{"as_of":"2026-08-13T10:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2487ac5f5a8c2f9feca4c34767a35901a8ad29a1bb4a2be37cc927e12e6c08f5","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:59:58.466519Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2412.19718/citation-record","integrity":"/paper/2412.19718/integrity","json":"/paper/2412.19718/citation-record.json","paper":"/paper/2412.19718"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1505.00468","last_updated":"2016-10-27T03:50:19Z","snapshot_observed_at":"2026-08-06T13:04:32.551262Z","submitted_at":"2015-05-03T20:07:39Z","title":"VQA: Visual Question Answering","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00468","snapshot_observed_at":"2026-08-10T23:59:58.296814Z","title":"and Parikh, D., (2015) VQA: Visual Question Answering","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.296814Z"},"links":{"cited_paper":"/paper/1505.00468","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:bcb33cda9041b089a117793c10179494e0a9e506832074d1f98f179194ab3336","observation_id":"c220bc16-53cc-4671-ac52-dbf989096cde","resolution":{"observed_at":"2026-08-10T23:59:58.296814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.18376","last_updated":"2024-05-27T17:55:18Z","snapshot_observed_at":"2026-08-13T05:39:26.541547Z","submitted_at":"2023-10-27T00:13:59Z","title":"SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation","version":4},"cited_work":{"arxiv_id":"2310.18376","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.18376","snapshot_observed_at":"2026-08-10T23:59:58.970749Z","title":"SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation","venue":"cs.CL","work_id":"b5895da1-360d-4443-930e-5a30ea21c1ea","year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.303268Z"},"links":{"cited_paper":"/paper/2310.18376","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:2443f373fe016194c278410d092ab6a869d6749a9074fdfa9ffb830a588e11e6","observation_id":"448a6cf0-a717-4726-9729-e6d96585ae3f","resolution":{"observed_at":"2026-08-10T23:59:58.976220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15363","last_updated":"2023-11-20T13:59:16Z","snapshot_observed_at":"2026-08-12T17:57:54.447850Z","submitted_at":"2023-08-29T14:59:54Z","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15363","snapshot_observed_at":"2026-08-10T23:59:58.309054Z","title":"and Zhou, J., (2023) Text -to-SQL Empowered by Large Language Models: A Benchmark Evaluation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.309054Z"},"links":{"cited_paper":"/paper/2308.15363","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:95caf6efeb8444c9478554074ed47f4ca33947bbed1e418b18baffdd548d71eb","observation_id":"4d39e6fe-e205-4536-9442-00bfd920e2f7","resolution":{"observed_at":"2026-08-10T23:59:58.309054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04702","last_updated":"2020-12-09T19:29:27Z","snapshot_observed_at":"2026-08-11T21:36:59.959178Z","submitted_at":"2020-06-08T15:59:00Z","title":"CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training","version":3},"cited_work":{"arxiv_id":"2006.04702","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.04702","snapshot_observed_at":"2026-08-10T23:59:58.928130Z","title":"CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training","venue":"cs.CL","work_id":"5f7f396f-64b7-4c50-a0b5-5400b086de51","year":2020},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.315388Z"},"links":{"cited_paper":"/paper/2006.04702","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:8d15d425b0e6aba986253fb63032a82ca8b9e2e55b6e41d2a63a23bf65a7f818","observation_id":"d93eae8d-0d5e-456a-a274-552016faf0f2","resolution":{"observed_at":"2026-08-10T23:59:58.933750Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.13729","last_updated":"2025-07-25T09:37:28Z","snapshot_observed_at":"2026-08-13T05:19:20.184754Z","submitted_at":"2023-11-22T22:52:00Z","title":"Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.13729","snapshot_observed_at":"2026-08-10T23:59:58.320915Z","title":"and Kavuluru, R., (2023) Comparison of pipeline, sequence-to-sequence, and GPT models for end -to-end relation extraction: experiments with the rare disease use -case","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.320915Z"},"links":{"cited_paper":"/paper/2311.13729","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:75c3ce31d7e6dc30266fe92d8b9dd4590b0a788d4b102342cf670a4b11f1f2fe","observation_id":"0921e10a-74d9-4cad-98fa-ede24d9b55ed","resolution":{"observed_at":"2026-08-10T23:59:58.320915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16483","last_updated":"2023-11-27T15:20:23Z","snapshot_observed_at":"2026-08-13T05:16:57.408767Z","submitted_at":"2023-11-27T15:20:23Z","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16483","snapshot_observed_at":"2026-08-10T23:59:58.326823Z","title":"and Zhang, H., (2023) ChartLlama: A Multimodal LLM for Chart Understanding and Generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.326823Z"},"links":{"cited_paper":"/paper/2311.16483","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:cac60f67806435f69440657fda02fee25a873faa8a2f53fccc9a1c463ba8fda5","observation_id":"8f0d4b1b-7ba6-47aa-b772-93335f381b44","resolution":{"observed_at":"2026-08-10T23:59:58.326823Z","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":"2026-08-10T23:59:59.104259Z","title":"and McMillan, C., (2022) Semantic Similarity Metrics for Evaluating Source Code Summarization","venue":null,"work_id":"ece0fc3e-9c9f-48c7-9028-f456874304e6","year":2022},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.334407Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:6f34d861cc1f4da77c4ec6f96b41affa6e770b2862e961f788513b0801837811","observation_id":"56776824-19e7-49c1-bd0f-63a644040e14","resolution":{"observed_at":"2026-08-10T23:59:59.110878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07855","last_updated":"2019-08-20T15:11:06Z","snapshot_observed_at":"2026-08-13T06:43:41.089525Z","submitted_at":"2019-08-20T15:11:06Z","title":"GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level","version":1},"cited_work":{"arxiv_id":"1908.07855","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.07855","snapshot_observed_at":"2026-08-10T23:59:58.867081Z","title":"GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level","venue":"cs.CL","work_id":"3f409f26-a99f-4aa8-8c66-f49a243fb043","year":2019},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.339736Z"},"links":{"cited_paper":"/paper/1908.07855","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:e3c1f72d2fc199a05ab571d5471c58eb02a3d2f465bfd3aa535629f82516c696","observation_id":"1e08c659-d70d-425f-983d-d391efcd37c9","resolution":{"observed_at":"2026-08-10T23:59:58.873303Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T23:59:59.084337Z","title":"and De Rijke, M., (2007) Machine learning for question answering from tabular data","venue":null,"work_id":"e8b2d77e-637a-4b32-bd11-ef338fe215a2","year":2007},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.345535Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:9433205a536b3a32d582dded62ef0035ea77f6ff6ccba2f787d9822a091fe1da","observation_id":"ede94a6a-4256-47cb-ba7d-c751693dfcb8","resolution":{"observed_at":"2026-08-10T23:59:59.089838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.01173","last_updated":"2023-11-02T12:13:52Z","snapshot_observed_at":"2026-08-13T05:34:16.777504Z","submitted_at":"2023-11-02T12:13:52Z","title":"CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.01173","snapshot_observed_at":"2026-08-10T23:59:58.351076Z","title":"and Chakrabarti, S., (2023) CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.351076Z"},"links":{"cited_paper":"/paper/2311.01173","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:ffe7a325344d88609c6e3b64c4566eae8e855efd1abdf105459f647bc678c1e9","observation_id":"185fafd5-6133-427e-a1d6-e4f4d54c8679","resolution":{"observed_at":"2026-08-10T23:59:58.351076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11429","last_updated":"2021-01-14T02:00:33Z","snapshot_observed_at":"2026-08-04T05:32:30.205166Z","submitted_at":"2021-01-14T02:00:33Z","title":"TSQA: Tabular Scenario Based Question Answering","version":1},"cited_work":{"arxiv_id":"2101.11429","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.11429","snapshot_observed_at":"2026-08-10T23:59:58.823472Z","title":"TSQA: Tabular Scenario Based Question Answering","venue":"cs.CL","work_id":"f89c5412-5c46-4e7b-a803-600d0ab74d52","year":2021},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.356615Z"},"links":{"cited_paper":"/paper/2101.11429","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:d8906f9dd6c6c67c0d468205b73a7abfa25073123b69bd3cabc79c7b64eb294c","observation_id":"3e814c0b-61a9-49b5-8493-6f4e2a97a168","resolution":{"observed_at":"2026-08-10T23:59:58.829807Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.12926","last_updated":"2021-12-24T03:33:20Z","snapshot_observed_at":"2026-08-10T13:38:48.377322Z","submitted_at":"2021-12-24T03:33:20Z","title":"nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.12926","snapshot_observed_at":"2026-08-10T23:59:58.362951Z","title":"and Li, G., (2021) nvBench: A Large -Scale Synthesized Dataset for Cross - Domain Natural Language to Visualization Task","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.362951Z"},"links":{"cited_paper":"/paper/2112.12926","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:32d079e9db8f035ccc23aa7b27e982793bd33a0484928258dde8d84903b782e2","observation_id":"3423201c-da51-4d7f-9ca6-dea604f7a234","resolution":{"observed_at":"2026-08-10T23:59:58.362951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16589","last_updated":"2024-03-13T09:45:02Z","snapshot_observed_at":"2026-08-13T04:32:16.560335Z","submitted_at":"2024-01-29T21:44:27Z","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","version":2},"cited_work":{"arxiv_id":"2401.16589","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.16589","snapshot_observed_at":"2026-08-10T23:59:58.781429Z","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","venue":"cs.CL","work_id":"5cb021ff-d95d-4ad6-9d95-d00ecd7b37f4","year":2024},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.367871Z"},"links":{"cited_paper":"/paper/2401.16589","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:90ae5c6a1b882346d1a5a534bf8fc3dd94796d74fc618a1a780e58ca59996054","observation_id":"236f04be-4685-4bcb-9f9e-bc814fb649c4","resolution":{"observed_at":"2026-08-10T23:59:58.787044Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14292","last_updated":"2023-03-24T22:21:32Z","snapshot_observed_at":"2026-08-03T09:05:15.693909Z","submitted_at":"2023-03-24T22:21:32Z","title":"Chat2VIS: Fine-Tuning Data Visualisations using Multilingual Natural Language Text and Pre-Trained Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14292","snapshot_observed_at":"2026-08-10T23:59:58.372876Z","title":"and Susnjak, T., (2023) Chat2VIS: Fine -Tuning Data Visualisations using Multilingual Natural Language Text and Pre-Trained Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.372876Z"},"links":{"cited_paper":"/paper/2303.14292","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:9ca5f9792e7346805652c4a4241a405d397d0a3f05c228e966632e03b814d18e","observation_id":"df1cbd7e-bd6f-4d00-af8f-5d73fa3c81e9","resolution":{"observed_at":"2026-08-10T23:59:58.372876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.10244","last_updated":"2022-03-19T05:00:30Z","snapshot_observed_at":"2026-08-11T03:45:43.920485Z","submitted_at":"2022-03-19T05:00:30Z","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.10244","snapshot_observed_at":"2026-08-10T23:59:58.378381Z","title":"and Hoque, E., (2022) ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.378381Z"},"links":{"cited_paper":"/paper/2203.10244","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:fc49ac065243de5294b966fdaa213adb5163bdcc9d942681eb44c564c99c956d","observation_id":"06d10849-dbef-4a73-9a4b-e845e46592ea","resolution":{"observed_at":"2026-08-10T23:59:58.378381Z","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":"2026-08-10T23:59:59.065761Z","title":"and Stasko, J., (2021) NL4DV: A toolkit for generating analytic specifications for data visualization from natural language queries","venue":null,"work_id":"4dfdee4f-3745-4882-b3ed-0ffbe19cc6d4","year":2021},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.384597Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:fc5adc7aa58727f818780cfb3730b9023127eafff4a4318a788a2807a5573396","observation_id":"6d437fa1-68fd-43d7-84ae-72ce30315dd9","resolution":{"observed_at":"2026-08-10T23:59:59.071610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14935","last_updated":"2023-03-27T06:31:21Z","snapshot_observed_at":"2026-08-11T16:21:15.703388Z","submitted_at":"2023-03-27T06:31:21Z","title":"TabIQA: Table Questions Answering on Business Document Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14935","snapshot_observed_at":"2026-08-10T23:59:58.389935Z","title":"and Takasu, A., (2023) TabIQA: Table Questions Answering on Business Document Images","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.389935Z"},"links":{"cited_paper":"/paper/2303.14935","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:ec8d6fde2152dde2be86367358b47f3f38854cfce0fdbe3b7bc02791b4559279","observation_id":"68b05633-bde5-4c72-86df-9514e5150c41","resolution":{"observed_at":"2026-08-10T23:59:58.389935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.04584","last_updated":"2021-04-09T19:42:24Z","snapshot_observed_at":"2026-08-04T07:02:00.543113Z","submitted_at":"2021-04-09T19:42:24Z","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","version":1},"cited_work":{"arxiv_id":"2104.04584","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.04584","snapshot_observed_at":"2026-08-10T23:59:58.702657Z","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","venue":"cs.CL","work_id":"e7a4707d-4994-4330-93da-bf5d6df4e43d","year":2021},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.395383Z"},"links":{"cited_paper":"/paper/2104.04584","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:af6df83b729de357e296d8b64b40195a8860bf17f981a0d724d35180f9048781","observation_id":"74e383b4-2d85-43dd-90a9-b87451cfbce7","resolution":{"observed_at":"2026-08-10T23:59:58.708077Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11242","last_updated":"2025-03-18T02:12:21Z","snapshot_observed_at":"2026-08-13T04:59:28.064899Z","submitted_at":"2023-12-18T14:40:20Z","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11242","snapshot_observed_at":"2026-08-10T23:59:58.401057Z","title":"and Li, Z., (2023a) MAC- SQL: A Multi -Agent Collaborative Framework for Text -to-SQL","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.401057Z"},"links":{"cited_paper":"/paper/2312.11242","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:578c7b32576aa10fcf1f9437e05f046f659c147e2f6367f047542168cdd7b29c","observation_id":"f7b38d98-b84c-4ac6-abea-3ac47f350a39","resolution":{"observed_at":"2026-08-10T23:59:58.401057Z","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":"2026-08-10T23:59:59.046443Z","title":"and Shah, S., (2023b) DocGraphLM: Documental Graph Language Model for Information Extraction","venue":null,"work_id":"56810430-15a9-404d-99f8-72a53333db3a","year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.406527Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:8a80c3d877e6fda9f7d8f5d6f4e16677f062205c6de00ba5ead9f8467fe64e2f","observation_id":"de242ce7-fb69-41a7-849c-05391274fdc1","resolution":{"observed_at":"2026-08-10T23:59:59.052767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T23:59:59.027772Z","title":"and Qu, H., (2022) A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization","venue":null,"work_id":"4ed1479e-56fd-49bd-9e61-45b778ae2ecc","year":2022},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.411695Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:f963572961e1f48122c677f9e585d72723c9c9875f6bbb3638641eb9d0121495","observation_id":"cc58d2f5-36c1-4ccb-aef7-84247d760d4e","resolution":{"observed_at":"2026-08-10T23:59:59.033403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00832","last_updated":"2023-10-02T00:48:01Z","snapshot_observed_at":"2026-08-13T05:59:44.453147Z","submitted_at":"2023-10-02T00:48:01Z","title":"Natural Language Models for Data Visualization Utilizing nvBench Dataset","version":1},"cited_work":{"arxiv_id":"2310.00832","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.00832","snapshot_observed_at":"2026-08-10T23:59:58.658847Z","title":"Natural Language Models for Data Visualization Utilizing nvBench Dataset","venue":"cs.CL","work_id":"bcd6c00c-9780-4dad-bd0d-ce6a58a6e84d","year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.416774Z"},"links":{"cited_paper":"/paper/2310.00832","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:de3e0fc0c9e44bf65109014a4b02d727ee80c77ac268f253bdd2b6548ea2ec48","observation_id":"1fb2a94e-516c-4639-8644-0c0ed7ec16bd","resolution":{"observed_at":"2026-08-10T23:59:58.664642Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03463","last_updated":"2025-02-22T08:32:05Z","snapshot_observed_at":"2026-08-13T05:08:47.662999Z","submitted_at":"2023-12-06T12:37:28Z","title":"DBCopilot: Natural Language Querying over Massive Databases via Schema Routing","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03463","snapshot_observed_at":"2026-08-10T23:59:58.422455Z","title":"and Zeng, Z., (2023c) DBCopilot: Scaling Natural Language Querying to Massive Databases","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.422455Z"},"links":{"cited_paper":"/paper/2312.03463","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:6d2e718dfec7b8a6a9969b18786d231245e35cf650686d266232f04256731dcc","observation_id":"f9c6f662-f848-41f0-ab57-79dcb198d6eb","resolution":{"observed_at":"2026-08-10T23:59:58.422455Z","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":"2026-08-10T23:59:59.008163Z","title":"and Qu, H., (2022) AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization","venue":null,"work_id":"c41a5c93-0ae6-4db6-bc1e-017cd0f650b2","year":2022},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.427643Z"},"links":{"citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:80e792262cd4a893b776d77c3ec2de9a83b8fbf8a459b3b47cf264acc3a62cf0","observation_id":"316c38d1-a3de-468b-991d-20b4506c983a","resolution":{"observed_at":"2026-08-10T23:59:59.013992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.18983","last_updated":"2023-10-29T11:38:08Z","snapshot_observed_at":"2026-08-13T05:38:11.923612Z","submitted_at":"2023-10-29T11:38:08Z","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","version":1},"cited_work":{"arxiv_id":"2310.18983","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.18983","snapshot_observed_at":"2026-08-10T23:59:58.612619Z","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","venue":"cs.AI","work_id":"96340ee0-942e-47f6-a3e0-dcc82f89abc4","year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.432706Z"},"links":{"cited_paper":"/paper/2310.18983","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:1c3e6948d5855da7735341e085a22cc545511d820b2e4e6014c00820e9e45637","observation_id":"716b83ed-2060-484f-a109-5b3b30d217fc","resolution":{"observed_at":"2026-08-10T23:59:58.621759Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08887","last_updated":"2019-02-02T23:53:18Z","snapshot_observed_at":"2026-07-06T07:03:52.901427Z","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":"2026-08-10T23:59:58.438966Z","title":"and Radev, D., (2018) Spider: A Large -Scale Human-Labeled Dataset for Complex and Cross -Domain Semantic Parsing and Text -to-SQL Task","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.438966Z"},"links":{"cited_paper":"/paper/1809.08887","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:c2c2b6258528a8af014532f405d4f172e1e0672192d323bb84a9451122165d64","observation_id":"b181b434-deb1-4027-905b-9735dd2e7d05","resolution":{"observed_at":"2026-08-10T23:59:58.438966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08526","last_updated":"2023-11-14T20:39:12Z","snapshot_observed_at":"2026-08-13T05:25:16.260740Z","submitted_at":"2023-11-14T20:39:12Z","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08526","snapshot_observed_at":"2026-08-10T23:59:58.444422Z","title":"and Charnois, T., (2023) GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.444422Z"},"links":{"cited_paper":"/paper/2311.08526","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:a0c95bd48bf53609ef69d6801416ed6b794f4916a054737594b53fae895946b4","observation_id":"c5626bc9-11c1-4b23-b126-db9b77ebda9d","resolution":{"observed_at":"2026-08-10T23:59:58.444422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17342","last_updated":"2023-10-26T12:16:25Z","snapshot_observed_at":"2026-08-13T05:39:56.174392Z","submitted_at":"2023-10-26T12:16:25Z","title":"ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17342","snapshot_observed_at":"2026-08-10T23:59:58.449721Z","title":"and Yu, K., (2023a) ACT -SQL: In-Context Learning for Text-to-SQL with Automatically -Generated Chain -of-Thought","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.449721Z"},"links":{"cited_paper":"/paper/2310.17342","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:18f36c404259822d17cfab17f4a481eab7b2f4951e1e2a2354f34935207761d0","observation_id":"11063a1c-9a64-4da1-9b61-34678826f9c5","resolution":{"observed_at":"2026-08-10T23:59:58.449721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00816","last_updated":"2024-08-14T07:26:08Z","snapshot_observed_at":"2026-08-13T04:10:27.667741Z","submitted_at":"2024-02-26T01:17:50Z","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.00816","snapshot_observed_at":"2026-08-10T23:59:58.455968Z","title":"and Zhang, Y., (2024) CFRet -DVQA: Coarse-to-Fine Retrieval and Efficient Tuning for Document Visual Question Answering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.455968Z"},"links":{"cited_paper":"/paper/2403.00816","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:5dc5a5db3b2467d854aed6594950bdbd93e16836d22113e4fb241ae48c49b167","observation_id":"b7e62b7d-d560-4d58-a00c-bdcc05e5a5f6","resolution":{"observed_at":"2026-08-10T23:59:58.455968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17894","last_updated":"2024-05-20T02:45:37Z","snapshot_observed_at":"2026-08-13T05:39:22.463757Z","submitted_at":"2023-10-27T05:01:20Z","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17894","snapshot_observed_at":"2026-08-10T23:59:58.461362Z","title":"and Yang, H., (2023b) Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.461362Z"},"links":{"cited_paper":"/paper/2310.17894","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:1be1956ff3ae473ecb0e682b57e4c5633d27e97a7ed24340187211444bd4220e","observation_id":"19b2009d-51c8-4dfd-b642-b79980801cad","resolution":{"observed_at":"2026-08-10T23:59:58.461362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.07624","last_updated":"2021-06-01T05:38:50Z","snapshot_observed_at":"2026-08-12T20:59:46.367520Z","submitted_at":"2021-05-17T06:12:06Z","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.07624","snapshot_observed_at":"2026-08-10T23:59:58.466519Z","title":"and Chua, T.-S., (2021) TAT- QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T23:59:58.466519Z"},"links":{"cited_paper":"/paper/2105.07624","citing_paper":"/paper/2412.19718"},"observation_digest":"sha256:1e2cf4294f8299dec15f5850321d180c3e9bb82c138f2989a7980275cd8b4771","observation_id":"df004027-d119-4085-b54f-6105fe08a7af","resolution":{"observed_at":"2026-08-10T23:59:58.466519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.19718","last_updated":"2024-12-27T16:17:22Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-11T21:36:55.353028Z","submitted_at":"2024-12-27T16:17:22Z","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":7,"verified_fuzzy":6},"total_outbound_references":31},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2412.19718."}