{"as_of":"2026-08-12T17:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2994fd227781bdb2eeeca74a1719c99306c01520429f42ad91a1e297aa6128e1","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:59:58.663292Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T06:03:43.410678Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T06:03:57.334781Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"cited_work":{"arxiv_id":"2501.14693","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.14693","snapshot_observed_at":"2026-08-07T06:03:57.334781Z","title":"Rethinking Table Instruction Tuning","venue":"cs.CL","work_id":"1f53fefe-9a25-4a78-b417-0e03fda0f19b","year":2025},"citing_paper":{"arxiv_id":"2506.06137","last_updated":"2025-06-06T14:52:19Z","snapshot_observed_at":"2026-08-09T22:49:50.230202Z","submitted_at":"2025-06-06T14:52:19Z","title":"Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T06:03:43.410678Z"},"links":{"cited_paper":"/paper/2501.14693","citing_paper":"/paper/2506.06137"},"observation_digest":"sha256:ab4ff3d7c3f92fa35580d6c8b7d14c317391f3668239d6d3702eed177482455e","observation_id":"6f031d59-c76c-4ae1-bae5-e6c18461f837","resolution":{"observed_at":"2026-08-07T06:03:57.412504Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.14693/citation-record","integrity":"/paper/2501.14693/integrity","json":"/paper/2501.14693/citation-record.json","paper":"/paper/2501.14693"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:59:58.367641Z","title":"URL: \" 'urlintro :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.367641Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:6157a4fd98961ca957c8ae9615deb7464d649d11250c943f2dc0a4f9b97ec1f0","observation_id":"96e8b386-9f57-4a52-8a1e-983b1f99b69a","resolution":{"observed_at":"2026-08-10T14:59:58.367641Z","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":"2026-08-10T14:59:58.373513Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.373513Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:9601a3d9cbeb31e973f7fa27195c38cbc8295f7f1bdb200c807b2d6214142c6b","observation_id":"c0601fd9-68a0-4e57-a005-4b187fdf3ed4","resolution":{"observed_at":"2026-08-10T14:59:58.373513Z","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":"2026-08-10T14:59:58.379297Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.379297Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:66fb3aa137e83f7b0623f8d2953772f8acf4d93bc90f0df6af22122ebacf8c36","observation_id":"2a6d0870-c0f9-4ee9-b2be-93dc6e8ea6b9","resolution":{"observed_at":"2026-08-10T14:59:58.379297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-08-10T14:07:02.234322Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-10T14:59:58.384647Z","title":"Phi-3 technical report: A highly capable language model locally on your phone","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.384647Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:286a39d9bd8b680d670798042e430698785fc43d48e9309b936decceda7e83f6","observation_id":"0c7641cf-3874-4296-9d40-80c4fac905b3","resolution":{"observed_at":"2026-08-10T14:59:58.384647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T14:59:58.389703Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.389703Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:e43c8ba4ae54285807b1c95e9b90524bc77d1f90aed07e5853c1ea48afb48e3c","observation_id":"7f377886-1c09-4305-97b4-4885a8a9bffe","resolution":{"observed_at":"2026-08-10T14:59:58.389703Z","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":"2026-08-10T14:59:58.394250Z","title":"The fact extraction and VER ification over unstructured and structured information ( FEVEROUS ) shared task","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.394250Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:bb597db036a3e440dc30ea857cce8767c4f3ad204c948bda11b908a2e222cd19","observation_id":"57fdcb65-cf4f-4ff9-8359-d1a04c09409d","resolution":{"observed_at":"2026-08-10T14:59:58.394250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-08-09T21:25:20.369782Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-10T14:59:58.399360Z","title":"Qwen technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.399360Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:60d6e77c7b93b55149ba97256952a36d7587c4d629c91c91d63611044c2cf922","observation_id":"412069e0-fe83-4035-8159-2f67e57ab74a","resolution":{"observed_at":"2026-08-10T14:59:58.399360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11853","last_updated":"2023-11-27T00:42:07Z","snapshot_observed_at":"2026-07-06T15:29:50.743434Z","submitted_at":"2023-05-19T17:43:58Z","title":"How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11853","snapshot_observed_at":"2026-08-10T14:59:58.404418Z","title":"How to prompt llms for text-to-sql: A study in zero-shot, single-domain, and cross-domain settings","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.404418Z"},"links":{"cited_paper":"/paper/2305.11853","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:72b9099db836256fc8f378da863cd04e4cba3b9ead204cc9f31659a003751dcd","observation_id":"11948538-93c6-49a2-b3f7-62ce8b015ddf","resolution":{"observed_at":"2026-08-10T14:59:58.404418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02164","last_updated":"2020-06-14T19:14:22Z","snapshot_observed_at":"2026-08-10T16:21:51.911168Z","submitted_at":"2019-09-05T00:25:17Z","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.02164","snapshot_observed_at":"2026-08-10T14:59:58.409089Z","title":"Tabfact: A large-scale dataset for table-based fact verification","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.409089Z"},"links":{"cited_paper":"/paper/1909.02164","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:51950bed0ef3d131346e02a183103dfb2d5f4ca9c5890cb3e5d0b8f80f31c344","observation_id":"b4bfff87-87b5-4012-a694-ae69b1a713b5","resolution":{"observed_at":"2026-08-10T14:59:58.409089Z","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":"2026-08-10T14:59:58.414151Z","title":"H ybrid QA : A dataset of multi-hop question answering over tabular and textual data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.414151Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:054b312d5aa5474092727910875824997af3a7596b097ceb5aa519c428663679","observation_id":"f6340280-e65f-4c16-a882-70b45aae325f","resolution":{"observed_at":"2026-08-10T14:59:58.414151Z","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":"2026-08-10T14:59:58.419032Z","title":"H i T ab: A hierarchical table dataset for question answering and natural language generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.419032Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:0c5b894bb108e3ca2651b12c8c431bb57f05e94a42c6557fee130cd4c1d4b1f3","observation_id":"74e624f1-4e5e-4b54-be5c-ae76a9b35f45","resolution":{"observed_at":"2026-08-10T14:59:58.419032Z","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":"2026-08-10T14:59:58.423985Z","title":"Vicuna: An open-source chatbot impressing gpt-4 with 90\\ See https://vicuna","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.423985Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:83b557b22b48f489f0a78320947ad1de0525146d1cceca1e1bbb9afb72037cca","observation_id":"0ceee8c1-5de8-41fc-9adb-f9fecfe478fa","resolution":{"observed_at":"2026-08-10T14:59:58.423985Z","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":"2026-08-10T14:59:58.428689Z","title":"Scaling instruction-finetuned language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.428689Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:c2b59586dd76a1a2576e658fa334c238856df7e7c7909c61434d8d6ffcfa0798","observation_id":"f2ee7d09-a517-4eb9-bdc8-213e8ff52175","resolution":{"observed_at":"2026-08-10T14:59:58.428689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-10T14:59:58.433443Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.433443Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:8fce1dadc3d0d18a387a949bcc875a710c530c43ca6e745a96059f651cd6a7e7","observation_id":"d88237cd-e71f-4568-9bef-74524daf5753","resolution":{"observed_at":"2026-08-10T14:59:58.433443Z","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":"2026-08-10T14:59:59.670272Z","title":"Tables as texts or images: Evaluating the table reasoning ability of LLM s and MLLM s","venue":null,"work_id":"31babb43-7a16-4137-b22b-a415d5c1fd16","year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.438203Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:7af825ec7a56ab07e362b143ff20cdbca928a7060d5567cdb7c453dc574d6e54","observation_id":"39d86cca-52bd-4069-a526-cd041f6e33a1","resolution":{"observed_at":"2026-08-10T14:59:59.675490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T14:59:58.442816Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.442816Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:2f0a9c0e534f8e78364cfc4e63afc46076501f0bcec5de7df06f236018c5b5c3","observation_id":"cfa9fc99-f883-44f5-9251-c28d35937bf9","resolution":{"observed_at":"2026-08-10T14:59:58.442816Z","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":"2026-08-10T14:59:58.447416Z","title":"BERT : Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.447416Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:c74c6962ce98ed3a6ac27e91cb4d52f455309089a03ee3d585f9085cd1ffe31f","observation_id":"82bde568-04c7-4adb-8227-11cf5bd87793","resolution":{"observed_at":"2026-08-10T14:59:58.447416Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-10T14:59:58.451560Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.451560Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:6aa306773516af162504b457461dcb7367eaca119d83853db14c6fc20f0bdda7","observation_id":"b267509e-aa7e-447e-b71a-c507c1586e42","resolution":{"observed_at":"2026-08-10T14:59:58.451560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.05414","last_updated":"2017-07-14T00:45:59Z","snapshot_observed_at":"2026-08-02T19:17:38.090294Z","submitted_at":"2017-05-15T19:11:12Z","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.05414","snapshot_observed_at":"2026-08-10T14:59:58.456823Z","title":"Key-value retrieval networks for task-oriented dialogue","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.456823Z"},"links":{"cited_paper":"/paper/1705.05414","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:3a57c3fb40c034816abcd8359e40aaa6b4e5f8f45fa3bb0bac5fc332b362b986","observation_id":"d3b92195-61c8-4822-869f-91626925cfec","resolution":{"observed_at":"2026-08-10T14:59:58.456823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11738","last_updated":"2024-02-21T12:59:21Z","snapshot_observed_at":"2026-07-31T18:12:14.483728Z","submitted_at":"2023-05-19T15:19:44Z","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11738","snapshot_observed_at":"2026-08-10T14:59:58.461595Z","title":"Critic: Large language models can self-correct with tool-interactive critiquing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.461595Z"},"links":{"cited_paper":"/paper/2305.11738","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:a368a67d3a77ae1cb5b1509db518db0b57e725b39f37283dd20f0fc0edf1fb6e","observation_id":"4f32118a-6241-4daf-b95d-740fc17cc614","resolution":{"observed_at":"2026-08-10T14:59:58.461595Z","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":"2026-08-10T14:59:58.466589Z","title":"INFOTABS : Inference on tables as semi-structured data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.466589Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:474df7714faf542d0471b54221e6ff0f19c87fb7a03d873dbaf77310fe28916a","observation_id":"a3e61928-7e4b-41d8-89dc-e5c3a8be2d93","resolution":{"observed_at":"2026-08-10T14:59:58.466589Z","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":"2026-08-10T14:59:58.471485Z","title":"Measuring massive multitask language understanding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.471485Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:a05bd0e8e231c99bdd338a53e2590c5fcfb39097c651818d8e9b7ac67f3ae8ea","observation_id":"bfe465ec-c4bc-4c25-b581-0e9d156af821","resolution":{"observed_at":"2026-08-10T14:59:58.471485Z","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":"2026-08-10T14:59:58.476243Z","title":"T a P as: Weakly supervised table parsing via pre-training","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.476243Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:baa767613bba7f16feac3d0a27dde07bb89fb017f32c0ec9dccf5f6171ad996c","observation_id":"029eae3f-05c1-4987-b7ba-86af5ab6e2ac","resolution":{"observed_at":"2026-08-10T14:59:58.476243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-10T14:59:58.480909Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.480909Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:919daeb9e0e19c03c67bf09abd421af5b7d9d8fe519acbe3e75a5263fff72799","observation_id":"fde0f27f-3588-417e-af9d-84f9cedd6255","resolution":{"observed_at":"2026-08-10T14:59:58.480909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-10T14:59:58.485430Z","title":"Mistral 7b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.485430Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:6ba968e3bcbe10f9e5e43ff0c02e4e30b8281b15c9d752e555c7726074ac5ef1","observation_id":"65965349-b386-4502-be28-5299681c3f7d","resolution":{"observed_at":"2026-08-10T14:59:58.485430Z","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":"2026-08-10T14:59:58.490569Z","title":"AIT-QA : Q uestion answering dataset over complex tables in the airline industry","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.490569Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:c2a946383fe2e43d83e25341e1204e1a5ad0846db25d4ddcab4beab04fd6b473","observation_id":"39fadb3f-6fe1-4eef-9b4b-43ee48745a64","resolution":{"observed_at":"2026-08-10T14:59:58.490569Z","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":"2026-08-10T14:59:58.495596Z","title":"Neural text generation from structured data with application to the biography domain","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.495596Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:7e88fbc11296016a858f4075f219ddc458ac959947780788a14638c65b22a639","observation_id":"27717b3f-c4e8-4cf9-82ed-c3466f4093e7","resolution":{"observed_at":"2026-08-10T14:59:58.495596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T14:59:58.500992Z","title":"Table-gpt: Table-tuned gpt for diverse table tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.500992Z"},"links":{"cited_paper":"/paper/2310.09263","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:d7849d9da40f72905abed3b7c2afe9f16d796a5cc70ac03ba4b0b596063a225e","observation_id":"e3915953-0c50-4bed-8830-ef50fc4e4409","resolution":{"observed_at":"2026-08-10T14:59:58.500992Z","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":"2026-08-10T14:59:59.621202Z","title":"Table-to-text generation by structure-aware seq2seq learning","venue":null,"work_id":"57f8eec5-ddb8-48fd-92c5-cadf70d5ef6d","year":2018},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.505884Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:e4f1e84a745343a6ac9cb2af13ba25ef8b7c0b5e201821e19aa0aa29f9becb1f","observation_id":"42ee9c59-be55-4566-b23d-81de7b1835ae","resolution":{"observed_at":"2026-08-10T14:59:59.627694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T14:59:58.510606Z","title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.510606Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:3744477956a080bdb18ef2c996ed836f5f7b1e3fd34b5224e1b4293ad22fbafc","observation_id":"f85a8118-77e2-4a22-9063-bc1773eff1fb","resolution":{"observed_at":"2026-08-10T14:59:58.510606Z","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":"2026-08-10T14:59:58.515318Z","title":"F e T a QA : Free-form table question answering","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.515318Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:ffdbedc91c8005597c23e9723a683a99d9e303f06cd82af60a4620e8becf017c","observation_id":"649fd74e-db73-4d0d-af9c-583a7a9d5b2c","resolution":{"observed_at":"2026-08-10T14:59:58.515318Z","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":"2026-08-10T14:59:58.520110Z","title":"ToTTo : A controlled table-to-text generation dataset","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.520110Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:eb6eda50a9e187f41e0a8870b921355fdd7d55285b9f488b85c8e3fde6cfb205","observation_id":"54b97192-fe0f-40f3-a955-20d010da747c","resolution":{"observed_at":"2026-08-10T14:59:58.520110Z","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":"2026-08-10T14:59:58.524898Z","title":"Compositional semantic parsing on semi-structured tables","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.524898Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:4e49c08aeb8df92ba631647aa0dd9c5251e8a31d09d7125cc2dc5b7568b8c35b","observation_id":"30ab07de-dac0-4acf-b5f1-0ab26aa39a07","resolution":{"observed_at":"2026-08-10T14:59:58.524898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-10T14:59:58.529635Z","title":"Qwen2.5 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.529635Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:18473c6a88bcb7d5eb5ac5732e2c0371eee447a077129b9b8e5a02dae1e40f5c","observation_id":"411c5b93-cb2e-449c-9804-0deda9d2031b","resolution":{"observed_at":"2026-08-10T14:59:58.529635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12022","last_updated":"2023-11-20T18:57:34Z","snapshot_observed_at":"2026-08-10T12:02:35.919497Z","submitted_at":"2023-11-20T18:57:34Z","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12022","snapshot_observed_at":"2026-08-10T14:59:58.534356Z","title":"Gpqa: A graduate-level google-proof q&a benchmark","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.534356Z"},"links":{"cited_paper":"/paper/2311.12022","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:19947617cebfc6fb8082a9b9dacc2abc8c49eb92b283a7d8da7d9ee152526af3","observation_id":"34dc890b-8f17-4612-9d69-1a9e6ef4674c","resolution":{"observed_at":"2026-08-10T14:59:58.534356Z","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":"2026-08-10T14:59:58.538899Z","title":"Assessing llms' mathematical reasoning in financial document question answering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.538899Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:a28373f9af8cfab0dde9748cd31850af0c6037b67475e8335531533fdefa2c60","observation_id":"c966cd12-fa7f-4fdd-9f26-ffdb3b8e4d71","resolution":{"observed_at":"2026-08-10T14:59:58.538899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-07T15:32:17.369903Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-10T14:59:58.543109Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.543109Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:4b1b5d11bed7d0b3ae08a427e1e06ad1643ab7d5e5ed8f019aa0b5b5dd6cbb0d","observation_id":"af3be644-c0c9-4540-bfd3-a6aa1b03d07f","resolution":{"observed_at":"2026-08-10T14:59:58.543109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-10T14:59:58.548023Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.548023Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:12a3658d63b40a86655e7790908ba690398579d79c5193fb86ae2dd975be5be2","observation_id":"e256fce7-0d3b-416d-8eab-5d2d99d601c1","resolution":{"observed_at":"2026-08-10T14:59:58.548023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01574","last_updated":"2024-11-06T02:54:00Z","snapshot_observed_at":"2026-08-06T00:29:17.674418Z","submitted_at":"2024-06-03T17:53:00Z","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01574","snapshot_observed_at":"2026-08-10T14:59:58.553046Z","title":"Mmlu-pro: A more robust and challenging multi-task language understanding benchmark","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.553046Z"},"links":{"cited_paper":"/paper/2406.01574","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:0a525914f27a71a76258cd2134701030641a8c5b8f91a5184c60f90a4fc80082","observation_id":"60c5a44b-e9dc-45b9-990b-6b1e2eb6e3b5","resolution":{"observed_at":"2026-08-10T14:59:58.553046Z","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":"2026-08-10T14:59:58.558135Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.558135Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:babdb55d2dfbf9d7669b441d9a569c10f52d8fd40dd64b6470bc5b90eadc1984","observation_id":"2c4fcea9-c720-4b91-94b4-3138b344da81","resolution":{"observed_at":"2026-08-10T14:59:58.558135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.09174","last_updated":"2025-03-18T07:13:18Z","snapshot_observed_at":"2026-08-09T09:48:05.918224Z","submitted_at":"2024-08-17T11:40:10Z","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.09174","snapshot_observed_at":"2026-08-10T14:59:58.563072Z","title":"Tablebench: A comprehensive and complex benchmark for table question answering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.563072Z"},"links":{"cited_paper":"/paper/2408.09174","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:a2dcb8f18865f7e0b20c69c87a9a9c6b98960c591838f06b0eec612ae73c605d","observation_id":"423b7eac-1f98-462e-96a4-19acc45ffdcc","resolution":{"observed_at":"2026-08-10T14:59:58.563072Z","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":"2026-08-10T14:59:58.568026Z","title":"Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.568026Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:1298d3649621eb1292971c134f17c94e6331df2ff8aa88b79ffb31de46cccd1d","observation_id":"4387817f-a8f0-49c8-afb2-db6e9fe143c1","resolution":{"observed_at":"2026-08-10T14:59:58.568026Z","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":"2026-08-10T14:59:58.574159Z","title":"Mmtu: A massive multi-task table understanding and reasoning benchmark","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.574159Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:d72816b68dd7e4eb05ee2284a607835ad1bf167f2244ee39cec0e445752f5a88","observation_id":"1cc6fb3c-424f-46eb-8b51-0629fc8728ad","resolution":{"observed_at":"2026-08-10T14:59:58.574159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-10T14:59:58.579539Z","title":"Qwen3 technical report","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.579539Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:2f6fd30a2a5b394640d06a87ad18ac600155da39659c7a2e586d5cefb95e83c2","observation_id":"d8cf8a38-e461-499a-8d59-4699d229e4a2","resolution":{"observed_at":"2026-08-10T14:59:58.579539Z","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":"2026-08-10T14:59:58.585768Z","title":"T able F ormer: Robust transformer modeling for table-text encoding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.585768Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:03f3c42ab045b532a460752c2b44aca61174ef4e9ba5c65f11af502a1b36746d","observation_id":"d2c5db91-36f3-4bfe-916c-75c418ebff3e","resolution":{"observed_at":"2026-08-10T14:59:58.585768Z","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":"2026-08-10T14:59:58.591622Z","title":"Table-r1: Inference-time scaling for table reasoning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.591622Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:5a231d2503fc35576f7848e3ce007c7eb03100908db557732373e435762937f5","observation_id":"01bc38b5-44ad-4205-b69c-20442019f37a","resolution":{"observed_at":"2026-08-10T14:59:58.591622Z","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":"2026-08-10T14:59:58.596540Z","title":"T a BERT : Pretraining for joint understanding of textual and tabular data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.596540Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:b95eec0a8eca7fe0565e547c79cc92326b4b92d64fc86f5dd6652a1315ab84ff","observation_id":"d5180eba-2f33-4e16-9743-9cb77185969d","resolution":{"observed_at":"2026-08-10T14:59:58.596540Z","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":"2026-08-10T14:59:58.601747Z","title":"Tablegpt: Towards unifying tables, nature language and commands into one gpt","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.601747Z"},"links":{"cited_paper":"/paper/2307.08674","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:f5b7c85410a937864e112f55997c7decde633e8148df620cde8c813b1934bb3b","observation_id":"ea8540d0-064e-4ab6-91c3-a3967ca26649","resolution":{"observed_at":"2026-08-10T14:59:58.601747Z","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":"2026-08-10T14:59:58.606794Z","title":"T able L lama: Towards open large generalist models for tables","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.606794Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:7115d40f066f9f718fd7f11cb26180538cba888bf307b65cdf68eff2eceac68f","observation_id":"7c70a6b9-f587-4cbf-806b-2ec792b0884b","resolution":{"observed_at":"2026-08-10T14:59:58.606794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19318","last_updated":"2025-02-17T13:45:00Z","snapshot_observed_at":"2026-08-11T05:09:44.584688Z","submitted_at":"2024-03-28T11:21:12Z","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19318","snapshot_observed_at":"2026-08-10T14:59:58.611787Z","title":"Tablellm: Enabling tabular data manipulation by llms in real office usage scenarios","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.611787Z"},"links":{"cited_paper":"/paper/2403.19318","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:fba33e03c0ceecb7ede551057135be0753d0da1ab4e624244491d47bddadc152","observation_id":"578a8150-7809-4646-8674-4b3a0a7e1197","resolution":{"observed_at":"2026-08-10T14:59:58.611787Z","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":"2026-08-10T14:59:59.573303Z","title":"Multimodal table understanding","venue":null,"work_id":"ff206b94-f1b0-4dd3-a52d-ac0123f580ce","year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.618201Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:a23b475f4b9475ee77a0d982e14b5a3cfde3bb56173e2df64b16d4045f318ef6","observation_id":"c954a82d-bd28-4dbb-bae8-9e1c8a0b6025","resolution":{"observed_at":"2026-08-10T14:59:59.578809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T14:59:58.623595Z","title":"L lama F actory: Unified efficient fine-tuning of 100+ language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.623595Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:2a39601bdf054393cfdc4228a37fa9a07a2b4b1f09f88fefebbb149e4b737b5c","observation_id":"d6f0366d-7961-42b6-9b05-8c2238137d35","resolution":{"observed_at":"2026-08-10T14:59:58.623595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.00103","last_updated":"2017-11-09T23:06:14Z","snapshot_observed_at":"2026-08-03T05:45:09.122112Z","submitted_at":"2017-08-31T23:12:15Z","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.00103","snapshot_observed_at":"2026-08-10T14:59:58.629136Z","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.629136Z"},"links":{"cited_paper":"/paper/1709.00103","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:1bf363130f6fe3a1e97be845728dbcf6cba807f8fae1761af1cf9741c95ba3fc","observation_id":"a68c9f11-79b6-4cb5-a7df-8323fb0031c0","resolution":{"observed_at":"2026-08-10T14:59:58.629136Z","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":"2026-08-10T14:59:58.634125Z","title":"Lima: Less is more for alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.634125Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:6ac34ba3d36572405d4bbd976a79c011bf6e926434e917a6bddf44725cf3214e","observation_id":"ec1322b3-c36f-4882-980b-672a3e633931","resolution":{"observed_at":"2026-08-10T14:59:58.634125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07911","last_updated":"2023-11-14T05:13:55Z","snapshot_observed_at":"2026-07-06T16:47:08.877195Z","submitted_at":"2023-11-14T05:13:55Z","title":"Instruction-Following Evaluation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07911","snapshot_observed_at":"2026-08-10T14:59:58.638716Z","title":"Instruction-following evaluation for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.638716Z"},"links":{"cited_paper":"/paper/2311.07911","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:2abc3ed8328bcde52427fbe11a69c12def18ba5e104453611cbc693a50a59da1","observation_id":"1db4ff07-2c9c-4735-8f64-faae5bb1b352","resolution":{"observed_at":"2026-08-10T14:59:58.638716Z","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":"2026-08-10T14:59:58.643660Z","title":"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":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.643660Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:386e13671586e84652d284bc855d0d4404bb85c48f277183c301bbd7d33ecce9","observation_id":"b7814380-3811-46d0-b8e0-6f4e00680d97","resolution":{"observed_at":"2026-08-10T14:59:58.643660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15043","last_updated":"2023-12-20T20:48:57Z","snapshot_observed_at":"2026-08-12T09:06:50.363435Z","submitted_at":"2023-07-27T17:49:12Z","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15043","snapshot_observed_at":"2026-08-10T14:59:58.648529Z","title":"Universal and transferable adversarial attacks on aligned language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.648529Z"},"links":{"cited_paper":"/paper/2307.15043","citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:e8f0a8feaa7aaefb9fc2ad04fd6698f252576bb16a848c9aca0ca20ae9b3302c","observation_id":"8120f81b-9326-490d-9d1a-402af4e00f12","resolution":{"observed_at":"2026-08-10T14:59:58.648529Z","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":"2026-08-10T14:59:58.653313Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.653313Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:88a917e519a40bd0a6d5167e9bda724ccf09b72a5f7fccabb6fb2406315ad2c2","observation_id":"196a251f-30c2-418e-a8df-843dc7a01dea","resolution":{"observed_at":"2026-08-10T14:59:58.653313Z","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":"2026-08-10T14:59:58.658293Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.658293Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:7e0886895d7085dd307089ee688db5d3cae2c20ad84baffa91cbbfacb6399f97","observation_id":"681c4cdb-540b-4e1e-991c-28e4a72e6e95","resolution":{"observed_at":"2026-08-10T14:59:58.658293Z","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":"2026-08-10T14:59:58.663292Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning","version":4},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-10T14:59:58.663292Z"},"links":{"citing_paper":"/paper/2501.14693"},"observation_digest":"sha256:814d288adb0931d3a13b9eea2a2efbe669b2e4562f4a9c2c6ae98bfaa58d4297","observation_id":"8894936b-fb43-40b6-848f-33e94f74306c","resolution":{"observed_at":"2026-08-10T14:59:58.663292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.14693","last_updated":"2025-08-01T18:31:52Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T15:59:52.443966Z","submitted_at":"2025-01-24T18:06:07Z","title":"Rethinking Table Instruction Tuning"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":56,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":60},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 1 inbound Pith citation observation for arXiv:2501.14693."}