{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3KHDXAK6OPQY3FAJXAMIK3YBJR","short_pith_number":"pith:3KHDXAK6","schema_version":"1.0","canonical_sha256":"da8e3b815e73e18d9409b818856f014c417276b196bbe327f09e86f6baa2b87b","source":{"kind":"arxiv","id":"2411.02059","version":3},"attestation_state":"computed","paper":{"title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Aofeng Su, Aowen Wang, Chao Ye, Chen Zhou, Gang Chen, Ga Zhang, Guangcheng Zhu, Haobo Wang, Hao Chen, Haokai Xu, Haoxuan Lan, Haoze Li, Jiaming Tian, Jing Yuan, Junbo Zhao, Junlin Zhou, Kaizhe Shou, Liangyu Zha, Lin Long, Liyao Li, Pengzuo Wu, Qingyi Huang, Qi Zhang, Saisai Yang, Tao Zhang, Wentao Ye, Wufang Zhu, Xiang Li, Xiaomeng Hu, Xijun Gu, Xinjie Sun, Yuhang Yang, Zhiqing Xiao","submitted_at":"2024-11-04T13:03:13Z","abstract_excerpt":"The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains.\n  This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise sol"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.02059","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-04T13:03:13Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"b1e9dfd758f722abdd9246f78fe2ccd851b1e3af1e474438d4c20e4da71a4d26","abstract_canon_sha256":"81c93363ebabbbe1b71e9a48820dffe44287574ba69667f6a5ae1add94567f5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:13.453771Z","signature_b64":"zlsx1bbFOyfBsw5MQ1xoO9nIIKxHvTExVWL3ExHHTc6PEGaUB3dlLds9qXcE7j/G8mEuZk5HPikE2TxTcKQMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8e3b815e73e18d9409b818856f014c417276b196bbe327f09e86f6baa2b87b","last_reissued_at":"2026-07-05T09:32:13.453264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:13.453264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Aofeng Su, Aowen Wang, Chao Ye, Chen Zhou, Gang Chen, Ga Zhang, Guangcheng Zhu, Haobo Wang, Hao Chen, Haokai Xu, Haoxuan Lan, Haoze Li, Jiaming Tian, Jing Yuan, Junbo Zhao, Junlin Zhou, Kaizhe Shou, Liangyu Zha, Lin Long, Liyao Li, Pengzuo Wu, Qingyi Huang, Qi Zhang, Saisai Yang, Tao Zhang, Wentao Ye, Wufang Zhu, Xiang Li, Xiaomeng Hu, Xijun Gu, Xinjie Sun, Yuhang Yang, Zhiqing Xiao","submitted_at":"2024-11-04T13:03:13Z","abstract_excerpt":"The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains.\n  This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02059","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.02059/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.02059","created_at":"2026-07-05T09:32:13.453327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02059v3","created_at":"2026-07-05T09:32:13.453327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02059","created_at":"2026-07-05T09:32:13.453327+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KHDXAK6OPQY","created_at":"2026-07-05T09:32:13.453327+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KHDXAK6OPQY3FAJ","created_at":"2026-07-05T09:32:13.453327+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KHDXAK6","created_at":"2026-07-05T09:32:13.453327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06482","citing_title":"Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11537","citing_title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09578","citing_title":"TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09323","citing_title":"TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05382","citing_title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21974","citing_title":"Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20254","citing_title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06806","citing_title":"MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22758","citing_title":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12282","citing_title":"Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17225","citing_title":"A Multi-Agent Approach for Claim Verification from Tabular Data Documents","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR","json":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR.json","graph_json":"https://pith.science/api/pith-number/3KHDXAK6OPQY3FAJXAMIK3YBJR/graph.json","events_json":"https://pith.science/api/pith-number/3KHDXAK6OPQY3FAJXAMIK3YBJR/events.json","paper":"https://pith.science/paper/3KHDXAK6"},"agent_actions":{"view_html":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR","download_json":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR.json","view_paper":"https://pith.science/paper/3KHDXAK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02059&json=true","fetch_graph":"https://pith.science/api/pith-number/3KHDXAK6OPQY3FAJXAMIK3YBJR/graph.json","fetch_events":"https://pith.science/api/pith-number/3KHDXAK6OPQY3FAJXAMIK3YBJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR/action/storage_attestation","attest_author":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR/action/author_attestation","sign_citation":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR/action/citation_signature","submit_replication":"https://pith.science/pith/3KHDXAK6OPQY3FAJXAMIK3YBJR/action/replication_record"}},"created_at":"2026-07-05T09:32:13.453327+00:00","updated_at":"2026-07-05T09:32:13.453327+00:00"}