{"as_of":"2026-08-06T18:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c81c36cb5fca476de48a21d784fa255bc22442a45c4c47264f81b118f92736ce","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:22:50.938199Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+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/2508.18676/citation-record","integrity":"/paper/2508.18676/integrity","json":"/paper/2508.18676/citation-record.json","paper":"/paper/2508.18676"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.05952","last_updated":"2025-04-07T00:44:34Z","snapshot_observed_at":"2026-07-06T18:43:00.310399Z","submitted_at":"2024-06-29T21:24:19Z","title":"H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables","version":3},"cited_work":{"arxiv_id":"2407.05952","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.05952","snapshot_observed_at":"2026-08-05T16:22:51.593612Z","title":"H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables","venue":"cs.DB","work_id":"4599016e-644f-47b4-b295-6b50ca07ae00","year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.706646Z"},"links":{"cited_paper":"/paper/2407.05952","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:a120c803dd2d6b72fb14a07873c46df790783c0db105975a513415feaa69dd02","observation_id":"d2a25411-95a3-407a-a8a3-caefed1c0cdf","resolution":{"observed_at":"2026-08-05T16:22:51.599284Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11018","last_updated":"2024-10-17T17:45:09Z","snapshot_observed_at":"2026-07-06T18:01:18.745347Z","submitted_at":"2024-04-17T02:49:26Z","title":"Many-Shot In-Context Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11018","snapshot_observed_at":"2026-08-05T16:22:50.712218Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.712218Z"},"links":{"cited_paper":"/paper/2404.11018","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:c39fc1f450c413d786b84b803de282961fab1976f419376e99784bb510e6759f","observation_id":"2de5a514-6e0c-4836-840b-4f516ef72eeb","resolution":{"observed_at":"2026-08-05T16:22:50.712218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11511","last_updated":"2023-10-17T18:18:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-17T18:18:32Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11511","snapshot_observed_at":"2026-08-05T16:22:50.718279Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.718279Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:b0d72a740c182a56889496e8d8e1a6bcadf71fc4293b10ac58a7f083c9b8d9ac","observation_id":"cef81262-de53-44ea-a679-d72df9925769","resolution":{"observed_at":"2026-08-05T16:22:50.718279Z","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":"2026-08-05T16:22:50.723980Z","title":"Cafarella, Alon Halevy, Daisy Zhe Wang, Eugene Wu, and Yang Zhang","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.723980Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:6fdbfdc0ed34462f0a81a65d3ce144deb58b599bdf8e42899ee09f34d733e802","observation_id":"ae042973-3715-4ae4-870e-0d95f9b0f27c","resolution":{"observed_at":"2026-08-05T16:22:50.723980Z","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":"2026-08-05T16:22:50.729618Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.729618Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:8061703645332f1d0289583d72de6ab823337754386c19eb2d1aa75e06879f68","observation_id":"48cd6a01-ca60-4fef-b9d4-304621a090d4","resolution":{"observed_at":"2026-08-05T16:22:50.729618Z","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":"2026-08-05T16:22:51.807133Z","title":null,"venue":null,"work_id":"61406855-b914-4dd1-a49a-938f9fe4969e","year":2019},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.734958Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:24faaa7c0211fb65731f9b8fa1e642de9e8f0613e652e4d373b6af6d333e41a2","observation_id":"2e075d76-9a2d-4377-8190-c2857f497b2f","resolution":{"observed_at":"2026-08-05T16:22:51.813154Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03524","last_updated":"2025-03-02T15:54:11Z","snapshot_observed_at":"2026-08-05T00:35:54.877130Z","submitted_at":"2024-10-04T15:44:47Z","title":"Steering Large Language Models between Code Execution and Textual Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03524","snapshot_observed_at":"2026-08-05T16:22:50.740416Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.740416Z"},"links":{"cited_paper":"/paper/2410.03524","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:380f911bb827b91317c27e6226c982138789b47627a97816fddf894748ef0d73","observation_id":"2de2a41f-b63d-4071-9f11-6403757b0a4c","resolution":{"observed_at":"2026-08-05T16:22:50.740416Z","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":"2026-08-05T16:22:51.789600Z","title":null,"venue":null,"work_id":"02e6fbf0-7cbb-4e9b-b532-4acb59db06e9","year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.746035Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:3e255e7c831dfd999d66ea0f2ea4c6c017470622404512e5943e30cb8a6768dd","observation_id":"bd0a8fa8-4406-4702-90a9-19262b8c333c","resolution":{"observed_at":"2026-08-05T16:22:51.795092Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.findings-emnlp.27","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:22:51.029482Z","title":null,"venue":null,"work_id":"23cb4b6b-89d7-4097-a631-121af83c1148","year":2020},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.750801Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:a1d8ca22cb3914598f096897d71718cdf62a51924b43dc8ff542b0abfa23880d","observation_id":"d4a24f34-8d86-4d0d-9326-4dfdd7a8447a","resolution":{"observed_at":"2026-08-05T16:22:51.035652Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-05T16:22:51.771008Z","title":null,"venue":null,"work_id":"4e6ee366-6154-4102-a966-4228c6626a67","year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.755992Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:1a07f20c2371d6c0840401ae8bb7ede1735ad89fddc37cd4756bfc908a964cab","observation_id":"648e49c1-fada-4ae7-b55c-dfd5c2e1fd36","resolution":{"observed_at":"2026-08-05T16:22:51.776763Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-05T16:22:50.762735Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.762735Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:ca480421195677030267bd6f373cd9c342cb5b37cb2266449ddcbbb4be697340","observation_id":"c92d935f-5360-45bd-823c-6e906623d25f","resolution":{"observed_at":"2026-08-05T16:22:50.762735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08998","last_updated":"2023-08-21T10:23:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-17T14:12:48Z","title":"Reinforced Self-Training (ReST) for Language Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08998","snapshot_observed_at":"2026-08-05T16:22:50.767606Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.767606Z"},"links":{"cited_paper":"/paper/2308.08998","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:bfa613681835c1f73af866203e7f0b7483bca74d5433d0b484913530cbb9ef2c","observation_id":"fbf281ee-c15b-4e3a-b418-d7d51a551176","resolution":{"observed_at":"2026-08-05T16:22:50.767606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09543","last_updated":"2023-03-24T09:17:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-11-18T06:48:00Z","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.09543","snapshot_observed_at":"2026-08-05T16:22:50.772814Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.772814Z"},"links":{"cited_paper":"/paper/2111.09543","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:f577608666da92f095bbe5fbf44caa7c2a7f5c2dd3d4cdb46748d1d9f070a92d","observation_id":"bcbe7d90-ab51-423e-9af4-f49e6f60e82f","resolution":{"observed_at":"2026-08-05T16:22:50.772814Z","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":"2026-08-05T16:22:50.778057Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.778057Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:07f0e87069599fbd284d56b6f36c712c853387af62d5d97bb34aae78d512ef69","observation_id":"7a57fe15-3d1c-4ede-a7cb-ff6a50585a3f","resolution":{"observed_at":"2026-08-05T16:22:50.778057Z","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":"2026-08-05T16:22:51.751884Z","title":null,"venue":null,"work_id":"8f61705f-bcec-4a3d-bcb9-e3d1ff8937fd","year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.782925Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:c952979c2f4bf6335bf21b83f173757ffab6e7d108bb52999cbf7c90027eb3b0","observation_id":"f1bd013c-ea94-4279-abd2-78ada6aff804","resolution":{"observed_at":"2026-08-05T16:22:51.758294Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01798","last_updated":"2024-03-14T04:27:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-03T04:56:12Z","title":"Large Language Models Cannot Self-Correct Reasoning Yet","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01798","snapshot_observed_at":"2026-08-05T16:22:50.787817Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.787817Z"},"links":{"cited_paper":"/paper/2310.01798","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:802c94d2a05926d65621ab7f5b88773fa4dc17e2eeefea7f8be3f5ad5787508b","observation_id":"c0e2dce3-80da-48ee-9047-8326fa16bf56","resolution":{"observed_at":"2026-08-05T16:22:50.787817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09645","last_updated":"2023-10-23T07:51:23Z","snapshot_observed_at":"2026-07-06T15:28:16.998343Z","submitted_at":"2023-05-16T17:45:23Z","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.09645","snapshot_observed_at":"2026-08-05T16:22:50.792809Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.792809Z"},"links":{"cited_paper":"/paper/2305.09645","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:01916d5bf658a293cd7678ad5ec30719815208ac7647a6338599a23f5445bfb7","observation_id":"e8e6e0fd-56ac-41d9-bf16-9f112015f9c2","resolution":{"observed_at":"2026-08-05T16:22:50.792809Z","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":"2026-08-05T16:22:50.798682Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.798682Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:c869b7b826abd2e3a683d645a8029f6faabcedbbc5f9bca4abede3598696f43e","observation_id":"e5e9d5e3-38ab-4053-9719-c340687969dc","resolution":{"observed_at":"2026-08-05T16:22:50.798682Z","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":"2026-08-05T16:22:51.730255Z","title":null,"venue":null,"work_id":"ad76fd5f-0840-4b3d-a637-9cab85a00d0e","year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.803916Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:8978b42d4e409b56b233ed3645d330aefa4f1a7d34a2de2529247bdcc5552d3c","observation_id":"a2cbb05d-7954-4223-84d7-e5dde5e17109","resolution":{"observed_at":"2026-08-05T16:22:51.737202Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09263","last_updated":"2023-10-13T17:20:56Z","snapshot_observed_at":"2026-08-05T14:02:04.408768Z","submitted_at":"2023-10-13T17:20:56Z","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09263","snapshot_observed_at":"2026-08-05T16:22:50.809542Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.809542Z"},"links":{"cited_paper":"/paper/2310.09263","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:5838a233252e9b8d00f430a8c68198cb1da33e35489e5e8e2fa14cab317312bc","observation_id":"7338b5a2-b0fc-4bc3-902a-5d942da7f062","resolution":{"observed_at":"2026-08-05T16:22:50.809542Z","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":"2026-08-05T16:22:51.709902Z","title":null,"venue":null,"work_id":"3facc55b-5d93-4dbe-a931-7d48e6b3ecd5","year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.814733Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:555d11cad8b32117fffd60407c7440ea6ef1950424f26f1002d6ba0db0e344b5","observation_id":"daadfe73-90ef-4bad-a2e0-71ef875d478f","resolution":{"observed_at":"2026-08-05T16:22:51.715600Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-05T16:22:51.691021Z","title":null,"venue":null,"work_id":"f2ed4bc2-3a0f-4f5d-9a2c-396049555781","year":2021},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.819527Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:5786a4235fd675bc97acce961ade152265f2d5221615cb1ecb2098d8e0f6d5d0","observation_id":"cd0b98e2-6ef8-4d5a-aa30-e170bc2c8bb3","resolution":{"observed_at":"2026-08-05T16:22:51.696811Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.16702","last_updated":"2023-12-27T19:58:52Z","snapshot_observed_at":"2026-07-06T17:09:02.167931Z","submitted_at":"2023-12-27T19:58:52Z","title":"Rethinking Tabular Data Understanding with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.16702","snapshot_observed_at":"2026-08-05T16:22:50.824293Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.824293Z"},"links":{"cited_paper":"/paper/2312.16702","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:5f33530bbc83644735acd6a40c2a67033d38ff154780a3630621defe3672689c","observation_id":"ced3f6b9-097b-4db9-a574-351596588d7a","resolution":{"observed_at":"2026-08-05T16:22:50.824293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12644","last_updated":"2025-08-08T04:35:26Z","snapshot_observed_at":"2026-07-06T19:52:42.231424Z","submitted_at":"2024-11-19T16:54:45Z","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12644","snapshot_observed_at":"2026-08-05T16:22:50.829373Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.829373Z"},"links":{"cited_paper":"/paper/2411.12644","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:d132a34aae900283ba996da5bb7fc6281442bb6d16ca4e5435fd387687e48c29","observation_id":"524a0937-2b4e-4ad7-a2cc-cce4db8b2995","resolution":{"observed_at":"2026-08-05T16:22:50.829373Z","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":"2026-08-05T16:22:50.834346Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.834346Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:1c4f11cf8660ea95ccb18fcbaa85ad0de56da3963ef59a6d091bb5819031f028","observation_id":"38992f59-4837-4aa9-87e0-6e3933628973","resolution":{"observed_at":"2026-08-05T16:22:50.834346Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-05T16:22:50.839164Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.839164Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:9e1cbccf04e1e28eaa3670b433c69285227c729ed2fb6e788e9fceec6bc3d7f1","observation_id":"fd05dfd8-238c-4ecb-ac15-f41a82e92159","resolution":{"observed_at":"2026-08-05T16:22:50.839164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01155","last_updated":"2024-02-13T09:11:01Z","snapshot_observed_at":"2026-08-04T21:58:33.840061Z","submitted_at":"2024-02-02T05:48:39Z","title":"CABINET: Content Relevance based Noise Reduction for Table Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01155","snapshot_observed_at":"2026-08-05T16:22:50.845445Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.845445Z"},"links":{"cited_paper":"/paper/2402.01155","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:28c15a53863e74be5a7f6c25f9099c2370dad64fe77a9ffba754eb1c0c744618","observation_id":"7f2443df-323a-4fd6-aba3-f253945c9f43","resolution":{"observed_at":"2026-08-05T16:22:50.845445Z","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":"2026-08-05T16:22:51.670336Z","title":null,"venue":null,"work_id":"524e9397-ce73-47cf-bd49-9cf58ec133e9","year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.850686Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:fd44a74ef884f835667e5f034ba22fa985036f08898e61ca178be2bf92c6b723","observation_id":"35f10aa1-8893-4452-b72e-9bb04b74ef60","resolution":{"observed_at":"2026-08-05T16:22:51.676394Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-05T16:22:50.857212Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.857212Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:8645e3f113304645a049e0f8071dfc30413bcd249999eb8c21b1011fe7875851","observation_id":"74fadc04-3375-41ec-9c33-da8c6e8c4019","resolution":{"observed_at":"2026-08-05T16:22:50.857212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06585","last_updated":"2024-04-18T03:12:09Z","snapshot_observed_at":"2026-07-06T16:59:56.350207Z","submitted_at":"2023-12-11T18:17:43Z","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.06585","snapshot_observed_at":"2026-08-05T16:22:50.862355Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.862355Z"},"links":{"cited_paper":"/paper/2312.06585","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:4f0a027d5dce25102e09eb20feeb69c327b09aafe59d27adfc75455d5a290b8e","observation_id":"71059b91-6525-46b3-98d2-7379c09ed54a","resolution":{"observed_at":"2026-08-05T16:22:50.862355Z","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":"2026-08-05T16:22:51.638517Z","title":null,"venue":null,"work_id":"78f0049d-a616-47a3-b136-650017f0fda6","year":2021},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.868223Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:ee6274821e4a7bacea3892603c879f83dc431803677581289144cb20c69f39b3","observation_id":"92bd4919-b8ac-4109-8472-5089b7716ff5","resolution":{"observed_at":"2026-08-05T16:22:51.644272Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04398","last_updated":"2024-01-19T01:05:05Z","snapshot_observed_at":"2026-07-06T17:13:08.935785Z","submitted_at":"2024-01-09T07:46:26Z","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04398","snapshot_observed_at":"2026-08-05T16:22:50.873494Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.873494Z"},"links":{"cited_paper":"/paper/2401.04398","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:c93ee44a6c6e6ea6d0e451004dba46d1e15971d9c9ad2cc52402f38eb1f023ea","observation_id":"a976de8e-c5ce-4d2d-9b79-b85b4fa3425d","resolution":{"observed_at":"2026-08-05T16:22:50.873494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02177","last_updated":"2025-03-28T07:03:38Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:21:19Z","title":"ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context","version":3},"cited_work":{"arxiv_id":"2403.02177","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.02177","snapshot_observed_at":"2026-08-05T16:22:51.242800Z","title":"ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context","venue":"cs.CL","work_id":"216a9c35-1ccf-4206-b6a4-fb92edf76945","year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.878782Z"},"links":{"cited_paper":"/paper/2403.02177","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:8c6999e9a5a33d198381825feffbcbd3671a8bc19d0d1446333e4b882eabe844","observation_id":"0ac41209-30f1-41d8-afc6-7ed0cbb5abf1","resolution":{"observed_at":"2026-08-05T16:22:51.249566Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.05966","last_updated":"2022-10-18T15:56:01Z","snapshot_observed_at":"2026-07-06T12:27:42.701847Z","submitted_at":"2022-01-16T04:36:18Z","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.05966","snapshot_observed_at":"2026-08-05T16:22:50.884020Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.884020Z"},"links":{"cited_paper":"/paper/2201.05966","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:c80bd546b204790fb60ace5b7513684d3e9f9a7f44ec846efae10dc0ceb34884","observation_id":"e9a4bce6-1cc6-4acb-a236-43318a3ae764","resolution":{"observed_at":"2026-08-05T16:22:50.884020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15884","last_updated":"2024-10-07T02:19:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-29T04:36:39Z","title":"Corrective Retrieval Augmented Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15884","snapshot_observed_at":"2026-08-05T16:22:50.890723Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.890723Z"},"links":{"cited_paper":"/paper/2401.15884","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:2e79cfc71e7e68fa7a21c1b7d1f9082f6f46f8844dcafe068e14e2f96b717ada","observation_id":"b3320137-faea-44dc-b14e-78d80162c814","resolution":{"observed_at":"2026-08-05T16:22:50.890723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09249","last_updated":"2024-03-13T08:20:34Z","snapshot_observed_at":"2026-08-03T13:32:00.010393Z","submitted_at":"2023-07-18T13:28:31Z","title":"UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09249","snapshot_observed_at":"2026-08-05T16:22:50.897110Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.897110Z"},"links":{"cited_paper":"/paper/2307.09249","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:82905e8cb2bbab04ba431be1609bb983e370ea95dd5003f5db7069017692bd5c","observation_id":"0fc7af22-d5b5-4e62-b488-ecbf0d9befef","resolution":{"observed_at":"2026-08-05T16:22:50.897110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13808","last_updated":"2023-04-27T11:24:10Z","snapshot_observed_at":"2026-08-02T04:41:43.291521Z","submitted_at":"2023-01-31T17:51:45Z","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","version":3},"cited_work":{"arxiv_id":"2301.13808","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.13808","snapshot_observed_at":"2026-08-05T16:22:51.164196Z","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","venue":"cs.CL","work_id":"b481c62f-3d1b-440a-9857-f6c2810cbeda","year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.902039Z"},"links":{"cited_paper":"/paper/2301.13808","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:7fb06915b3e31ef289bea9192e34020ba7f9163b2297c7aaba15513e172cdadc","observation_id":"51ef407c-a18d-48b2-82a3-ca162a7c8d5b","resolution":{"observed_at":"2026-08-05T16:22:51.170253Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-07-06T18:29:04.294349Z","submitted_at":"2024-06-11T17:32:21Z","title":"TextGrad: Automatic \"Differentiation\" via Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07496","snapshot_observed_at":"2026-08-05T16:22:50.907232Z","title":"differentiation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.907232Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:5446e0b773bc5a46b0b6b1abd9012564e340f58eeb417272e247eeae0e139cc9","observation_id":"64223b63-9882-44f1-9d82-987093b72b33","resolution":{"observed_at":"2026-08-05T16:22:50.907232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08674","last_updated":"2023-08-07T12:08:17Z","snapshot_observed_at":"2026-07-06T15:54:58.589775Z","submitted_at":"2023-07-17T17:36:09Z","title":"TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08674","snapshot_observed_at":"2026-08-05T16:22:50.912101Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.912101Z"},"links":{"cited_paper":"/paper/2307.08674","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:0d41dba41452715859f6f0e9bb6b6fdb6079e5da02c67cc4117a3ed13ce0aec4","observation_id":"6ab8e126-948c-4e24-8439-b0a1cde8716d","resolution":{"observed_at":"2026-08-05T16:22:50.912101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09206","last_updated":"2024-04-04T17:10:25Z","snapshot_observed_at":"2026-08-03T02:14:59.224480Z","submitted_at":"2023-11-15T18:47:52Z","title":"TableLlama: Towards Open Large Generalist Models for Tables","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09206","snapshot_observed_at":"2026-08-05T16:22:50.917417Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.917417Z"},"links":{"cited_paper":"/paper/2311.09206","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:6ecd0a5528463d9600a3c68d7fa9d09e021df1d52718d50eedb5bed5e045599d","observation_id":"7d7f51e5-05cc-4809-83e5-8c46378e393d","resolution":{"observed_at":"2026-08-05T16:22:50.917417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00815","last_updated":"2023-10-01T23:14:38Z","snapshot_observed_at":"2026-07-06T16:26:13.862006Z","submitted_at":"2023-10-01T23:14:38Z","title":"ReAcTable: Enhancing ReAct for Table Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00815","snapshot_observed_at":"2026-08-05T16:22:50.922518Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.922518Z"},"links":{"cited_paper":"/paper/2310.00815","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:9bb96f5a666cfbb73b45dff47d6d3a3cc975c0323133e2c96476fa9899b9adff","observation_id":"43632370-f14a-4c6f-8c06-f900a0f4cb95","resolution":{"observed_at":"2026-08-05T16:22:50.922518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.12374","last_updated":"2022-10-22T07:04:02Z","snapshot_observed_at":"2026-07-06T14:09:01.413494Z","submitted_at":"2022-10-22T07:04:02Z","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","version":1},"cited_work":{"arxiv_id":"2210.12374","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.12374","snapshot_observed_at":"2026-08-05T16:22:51.065594Z","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","venue":"cs.CL","work_id":"45f943fd-d2ed-400f-8846-69e1af602ad1","year":2022},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.927537Z"},"links":{"cited_paper":"/paper/2210.12374","citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:cef306022c5a28bd8bb0214bfca8555cf19cb9fda7c52e4d96b14ac610c0887f","observation_id":"5904bc5b-ba22-48b1-bfa8-37c88207ff9b","resolution":{"observed_at":"2026-08-05T16:22:51.072117Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-05T16:22:50.932869Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.932869Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:991f7364ce2dea359418d535bb3a0980a08a470f3fc8224e84316227bc91a8db","observation_id":"ba15425c-a180-438b-9be1-704ca0d03141","resolution":{"observed_at":"2026-08-05T16:22:50.932869Z","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":"2026-08-05T16:22:50.938199Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-05T16:22:50.938199Z"},"links":{"citing_paper":"/paper/2508.18676"},"observation_digest":"sha256:b710c999aacf2c4ddbb30e78b3a45b7eeb1307717d1049981142dd7beb64c8b3","observation_id":"a15b98c3-a174-4dd8-9b49-3d97f3ca45a6","resolution":{"observed_at":"2026-08-05T16:22:50.938199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.18676","last_updated":"2025-08-26T04:46:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T16:22:48.773594Z","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":44},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2508.18676."}