ed588101472e9f5c7d6cf434e708c9c53d770c6d51b8467d91c97cb99e2d632c","observation_id":"6d120e40-7221-4f1e-8716-ae7e6a1cd939","resolution":{"observed_at":"2026-08-07T05:38:19.129283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16755","last_updated":"2024-11-25T19:43:07Z","snapshot_observed_at":"2026-08-10T00:32:43.432521Z","submitted_at":"2024-05-27T01:54:16Z","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16755","snapshot_observed_at":"2026-08-07T05:38:16.306896Z","title":"Chess: Contextual harnessing for efficient sql synthesis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.306896Z"},"links":{"cited_paper":"/paper/2405.16755","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:7f93dbdac8ce2b29e022b69fd66923c9cf1aecd8deafcdaba0fa36eb5df41e95","observation_id":"6d631799-fb45-4ee7-ac29-06a54dee4cd3","resolution":{"observed_at":"2026-08-07T05:38:16.306896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00073","last_updated":"2024-11-26T13:55:29Z","snapshot_observed_at":"2026-07-06T19:43:09.889618Z","submitted_at":"2024-10-31T16:22:26Z","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00073","snapshot_observed_at":"2026-08-07T05:38:16.311735Z","title":"Rsl-sql: Robust schema linking in text-to-sql generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.311735Z"},"links":{"cited_paper":"/paper/2411.00073","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:a0ad54ba95d80029d0e126f22d29563901bb71502633788521a21de8c7a7aec4","observation_id":"ff16517a-c1e9-4be8-a749-f83a9b4d7cd1","resolution":{"observed_at":"2026-08-07T05:38:16.311735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.08599","last_updated":"2025-02-10T10:28:55Z","snapshot_observed_at":"2026-07-06T19:49:44.167865Z","submitted_at":"2024-11-13T13:30:21Z","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.08599","snapshot_observed_at":"2026-08-07T05:38:16.316282Z","title":"Xiyan-sql: A multi-generator ensemble framework for text-to-sql,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.316282Z"},"links":{"cited_paper":"/paper/2411.08599","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:7551c78dd02e920742fd6ebc7353b75db5bbeceb9d34bdbd40ef824092209e75","observation_id":"5c053738-9916-4c99-92b9-a2763ec99a41","resolution":{"observed_at":"2026-08-07T05:38:16.316282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07702","last_updated":"2024-08-18T19:06:04Z","snapshot_observed_at":"2026-08-09T10:22:26.321343Z","submitted_at":"2024-08-14T17:59:04Z","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.07702","snapshot_observed_at":"2026-08-07T05:38:16.320221Z","title":"The death of schema linking? text-to-sql in the age of well-reasoned language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.320221Z"},"links":{"cited_paper":"/paper/2408.07702","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:058e2f3fdae3a9db048c059d7ce10231e8c0fcd028bc781940715a7afeb026e5","observation_id":"593acb4f-a354-40b7-a483-e22e4cc24245","resolution":{"observed_at":"2026-08-07T05:38:16.320221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:18.754670Z","title":"Purple: Making a large language model a better sql writer,","venue":null,"work_id":"5b6cf0e7-2ad3-4ece-9dad-c3c6fd282c9e","year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.324435Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:6e13eb612820dcc4a2da2e3a227a2e535b44fcdf2abef391f4c26ad8a6623e43","observation_id":"d6e42dbb-61f6-427d-b940-c0a6e9b6a3ef","resolution":{"observed_at":"2026-08-07T05:38:18.851801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16751","last_updated":"2025-01-28T09:45:41Z","snapshot_observed_at":"2026-08-09T02:38:25.251241Z","submitted_at":"2024-09-25T09:02:48Z","title":"E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16751","snapshot_observed_at":"2026-08-07T05:38:16.328132Z","title":"E-sql: Direct schema linking via question enrichment in text-to-sql,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.328132Z"},"links":{"cited_paper":"/paper/2409.16751","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:6f7eded3d2c4eaa91fce434d9fbfcf3f7fdf73892e9424cf668051f1eeeb0db3","observation_id":"cbe6b730-d104-4e50-9119-69d8b48fca89","resolution":{"observed_at":"2026-08-07T05:38:16.328132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07467","last_updated":"2024-05-13T04:59:32Z","snapshot_observed_at":"2026-07-06T18:13:20.536375Z","submitted_at":"2024-05-13T04:59:32Z","title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07467","snapshot_observed_at":"2026-08-07T05:38:16.331686Z","title":"Mcs-sql: Leveraging multiple prompts and multiple-choice selection for text-to-sql generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.331686Z"},"links":{"cited_paper":"/paper/2405.07467","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:0fe79a8425ff0be749525c8ade3d8ffb51bc134d5fbf0a9f72e33f9e4762262b","observation_id":"a35100ae-d37d-48e9-866d-c6bbae8882fc","resolution":{"observed_at":"2026-08-07T05:38:16.331686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.335952Z","title":"Codes: Towards building open-source language models for text-to-sql,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.335952Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:c6ef8441a2b1000a2768ab54ad3af5cc27d541859d91055d5fe35737b6b4d675","observation_id":"bc7c537a-7807-4a49-9eab-677d07830af3","resolution":{"observed_at":"2026-08-07T05:38:16.335952Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:18.534236Z","title":"Synthesizing text-to-SQL data from weak and strong LLMs,","venue":null,"work_id":"42d4cd02-37ea-40ed-858a-998555bfff23","year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.342767Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:29ddedad346f660ce49cd2475ccd2f9195c64b8e8e45174aea126e464e701e15","observation_id":"09d05fd5-590d-46de-9c45-e29e90e1f59f","resolution":{"observed_at":"2026-08-07T05:38:18.633567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.339448Z","title":"Available: https://doi.org/10.1145/3654930","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.339448Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:f51afb124b2244c0097bd017711e9913ff443c0731b30d06d712ae547a9a4dd3","observation_id":"cbfd1ac9-f21d-4264-81d7-943d24345190","resolution":{"observed_at":"2026-08-07T05:38:16.339448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"8555.25945","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.714341Z","title":"Nalir: an interactive natural language interface for querying relational databases,","venue":null,"work_id":"d5a8886f-ad98-47a3-a046-d07c4f6f0ab1","year":2014},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.349731Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:ad7ed33e4fe90d8eec73aec4daacac3554592abbfd0f200283ccecb22c6f8f2b","observation_id":"13a84b38-18b6-4274-92d5-e19cd47ec97c","resolution":{"observed_at":"2026-08-07T05:38:16.814638Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.346179Z","title":"The dawn of natural language to sql: Are we fully ready?","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.346179Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:17ff9bc54201414413fc51a2ffb6d94eecd8632ae1ada13bdcc7dd94c3a5b184","observation_id":"64c49a07-1de3-423a-b55e-7cd6095fb74f","resolution":{"observed_at":"2026-08-07T05:38:16.346179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.357212Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.357212Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:ef61b31883a525259387010021ae3707e821f90814363fa6bc89ff95ce5609d0","observation_id":"9def7839-aae2-4640-9b7e-92f3b0a9d8d8","resolution":{"observed_at":"2026-08-07T05:38:16.357212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.3215","last_updated":"2014-12-14T20:59:51Z","snapshot_observed_at":"2026-08-02T03:58:50.109606Z","submitted_at":"2014-09-10T19:55:35Z","title":"Sequence to Sequence Learning with Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.3215","snapshot_observed_at":"2026-08-07T05:38:16.353724Z","title":"Sequence to sequence learning with neural networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.353724Z"},"links":{"cited_paper":"/paper/1409.3215","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:dcc82edf635fb212ffcfb3121238bc19d4035771ad2d914c839dc241925eb21b","observation_id":"6a1a96a0-89b4-487b-8582-89f01d9fe848","resolution":{"observed_at":"2026-08-07T05:38:16.353724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:18.044558Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer,","venue":null,"work_id":"9845829f-33a6-41f0-9ebe-f67fce87ba9e","year":2020},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.364280Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:72fc2e49d37db4b03508b7681168fa2c5a1d9d2b704bd04a89cb692f9885e26c","observation_id":"8860740f-9af9-4dfc-8792-6e01ccb45787","resolution":{"observed_at":"2026-08-07T05:38:18.140657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:18.292155Z","title":"Bert: Pre- training of deep bidirectional transformers for language understanding,","venue":null,"work_id":"96b6a195-15e7-40d5-a524-d03fdaee147e","year":2019},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.360759Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:b1e66741408b76979fd9b00df79680cd5076378a0250e956f9312792c23a927b","observation_id":"51ab76d5-da45-4edf-a0e2-ce8f1610fc22","resolution":{"observed_at":"2026-08-07T05:38:18.405116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.371060Z","title":"Get to the point: Summarization with pointer-generator networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.371060Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:7e7ada65c888619ecb0475a5ec0e52f1689f85c7ea02e671c00ab3c4a29fe39e","observation_id":"42fb86a9-18c2-4e98-a789-7261603716ca","resolution":{"observed_at":"2026-08-07T05:38:16.371060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:17.801204Z","title":"Bridging textual and tabular data for cross-domain text-to-SQL semantic parsing,","venue":null,"work_id":"76e68c05-77df-429c-a3a0-fa4d51a98533","year":2020},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.367546Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:da280e6cb5deb7313fb540eefd236402333d2a2313564030fccbaf183c0697af","observation_id":"5e8fdd62-6779-482c-8280-11b63537667b","resolution":{"observed_at":"2026-08-07T05:38:17.924960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-07T05:38:16.378630Z","title":"Gemini: A family of highly capable multimodal models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.378630Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:8b56a8c4c3984af9492e78eb4b9ae04956679ce6fbc87e7676a28e121f46e223","observation_id":"38803d7f-081d-42f4-a233-23662f3b0462","resolution":{"observed_at":"2026-08-07T05:38:16.378630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T05:38:16.375170Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.375170Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:a9b5cdd2404dacd41588af83090fc22b7b5d513142aa9021ba16f49ba80b4df8","observation_id":"c7030597-3a6b-4ee2-8441-ddf457f0de20","resolution":{"observed_at":"2026-08-07T05:38:16.375170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06161","last_updated":"2023-12-13T14:44:10Z","snapshot_observed_at":"2026-07-06T15:25:35.930688Z","submitted_at":"2023-05-09T08:16:42Z","title":"StarCoder: may the source be with you!","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06161","snapshot_observed_at":"2026-08-07T05:38:16.385819Z","title":"Starcoder: may the source be with you!","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.385819Z"},"links":{"cited_paper":"/paper/2305.06161","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:87649027e7d524f705c33262ae9336a86da237f93bd0d4ece5ed395f7e5691ed","observation_id":"07eca7a3-3e5f-4520-bcb6-77c94f8b1025","resolution":{"observed_at":"2026-08-07T05:38:16.385819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T05:38:16.382341Z","title":"Llama 2: Open foundation and fine-tuned chat models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.382341Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:8b1f075d15298ad9c1cd05a2af0cc6f5b2012a8c341843491109cecb84e381b2","observation_id":"bab37083-509a-46c4-beda-83b3bfe0c2ea","resolution":{"observed_at":"2026-08-07T05:38:16.382341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:17.618854Z","title":"Din-sql: Decomposed in-context learning of text-to-sql with self-correction,","venue":null,"work_id":"eb140b5f-ca18-4808-88db-254b976087d5","year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.395829Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:5485df29cdbfaaa3db3aaea4b545167238171901ff06c654437807ded408237e","observation_id":"04b62657-2fee-4135-ab7b-463399279ce3","resolution":{"observed_at":"2026-08-07T05:38:17.724623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07306","last_updated":"2023-07-14T12:30:41Z","snapshot_observed_at":"2026-07-06T15:54:01.430352Z","submitted_at":"2023-07-14T12:30:41Z","title":"C3: Zero-shot Text-to-SQL with ChatGPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07306","snapshot_observed_at":"2026-08-07T05:38:16.391072Z","title":"C3: Zero-shot text-to-sql with chatgpt,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.391072Z"},"links":{"cited_paper":"/paper/2307.07306","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:ae3597fbd1f4195342b73495ed8b563141efa03274d8440f78bd95515bf7c7c4","observation_id":"66a578c5-bc6c-4531-bc5f-7bd230b84fad","resolution":{"observed_at":"2026-08-07T05:38:16.391072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-07T05:38:16.405275Z","title":"Self-consistency improves chain of thought reasoning in language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.405275Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:443cca200505adb4e4274f7d544cedd7c61cba21fedc592edde69d92b4937de0","observation_id":"41deecea-15a6-44f8-a299-b6b475bb3fbe","resolution":{"observed_at":"2026-08-07T05:38:16.405275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:17.410007Z","title":"Text- to-sql empowered by large language models: A benchmark evaluation,","venue":null,"work_id":"d0e071c1-3961-402f-be3c-5c1012b00235","year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.400848Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:af2ce5204c7b204e0b83f69493115304c60f7ab36b4a7dcdf3d13f914f0e9463","observation_id":"851bbb25-657b-4ca5-b2d7-5391539de85f","resolution":{"observed_at":"2026-08-07T05:38:17.506198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:17.214732Z","title":"Self-Polish: Enhance reasoning in large language models via problem refinement,","venue":null,"work_id":"b78ad34c-1055-4613-a206-9e9aac43bb5d","year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.415076Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:7a6c05be98ccfcea1a5410ca1bafca8890103e1fc58ebf166230bcbfd1db79ac","observation_id":"49dfb382-4cfd-4f29-9072-ca9d5cfbf21a","resolution":{"observed_at":"2026-08-07T05:38:17.295601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12916","last_updated":"2025-02-16T17:37:28Z","snapshot_observed_at":"2026-07-06T19:34:51.296918Z","submitted_at":"2024-10-16T18:03:24Z","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12916","snapshot_observed_at":"2026-08-07T05:38:16.409851Z","title":"Msc-sql: Multi-sample critiquing small language models for text-to-sql translation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.409851Z"},"links":{"cited_paper":"/paper/2410.12916","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:3e396f6cae9645915a5f0c3e0faf503a72c342d11aff54f42394d97b438a6e17","observation_id":"dc6c4376-71d4-4bae-8f5d-7b83d069dbd6","resolution":{"observed_at":"2026-08-07T05:38:16.409851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.427700Z","title":"Mpnet: Masked and permuted pre-training for language understanding,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.427700Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:58920a1737221ed9e135cefd6eb5c5812b504ce2b914a2d0fd63b59a80fc7171","observation_id":"caa024c6-2715-4db4-8d32-0e71b55a6f50","resolution":{"observed_at":"2026-08-07T05:38:16.427700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T05:38:16.422463Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.422463Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:db55be5a4375aa726b7f43d16331617c11f7aa4f51993f931387df0ae9aee7b9","observation_id":"be8a2323-05e6-4328-bd2c-b73ce849ac6a","resolution":{"observed_at":"2026-08-07T05:38:16.422463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-07T05:38:16.438426Z","title":"Deepseek-v3 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.438426Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:e10568df77d182323df208785629922787e7622c30cd77cc1a8f5e002a028fed","observation_id":"1141bbed-6572-4c8b-b0d9-38afe4c01426","resolution":{"observed_at":"2026-08-07T05:38:16.438426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:38:16.433061Z","title":"Resdsql: decoupling schema linking and skeleton parsing for text-to-sql,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.433061Z"},"links":{"citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:c3570a7f06670f1fac5bb160483206093c797a93c33d1477ab0fb826196acce1","observation_id":"652f7266-0240-4d06-9dd5-85bb2dd06869","resolution":{"observed_at":"2026-08-07T05:38:16.433061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01943","last_updated":"2024-10-02T18:41:35Z","snapshot_observed_at":"2026-07-06T19:26:33.330434Z","submitted_at":"2024-10-02T18:41:35Z","title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01943","snapshot_observed_at":"2026-08-07T05:38:16.302160Z","title":"Available: https://arxiv.org/abs/2410.01943","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:16.302160Z"},"links":{"cited_paper":"/paper/2410.01943","citing_paper":"/paper/2506.07423"},"observation_digest":"sha256:0e897153e398825d14a972a334731e95a4005c17d47f734f82b7b719012cd8ee","observation_id":"5b9e1aaf-b702-4f55-815b-6713b985dc00","resolution":{"observed_at":"2026-08-07T05:38:16.302160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.07423","last_updated":"2025-06-09T04:44:31Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T10:23:03.965397Z","submitted_at":"2025-06-09T04:44:31Z","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2506.07423."}