{"as_of":"2026-08-21T15:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9823f6b330853688402447972c55917245e38c865c3de39fa62677064add67c0","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:30:45.155462Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2509.09234/citation-record","integrity":"/paper/2509.09234/integrity","json":"/paper/2509.09234/citation-record.json","paper":"/paper/2509.09234"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:30:43.512115Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.512115Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:3dfffb75d9b5eddcd02ae29cb8fbfac8afa3ccdbf27e4d3f806ca399573cc53d","observation_id":"80e155f8-004d-43e6-b84d-29e733e7cfbb","resolution":{"observed_at":"2026-08-04T19:30:43.512115Z","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":"2026-08-04T19:30:43.591340Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.591340Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:34d5890a5e29aba3f5958369475aed65fa1a451f791ef443eab28dbfaada4d61","observation_id":"ef5436a3-a9f3-474d-97d9-d8936a45529a","resolution":{"observed_at":"2026-08-04T19:30:43.591340Z","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":"2026-08-04T19:30:43.667270Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.667270Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:1be37d5a8bdcc12047fc6e4c04b2fba3af2657a7ea9b676ad83966c689405f9e","observation_id":"bfcbd212-6fbb-46da-869b-e4c3c33d0245","resolution":{"observed_at":"2026-08-04T19:30:43.667270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04434","last_updated":"2024-06-19T06:04:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-07T15:56:43Z","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04434","snapshot_observed_at":"2026-08-04T19:30:43.775377Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.775377Z"},"links":{"cited_paper":"/paper/2405.04434","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:42781b426a27107df5637e1a1d117c8f20187be521fac3add49bc2f0f888225f","observation_id":"44a43f0d-6c3c-4c6d-b3e8-399113d2b810","resolution":{"observed_at":"2026-08-04T19:30:43.775377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17944","last_updated":"2024-06-21T19:59:54Z","snapshot_observed_at":"2026-08-18T04:13:28.735758Z","submitted_at":"2024-02-27T23:59:01Z","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17944","snapshot_observed_at":"2026-08-04T19:30:43.846224Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.846224Z"},"links":{"cited_paper":"/paper/2402.17944","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:25e6e12d5f7873d2185c1a0385ad56051443c28b72095bbc18a62b968cf158b6","observation_id":"2cec3039-297b-4183-b484-8ea270eb1f59","resolution":{"observed_at":"2026-08-04T19:30:43.846224Z","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":"2026-08-04T19:30:43.928283Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:43.928283Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:3c850adcbb300d82d6404318cff3dad3aabe452e1cb456f4a5c24f8585119031","observation_id":"f19e185a-109f-46a6-8418-e068dfb6f070","resolution":{"observed_at":"2026-08-04T19:30:43.928283Z","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":"2026-08-04T19:30:44.011480Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.011480Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:8d68361c53d53ed25b47486936819fb398eff6c0ce38d424180257b9db034043","observation_id":"6f283a0a-56d6-4970-8bca-cc2af3fc3024","resolution":{"observed_at":"2026-08-04T19:30:44.011480Z","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":"2026-08-04T19:30:44.078940Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.078940Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:d0a73db50a016c4c4180468fbc0bc560d23da589b9cc04961137a1393ebf1b3a","observation_id":"b05058be-e0f4-4bfe-8351-158240ff8b38","resolution":{"observed_at":"2026-08-04T19:30:44.078940Z","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":"2026-08-04T19:30:44.152620Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.152620Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:3a2e7569df726c6b67aff558ebe0d013f1831447405296d95dc2a4cc63113b49","observation_id":"276ef2ab-9c99-465d-bc89-3430bf1af58b","resolution":{"observed_at":"2026-08-04T19:30:44.152620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05270","last_updated":"2022-07-12T02:44:40Z","snapshot_observed_at":"2026-08-19T06:10:38.033668Z","submitted_at":"2022-07-12T02:44:40Z","title":"A Survey on Table Question Answering: Recent Advances","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05270","snapshot_observed_at":"2026-08-04T19:30:44.195580Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.195580Z"},"links":{"cited_paper":"/paper/2207.05270","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:f9d74706bba3814ffc5991b4f019a4c94fb9ee3ceb260abadeca1809107902ca","observation_id":"025680ca-7e43-44b1-8436-cfb9423eb82e","resolution":{"observed_at":"2026-08-04T19:30:44.195580Z","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":"10.1109/dexa.2007.119","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":null,"work_id":"d61cb888-01c9-4365-bc7e-8699ce637b3f","year":2007},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.285862Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:14eab4c96146637c465b7f06541af5d34af632bb231545772e683c3b7dae5749","observation_id":"a7fc884b-5ca6-4565-b8de-ccdfbbb4fa3a","resolution":{"observed_at":"2026-08-04T19:34:25.613802Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11556","last_updated":"2023-04-23T06:52:35Z","snapshot_observed_at":"2026-08-16T15:38:26.775711Z","submitted_at":"2023-04-23T06:52:35Z","title":"Divide and Prompt: Chain of Thought Prompting for Text-to-SQL","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11556","snapshot_observed_at":"2026-08-04T19:30:44.371146Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.371146Z"},"links":{"cited_paper":"/paper/2304.11556","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:fd26158aca88ed11c7a473014c40e0562a2aff98de3110d6a97b2aa71801bc8f","observation_id":"9b69591d-a13d-419e-a95e-2655ca4e2cc6","resolution":{"observed_at":"2026-08-04T19:30:44.371146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01066","last_updated":"2025-02-04T03:46:27Z","snapshot_observed_at":"2026-08-16T13:13:35.275727Z","submitted_at":"2024-10-01T20:46:25Z","title":"From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01066","snapshot_observed_at":"2026-08-04T19:30:44.445676Z","title":"Maida, and Raju Gottumukkala","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.445676Z"},"links":{"cited_paper":"/paper/2410.01066","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:97a9ee272fc875cef1008243af5182f8488272d344db4a6a80100ec641478eb9","observation_id":"00594952-079c-47b1-8d98-afdffa7dad5a","resolution":{"observed_at":"2026-08-04T19:30:44.445676Z","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":"2026-08-04T19:30:44.520851Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.520851Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:610e8d4ec91d8a57c90ba2de8d89bef8c22a50e036a3ba6808adbd5e8a3ef8e9","observation_id":"27618cd8-1a25-4d2d-9c2e-6da9bc1e99bc","resolution":{"observed_at":"2026-08-04T19:30:44.520851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.16714","last_updated":"2022-03-30T23:30:16Z","snapshot_observed_at":"2026-08-17T16:01:59.751676Z","submitted_at":"2022-03-30T23:30:16Z","title":"End-to-End Table Question Answering via Retrieval-Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.16714","snapshot_observed_at":"2026-08-04T19:30:44.623315Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.623315Z"},"links":{"cited_paper":"/paper/2203.16714","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:25391fac27b0235ba9a87c0374b2e7ff13281c3f07ba650191305438647300d3","observation_id":"052fb10a-494a-4b87-9af6-9642a5d32b44","resolution":{"observed_at":"2026-08-04T19:30:44.623315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1508.00305","last_updated":"2015-08-03T02:53:01Z","snapshot_observed_at":"2026-08-19T03:11:23.683294Z","submitted_at":"2015-08-03T02:53:01Z","title":"Compositional Semantic Parsing on Semi-Structured Tables","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.00305","snapshot_observed_at":"2026-08-04T19:30:44.700779Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.700779Z"},"links":{"cited_paper":"/paper/1508.00305","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:af255e628bbd8d76576a677d8d2661adbb3c7385c7dea073fb8908ce62d01778","observation_id":"631450c5-5596-453d-9e96-7e760be26e87","resolution":{"observed_at":"2026-08-04T19:30:44.700779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11402","last_updated":"2025-03-12T04:37:42Z","snapshot_observed_at":"2026-08-16T13:42:19.779407Z","submitted_at":"2024-06-17T10:45:36Z","title":"Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11402","snapshot_observed_at":"2026-08-04T19:30:44.786694Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.786694Z"},"links":{"cited_paper":"/paper/2406.11402","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:443c2e15204235af769a81e60859a459920e54b9774c9acb089a4688ad07bf9d","observation_id":"e7ba0a9e-6f2d-4c4d-8f37-5f258d600510","resolution":{"observed_at":"2026-08-04T19:30:44.786694Z","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":"2026-08-04T19:30:44.907599Z","title":"A survey on advances in retrieval-augmented generation over tabular data and table qa","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:44.907599Z"},"links":{"citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:350dc56ee1a358397bacbbc48088c358cdde9386916aa6c843924da2de754d8b","observation_id":"55cea9d2-afca-4d8b-b977-4526f2bf46e7","resolution":{"observed_at":"2026-08-04T19:30:44.907599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.16991","last_updated":"2024-08-30T03:38:37Z","snapshot_observed_at":"2026-08-18T04:44:46.033446Z","submitted_at":"2024-08-30T03:38:37Z","title":"Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.16991","snapshot_observed_at":"2026-08-04T19:30:45.015054Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:45.015054Z"},"links":{"cited_paper":"/paper/2408.16991","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:ddb0461e6f3c7325ed64ab62e357223c9f2a377f809d11b9b646b47105dee6d4","observation_id":"db89f05e-f524-4ca2-a97a-a9c480e5382d","resolution":{"observed_at":"2026-08-04T19:30:45.015054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05850","last_updated":"2024-12-08T08:16:19Z","snapshot_observed_at":"2026-08-14T23:59:17.700802Z","submitted_at":"2024-12-08T08:16:19Z","title":"Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.05850","snapshot_observed_at":"2026-08-04T19:30:45.111981Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:45.111981Z"},"links":{"cited_paper":"/paper/2412.05850","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:f90e2a0e8bee5460a2b800db0c119a46eed286a958b9f440f84eb4e30221cebc","observation_id":"4d512271-410a-469b-8ff1-72c469334c9c","resolution":{"observed_at":"2026-08-04T19:30:45.111981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08887","last_updated":"2019-02-02T23:53:18Z","snapshot_observed_at":"2026-08-18T17:54:32.989741Z","submitted_at":"2018-09-24T13:03:13Z","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.08887","snapshot_observed_at":"2026-08-04T19:30:45.155462Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T19:30:45.155462Z"},"links":{"cited_paper":"/paper/1809.08887","citing_paper":"/paper/2509.09234"},"observation_digest":"sha256:7d447e9f15472e555a9387ff51cdb4dda02a8693daf77612cfc8d9af3f0f5d6a","observation_id":"11b89ed0-da4f-4c60-a7bf-07483a4e609f","resolution":{"observed_at":"2026-08-04T19:30:45.155462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09234","last_updated":"2025-09-11T08:12:38Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T06:34:31.935562Z","submitted_at":"2025-09-11T08:12:38Z","title":"Agentic LLMs for Question Answering over Tabular Data"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":21},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2509.09234."}