{"as_of":"2026-08-09T20:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:55162dd3da632920dfe96c530852d266cc8b44051d58a1f3d9f27ea7a267ffa9","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:47:40.700778Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T09:57:56.204342Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-08-06T21:47:40.700778Z","title":"Tapex: Table pre-training via learning a neural sql executor, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23463","last_updated":"2025-08-04T01:06:29Z","snapshot_observed_at":"2026-08-07T22:43:00.687784Z","submitted_at":"2025-06-30T02:03:23Z","title":"What to Keep and What to Drop: Adaptive Table Filtering Framework","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T21:47:40.700778Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2506.23463"},"observation_digest":"sha256:2dd3a437728a3f4c9dd3d6c8aee2a4783b1c80e56db3aca318e91fae4c070d4e","observation_id":"17ba75ed-0d45-4710-a91e-778e22250caf","resolution":{"observed_at":"2026-08-06T21:47:40.700778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-08-06T20:48:15.279540Z","title":"Tapex: Table pre-training via learning a neural sql executor.arXiv preprint arXiv:2107.07653, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.03018","last_updated":"2025-07-02T13:54:54Z","snapshot_observed_at":"2026-08-09T07:04:34.915775Z","submitted_at":"2025-07-02T13:54:54Z","title":"OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T20:48:15.279540Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2507.03018"},"observation_digest":"sha256:45fca0e3a3ddd3bef4d0f31ef3a6f2919e767301f603db1a960453a97719ac23","observation_id":"50de6d48-024b-4a36-bc2c-675945442484","resolution":{"observed_at":"2026-08-06T20:48:15.279540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-08-06T16:36:51.915513Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12981","last_updated":"2025-07-17T10:33:36Z","snapshot_observed_at":"2026-08-09T05:21:16.774382Z","submitted_at":"2025-07-17T10:33:36Z","title":"MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T16:36:51.915513Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2507.12981"},"observation_digest":"sha256:2d0a11f55ab8f1606606e73e504cb635fcb97035edfd7c088dd1a52b4bf53975","observation_id":"9b4dacb0-5c56-4b9c-92d4-4badf7d016da","resolution":{"observed_at":"2026-08-06T16:36:51.915513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-08-04T23:56:52.567514Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.06278","last_updated":"2026-07-26T14:15:22Z","snapshot_observed_at":"2026-08-09T07:39:46.027693Z","submitted_at":"2025-09-08T02:00:31Z","title":"TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T23:56:52.567514Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2509.06278"},"observation_digest":"sha256:820c8b290e277ee9f2faaaa18ab5833ef6cd2193a9a62193f95c8846119697d8","observation_id":"032466e9-ba86-4c9e-aa3e-529339ba4aca","resolution":{"observed_at":"2026-08-04T23:56:52.567514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2509.17680","last_updated":"2026-05-18T16:40:56Z","snapshot_observed_at":"2026-08-03T10:47:37.519453Z","submitted_at":"2025-09-22T12:25:57Z","title":"When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-21T21:38:09.388808Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2509.17680"},"observation_digest":"sha256:bd0ac98bea6a7a9b0c1cc69fdf18004ae9ced231fa50e692b6fbd632338ee606","observation_id":"c10ea1b3-72f8-4260-bcb3-4af4ecd88852","resolution":{"observed_at":"2026-05-21T21:40:40.872469Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2510.09671","last_updated":"2026-04-18T09:34:28Z","snapshot_observed_at":"2026-08-08T16:30:05.866004Z","submitted_at":"2025-10-08T14:56:03Z","title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T09:17:00.389716Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2510.09671"},"observation_digest":"sha256:f65328e537b3812660cde37068d5a9e205463bd24e19d4e7f7a951b4017cac58","observation_id":"17e83f1c-f9a2-4465-8f38-c9b32c83bac9","resolution":{"observed_at":"2026-05-18T09:21:10.707411Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2605.00199","last_updated":"2026-05-07T14:14:11Z","snapshot_observed_at":"2026-07-06T23:13:38.354733Z","submitted_at":"2026-04-30T20:25:41Z","title":"RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-09T20:26:56.917494Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2605.00199"},"observation_digest":"sha256:376451eda7b78f73efe000763dc882fd257c3f01d15b7ef96d19c4fa1edac6dc","observation_id":"2bc097e8-919f-40ce-8e0f-24f18b2fba65","resolution":{"observed_at":"2026-05-11T15:16:05.278829Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2606.10316","last_updated":"2026-06-09T02:11:16Z","snapshot_observed_at":"2026-07-06T23:49:32.647742Z","submitted_at":"2026-06-09T02:11:16Z","title":"TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T13:26:04.468972Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2606.10316"},"observation_digest":"sha256:07ec964a0693107e9c52efea644a295cccfa0459001dd99028c44f512ead4704","observation_id":"c1bbf099-b7a9-42d3-aa13-3f0a5f7eea73","resolution":{"observed_at":"2026-07-03T05:07:38.935366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2606.11537","last_updated":"2026-06-17T21:27:59Z","snapshot_observed_at":"2026-08-02T18:22:58.933031Z","submitted_at":"2026-06-10T00:45:39Z","title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-06-27T10:17:42.831128Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2606.11537"},"observation_digest":"sha256:4a3c6007aec211dbe86a50cac4043411e9afa4f5e924e9f3ef1adc4bc1eca5bf","observation_id":"50323458-9b57-4ad1-84ce-a501bd525e3f","resolution":{"observed_at":"2026-07-03T09:57:56.205994Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","version":3},"cited_work":{"arxiv_id":"2107.07653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.07653","snapshot_observed_at":"2026-07-03T09:57:56.204342Z","title":"InProceedings of the 4th Table Representation Learning Workshop, pages 217– 228, Vienna, Austria","venue":null,"work_id":"6c2bbb51-5d51-4d93-bcba-4277637a77ad","year":2021},"citing_paper":{"arxiv_id":"2606.29955","last_updated":"2026-06-29T08:33:52Z","snapshot_observed_at":"2026-08-05T13:41:28.044921Z","submitted_at":"2026-06-29T08:33:52Z","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-30T05:36:41.816068Z"},"links":{"cited_paper":"/paper/2107.07653","citing_paper":"/paper/2606.29955"},"observation_digest":"sha256:1e202efebe766f47f7fcc2700626017462eba53b3f42a585c933dbf21eda5008","observation_id":"52b0f627-198b-4eeb-be43-44b74b528deb","resolution":{"observed_at":"2026-06-30T14:04:45.401749Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2107.07653/citation-record","integrity":"/paper/2107.07653/integrity","json":"/paper/2107.07653/citation-record.json","paper":"/paper/2107.07653"},"outbound":[],"paper":{"arxiv_id":"2107.07653","last_updated":"2022-03-14T05:49:08Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T18:50:58.300917Z","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2107.07653."}