{"as_of":"2026-08-17T03:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1f4553f6e1e46288568b5b280c011d9e4056362e4664217785793de939a220df","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":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":34,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:08:10.168350Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":4,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","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":"2026-08-12T10:09:45.203352Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19504","last_updated":"2026-06-05T23:48:53Z","snapshot_observed_at":"2026-08-15T16:45:55.373094Z","submitted_at":"2024-11-29T06:48:13Z","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T10:09:45.203352Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2411.19504"},"observation_digest":"sha256:fd65012b64066743c8a703d761fd242fd9a7b68a0014c5a3b71e78edfa829276","observation_id":"cd2023f6-1d86-4e75-982c-1a8fd6574534","resolution":{"observed_at":"2026-08-12T10:09:45.203352Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-12T05:20:05.454496Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00535","last_updated":"2025-05-12T10:24:14Z","snapshot_observed_at":"2026-08-15T12:44:44.609531Z","submitted_at":"2024-11-30T16:58:42Z","title":"FullStack Bench: Evaluating LLMs as Full Stack Coders","version":6},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T05:20:05.454496Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2412.00535"},"observation_digest":"sha256:c5b067845101a5547095fb522c261850d472d90802bc3e24af9ae96926e09627","observation_id":"2b3a5e4f-c510-46aa-892c-90776783d379","resolution":{"observed_at":"2026-08-12T05:20:05.454496Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-11T23:49:05.068638Z","title":"Tablegpt2: A large multimodal model with tabular data integration,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02205","last_updated":"2025-04-07T12:01:15Z","snapshot_observed_at":"2026-08-14T09:26:02.576481Z","submitted_at":"2024-12-03T06:47:15Z","title":"DataLab: A Unified Platform for LLM-Powered Business Intelligence","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:05.068638Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2412.02205"},"observation_digest":"sha256:943c582422a269aef17e504efa0051569faec278bee5c93a685bed24954c354e","observation_id":"bd3cd1d4-a812-4b73-b0da-3683d09814b1","resolution":{"observed_at":"2026-08-11T23:49:05.068638Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-11T20:53:15.305084Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.05210","last_updated":"2024-12-06T17:40:38Z","snapshot_observed_at":"2026-08-15T02:44:11.981036Z","submitted_at":"2024-12-06T17:40:38Z","title":"Evaluating and Aligning CodeLLMs on Human Preference","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T20:53:15.305084Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2412.05210"},"observation_digest":"sha256:2c93ffae35301f8f3ee86445977278a0cbbdf2cddc8ef0ff4024ff7e0f81870d","observation_id":"0e356140-73ad-462b-a639-f74d9c7650fb","resolution":{"observed_at":"2026-08-11T20:53:15.305084Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-10T16:34:40.440365Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13042","last_updated":"2025-02-25T16:41:36Z","snapshot_observed_at":"2026-08-14T14:54:01.091789Z","submitted_at":"2025-01-22T17:44:01Z","title":"Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and Reasoning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T16:34:40.440365Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2501.13042"},"observation_digest":"sha256:447daecfcc4c027a2bf24e3cb1a799870ea5033a64c91f28b243490549e6919c","observation_id":"e3ba6728-7df0-4b30-a88b-224fe1c6a927","resolution":{"observed_at":"2026-08-10T16:34:40.440365Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-13T17:39:07.818259Z","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":"sha256:406ba1e6ec7e9d3e2ddb56a0d8d99cfd4f89500732bec5dda49a66b2ca989b7e","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":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","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":"2026-08-10T14:56:30.909708Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14717","last_updated":"2026-06-09T14:39:39Z","snapshot_observed_at":"2026-08-16T12:21:06.830663Z","submitted_at":"2025-01-24T18:50:26Z","title":"What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T14:56:30.909708Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2501.14717"},"observation_digest":"sha256:7718bc1dd35e339c78a6180ec731aabec5e0c3e9d855c8ba9bdc53e4d147afd2","observation_id":"042ffa3b-2aee-400f-8e7a-8be85550af0d","resolution":{"observed_at":"2026-08-10T14:56:30.909708Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-10T13:39:50.801231Z","title":"arXiv preprint arXiv:2411.02059 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16247","last_updated":"2025-01-27T17:48:48Z","snapshot_observed_at":"2026-08-12T06:57:45.048089Z","submitted_at":"2025-01-27T17:48:48Z","title":"Zero-Shot Decision Tree Construction via Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T13:39:50.801231Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2501.16247"},"observation_digest":"sha256:03f28bcebe6e7fbbd08c9f7d1e8156fab6941327dda6dbb15dd3874b2406ac4b","observation_id":"68980f3f-f440-4dab-a922-599858ec497d","resolution":{"observed_at":"2026-08-10T13:39:50.801231Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-09T19:30:38.568058Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00329","last_updated":"2025-02-01T06:03:55Z","snapshot_observed_at":"2026-08-15T14:17:07.891713Z","submitted_at":"2025-02-01T06:03:55Z","title":"CoddLLM: Empowering Large Language Models for Data Analytics","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T19:30:38.568058Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2502.00329"},"observation_digest":"sha256:585c77feee9d0cc63017bc51ff6c9a28f5add57e8086e071b726ec94f83a6bff","observation_id":"d84bc50f-3376-4380-9b72-59260c21d1c3","resolution":{"observed_at":"2026-08-09T19:30:38.568058Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-15T23:08:10.168350Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.05568","last_updated":"2025-06-11T17:37:10Z","snapshot_observed_at":"2026-08-15T23:00:01.696456Z","submitted_at":"2025-05-08T18:03:43Z","title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:08:10.168350Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2505.05568"},"observation_digest":"sha256:614e2af9163b7455fc5277c56d86842e197c15a445d87537b501f68171b2f79b","observation_id":"626ce1b7-e22d-4121-af29-5344dc056282","resolution":{"observed_at":"2026-08-15T23:08:10.168350Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-07T10:54:03.155456Z","title":"Tablegpt2: A large multimodal model with tabular data integration.arXiv preprint arXiv:2411.02059, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04088","last_updated":"2025-06-04T15:46:30Z","snapshot_observed_at":"2026-08-14T20:54:08.365995Z","submitted_at":"2025-06-04T15:46:30Z","title":"Multimodal Tabular Reasoning with Privileged Structured Information","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T10:54:03.155456Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2506.04088"},"observation_digest":"sha256:d04ae0b0b8ed035cb507eea1c70675db4203c49f7bb23b5d1c3b8e8a83e35a96","observation_id":"f419e710-3852-4772-a43b-728c9e814555","resolution":{"observed_at":"2026-08-07T10:54:03.155456Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-07T06:03:45.412474Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06137","last_updated":"2025-06-06T14:52:19Z","snapshot_observed_at":"2026-08-14T20:42:57.390325Z","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":33,"source":"pdf_text","source_observed_at":"2026-08-07T06:03:45.412474Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2506.06137"},"observation_digest":"sha256:da1b061bfec55482a2ecbf9da57e364588dee687f9b1eecd607e0bb0d36a2a6e","observation_id":"8c323538-ee50-4296-9ba5-97473bca09ff","resolution":{"observed_at":"2026-08-07T06:03:45.412474Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-07T05:01:08.638594Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09003","last_updated":"2025-06-11T03:30:10Z","snapshot_observed_at":"2026-08-15T06:15:19.729789Z","submitted_at":"2025-06-10T17:23:33Z","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T05:01:08.638594Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2506.09003"},"observation_digest":"sha256:2cbc089f74d0e3eebb56153e683273782176f1b57218db70e6662168b6f1cd78","observation_id":"794b2ab7-43e2-47bb-80f0-83534dfd3a17","resolution":{"observed_at":"2026-08-07T05:01:08.638594Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T23:20:03.333517Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18421","last_updated":"2025-07-14T06:09:12Z","snapshot_observed_at":"2026-08-13T21:22:47.097035Z","submitted_at":"2025-06-23T09:02:04Z","title":"TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:20:03.333517Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2506.18421"},"observation_digest":"sha256:54950b6dc57a5429d87b9f1729d13921a19cca32368bc9ee4596a24dbea25791","observation_id":"bdf2d175-1d2b-4802-868a-b97e70998156","resolution":{"observed_at":"2026-08-06T23:20:03.333517Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T20:16:03.928165Z","title":"Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han, and Dongmei Zhang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.03384","last_updated":"2025-07-04T08:32:17Z","snapshot_observed_at":"2026-08-15T16:41:44.868589Z","submitted_at":"2025-07-04T08:32:17Z","title":"LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T20:16:03.928165Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2507.03384"},"observation_digest":"sha256:939a4cc88fab62c15119b24a9e49fc4f8d6c1bd2811aaf03cb6a229339795406","observation_id":"d70a8907-08b1-4094-abbb-82692e3d32cb","resolution":{"observed_at":"2026-08-06T20:16:03.928165Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T17:43:53.884678Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.10088","last_updated":"2025-07-14T09:15:22Z","snapshot_observed_at":"2026-08-16T07:00:31.438247Z","submitted_at":"2025-07-14T09:15:22Z","title":"Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T17:43:53.884678Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2507.10088"},"observation_digest":"sha256:412fb61e4ff5115cf3b7fcbe4936333041f5d9e53f8bbbd1924593edde0f3aec","observation_id":"139d1d4c-88a9-4e1f-a35b-d09d3e809837","resolution":{"observed_at":"2026-08-06T17:43:53.884678Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T16:36:52.274316Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12981","last_updated":"2025-07-17T10:33:36Z","snapshot_observed_at":"2026-08-14T11:44:26.295463Z","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":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:36:52.274316Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2507.12981"},"observation_digest":"sha256:2a77eb9844eb4d97a93c640b5331d5299ccf8a9e134ae5344fc00e5df39ac03d","observation_id":"aff98b8a-ed77-40a7-94b8-bdfbd2da7bbd","resolution":{"observed_at":"2026-08-06T16:36:52.274316Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T14:58:59.456594Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17178","last_updated":"2025-08-29T06:52:20Z","snapshot_observed_at":"2026-08-14T19:48:19.536518Z","submitted_at":"2025-07-23T03:52:24Z","title":"SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T14:58:59.456594Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2507.17178"},"observation_digest":"sha256:48bdff1473fe0bdb45932c44a27b8dafe649c773307e5f5ce35df0baaded0764","observation_id":"0468101c-b92c-4af7-b7e2-3dc0dedfd032","resolution":{"observed_at":"2026-08-06T14:58:59.456594Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-06T11:44:34.069005Z","title":"Tablegpt2: A large multimodal model with tabular data integration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22462","last_updated":"2025-08-01T10:07:37Z","snapshot_observed_at":"2026-08-09T15:17:03.370644Z","submitted_at":"2025-07-30T08:08:48Z","title":"IFEvalCode: Controlled Code Generation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T11:44:34.069005Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2507.22462"},"observation_digest":"sha256:7e40ba0b14a7a44f2eb6d6a68f5b262ad6273af86e300d395a2b752d2f56e771","observation_id":"9a6340c3-009c-4a74-a149-3e50282c6250","resolution":{"observed_at":"2026-08-06T11:44:34.069005Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-05T12:43:34.102906Z","title":"Available from: https://arxiv","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01312","last_updated":"2025-09-01T09:53:01Z","snapshot_observed_at":"2026-08-14T04:12:23.054849Z","submitted_at":"2025-09-01T09:53:01Z","title":"TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T12:43:34.102906Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2509.01312"},"observation_digest":"sha256:ccb558648f63b9e61ebbe6518f55618aef2868bfbf27788512f25845fdddc9d7","observation_id":"9981d427-935c-412d-a650-04b1794bcbc2","resolution":{"observed_at":"2026-08-05T12:43:34.102906Z","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":"2026-08-16T13:03:12.263330Z","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":"2026-08-04T23:56:52.600044Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.06278","last_updated":"2026-07-26T14:15:22Z","snapshot_observed_at":"2026-08-14T20:19:09.298002Z","submitted_at":"2025-09-08T02:00:31Z","title":"TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T23:56:52.600044Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2509.06278"},"observation_digest":"sha256:d1cbb927fa5eac68883943a25b4be8ccef51676bbea33d2226feda631dc876d6","observation_id":"84e1238f-582e-4a82-8140-d7c6c257f014","resolution":{"observed_at":"2026-08-04T23:56:52.600044Z","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":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2509.06806","last_updated":"2026-04-11T15:54:00Z","snapshot_observed_at":"2026-08-12T12:42:13.900717Z","submitted_at":"2025-09-08T15:38:31Z","title":"MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining","version":6},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T18:09:18.157131Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2509.06806"},"observation_digest":"sha256:8269bab60e4b31f1984ac5a24a1c8322d7a6220ca64cc5a2cdc6c660f5e2900d","observation_id":"2b3788f0-0793-4588-96fa-e3fc3d62a133","resolution":{"observed_at":"2026-05-18T18:11:42.775039Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2604.12282","last_updated":"2026-04-14T04:47:21Z","snapshot_observed_at":"2026-08-12T18:26:02.537051Z","submitted_at":"2026-04-14T04:47:21Z","title":"Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-10T15:32:54.053527Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2604.12282"},"observation_digest":"sha256:8b3a48670b0e0367a90ad6a6c3a26fc91c4eb6f52dbeb476ba97a73f6bc9562f","observation_id":"46f8aa50-a9c2-4de7-9595-a1ee76a3b83c","resolution":{"observed_at":"2026-05-10T15:35:33.221526Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2604.17225","last_updated":"2026-04-19T03:13:41Z","snapshot_observed_at":"2026-08-15T04:27:07.694004Z","submitted_at":"2026-04-19T03:13:41Z","title":"A Multi-Agent Approach for Claim Verification from Tabular Data Documents","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T06:31:39.551106Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2604.17225"},"observation_digest":"sha256:f73547f304772bd91c574a22385389466fc3ce52c526ba5d40bec896116e7a27","observation_id":"2c7439d7-65b7-4808-8391-fa78042d5572","resolution":{"observed_at":"2026-05-10T06:36:36.659420Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2604.22758","last_updated":"2026-03-07T12:02:13Z","snapshot_observed_at":"2026-08-11T14:22:25.164891Z","submitted_at":"2026-03-07T12:02:13Z","title":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-15T15:18:54.967483Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2604.22758"},"observation_digest":"sha256:07c9e3bcfd38f53a8d59f35b5b25c1c2484cc59535faf1aacd68512e98d0ba05","observation_id":"f76b0985-0806-41be-af7e-5e08839f9d6f","resolution":{"observed_at":"2026-05-15T15:20:08.220204Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2605.00445","last_updated":"2026-05-09T10:13:39Z","snapshot_observed_at":"2026-08-12T12:28:50.428397Z","submitted_at":"2026-05-01T06:25:55Z","title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-09T19:39:34.361824Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2605.00445"},"observation_digest":"sha256:a258a05ba54adf41e40405d4c3c0a2b39a359f26b3daf1cffbc6c0cfc3c2b640","observation_id":"2ca8e584-c544-4534-bc29-7e38d9f1b3d0","resolution":{"observed_at":"2026-05-11T15:36:06.343470Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2605.00445","last_updated":"2026-05-09T10:13:39Z","snapshot_observed_at":"2026-08-12T12:28:50.428397Z","submitted_at":"2026-05-01T06:25:55Z","title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-12T02:26:05.632437Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2605.00445"},"observation_digest":"sha256:182bbd8d5050a92d8bb07ff00afcddb155ceceeae6360f39bc053c581a348b16","observation_id":"4dbfff7f-7e36-4436-b611-ed936d56635f","resolution":{"observed_at":"2026-05-12T02:26:16.619185Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2605.20254","last_updated":"2026-05-18T12:00:24Z","snapshot_observed_at":"2026-08-13T14:58:34.258198Z","submitted_at":"2026-05-18T12:00:24Z","title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T08:13:40.115115Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2605.20254"},"observation_digest":"sha256:7218421840b839b102d1afc6399aaf8a4ef1d0e1ab09b102fb95c506254d64ba","observation_id":"432bb007-a962-4ea4-9dc5-2df2736b2a37","resolution":{"observed_at":"2026-05-21T08:14:03.197217Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2605.21974","last_updated":"2026-05-21T04:08:42Z","snapshot_observed_at":"2026-08-16T20:14:34.644326Z","submitted_at":"2026-05-21T04:08:42Z","title":"Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-22T06:43:31.886617Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2605.21974"},"observation_digest":"sha256:c19dd9e51d2deeb21c890f6121e713e2233a2eccf5e865985517693caee4bc28","observation_id":"80cd3c3c-e589-43ce-96da-c8077de94e1d","resolution":{"observed_at":"2026-05-22T06:44:41.978882Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2606.05382","last_updated":"2026-06-03T19:35:54Z","snapshot_observed_at":"2026-08-09T19:38:09.332987Z","submitted_at":"2026-06-03T19:35:54Z","title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T06:03:01.785005Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2606.05382"},"observation_digest":"sha256:682fba7e9f38ee834295104e4c432a5eda308b03330faf0b0059b3c78835afe1","observation_id":"366ab853-da90-41d8-981d-6898e67dc9a3","resolution":{"observed_at":"2026-07-02T08:26:48.156507Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2606.09323","last_updated":"2026-06-08T10:39:25Z","snapshot_observed_at":"2026-08-15T04:15:23.975861Z","submitted_at":"2026-06-08T10:39:25Z","title":"TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-06-27T16:48:38.820334Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2606.09323"},"observation_digest":"sha256:471666877c02430b29a9d0c7c1f5cca4d257643000b4f6bd4b16e1f1af5ecdd9","observation_id":"246937a4-d6bc-418d-ae6e-84a1f657a0c5","resolution":{"observed_at":"2026-07-03T01:07:30.416192Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2606.09578","last_updated":"2026-06-08T14:52:46Z","snapshot_observed_at":"2026-08-08T10:39:22.564873Z","submitted_at":"2026-06-08T14:52:46Z","title":"TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T16:47:39.095271Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2606.09578"},"observation_digest":"sha256:00111080248b837abc589e81706b6eb532b52ebbd09ffeb47bb19c5391a417e3","observation_id":"3112295d-b637-4e4c-927d-f88412773401","resolution":{"observed_at":"2026-07-03T01:07:30.633304Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2606.11537","last_updated":"2026-06-17T21:27:59Z","snapshot_observed_at":"2026-08-13T19:05:34.141200Z","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":15,"source":"arxiv_source","source_observed_at":"2026-06-27T10:17:42.831128Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2606.11537"},"observation_digest":"sha256:a3970b06d08e0da21ca29f67825f07225f890be941156b03464762ad35d565c1","observation_id":"3ad5d628-bf7c-4e3d-9ec1-6ffa643daa90","resolution":{"observed_at":"2026-07-03T09:57:56.181680Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","version":3},"cited_work":{"arxiv_id":"2411.02059","doi":"10.48550/arxiv.2411.02059","metadata_source":"pith","pith_arxiv_id":"2411.02059","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2411.02059 , year =","venue":"cs.LG","work_id":"0e72aa0c-9cce-4fe9-8d36-916de00343fe","year":2024},"citing_paper":{"arxiv_id":"2607.06482","last_updated":"2026-07-07T16:43:05Z","snapshot_observed_at":"2026-08-15T18:00:18.380316Z","submitted_at":"2026-07-07T16:43:05Z","title":"Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-08T04:34:05.733204Z"},"links":{"cited_paper":"/paper/2411.02059","citing_paper":"/paper/2607.06482"},"observation_digest":"sha256:243d8be2b37b6a306e05e9b004c0b90bc1a2383c6e5a1530a800d9eab475e91a","observation_id":"fdf73d5a-0aa2-47db-b9ed-f25ddcfd762e","resolution":{"observed_at":"2026-07-08T04:34:31.166695Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.02059/citation-record","integrity":"/paper/2411.02059/integrity","json":"/paper/2411.02059/citation-record.json","paper":"/paper/2411.02059"},"outbound":[],"paper":{"arxiv_id":"2411.02059","last_updated":"2024-11-07T03:32:44Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T13:03:12.263330Z","submitted_at":"2024-11-04T13:03:13Z","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 34 inbound Pith citation observations for arXiv:2411.02059."}