{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4G7VHNFSWSQO24BMGIMFKZMFP5","short_pith_number":"pith:4G7VHNFS","schema_version":"1.0","canonical_sha256":"e1bf53b4b2b4a0ed702c32185565857f4bc9be295e448122523ba3e01c87ec86","source":{"kind":"arxiv","id":"2508.00217","version":1},"attestation_state":"computed","paper":{"title":"Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Wei Xu, Xiaofeng Wu","submitted_at":"2025-07-31T23:41:31Z","abstract_excerpt":"Tables have gained significant attention in large language models (LLMs) and multimodal large language models (MLLMs) due to their complex and flexible structure. Unlike linear text inputs, tables are two-dimensional, encompassing formats that range from well-structured database tables to complex, multi-layered spreadsheets, each with different purposes. This diversity in format and purpose has led to the development of specialized methods and tasks, instead of universal approaches, making navigation of table understanding tasks challenging. To address these challenges, this paper introduces k"},"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":"2508.00217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T23:41:31Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"77684a53faae9527ec15d42a195123638c06689a8231eb1f7c53a8bc4b06753f","abstract_canon_sha256":"87fa51427c5562c5ed43ce8ad3a7671337d147fbb2199d56fa42162eb2d4248a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:51.386908Z","signature_b64":"E3rF4HS7sz0cWTKUD4OqOQOCKFPDawRuAK1gCh/0/aycjUVRP6R3KzvOFCGKjI8df13os1Ecb8ugx11vS8M3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1bf53b4b2b4a0ed702c32185565857f4bc9be295e448122523ba3e01c87ec86","last_reissued_at":"2026-07-05T11:46:51.386373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:51.386373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Wei Xu, Xiaofeng Wu","submitted_at":"2025-07-31T23:41:31Z","abstract_excerpt":"Tables have gained significant attention in large language models (LLMs) and multimodal large language models (MLLMs) due to their complex and flexible structure. Unlike linear text inputs, tables are two-dimensional, encompassing formats that range from well-structured database tables to complex, multi-layered spreadsheets, each with different purposes. This diversity in format and purpose has led to the development of specialized methods and tasks, instead of universal approaches, making navigation of table understanding tasks challenging. To address these challenges, this paper introduces k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00217","kind":"arxiv","version":1},"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/2508.00217/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":"2508.00217","created_at":"2026-07-05T11:46:51.386431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00217v1","created_at":"2026-07-05T11:46:51.386431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00217","created_at":"2026-07-05T11:46:51.386431+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G7VHNFSWSQO","created_at":"2026-07-05T11:46:51.386431+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G7VHNFSWSQO24BM","created_at":"2026-07-05T11:46:51.386431+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G7VHNFS","created_at":"2026-07-05T11:46:51.386431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22938","citing_title":"Large language model-enabled automated data extraction for concrete materials informatics","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22938","citing_title":"Large language model-enabled automated data extraction for concrete materials informatics","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5","json":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5.json","graph_json":"https://pith.science/api/pith-number/4G7VHNFSWSQO24BMGIMFKZMFP5/graph.json","events_json":"https://pith.science/api/pith-number/4G7VHNFSWSQO24BMGIMFKZMFP5/events.json","paper":"https://pith.science/paper/4G7VHNFS"},"agent_actions":{"view_html":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5","download_json":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5.json","view_paper":"https://pith.science/paper/4G7VHNFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00217&json=true","fetch_graph":"https://pith.science/api/pith-number/4G7VHNFSWSQO24BMGIMFKZMFP5/graph.json","fetch_events":"https://pith.science/api/pith-number/4G7VHNFSWSQO24BMGIMFKZMFP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5/action/storage_attestation","attest_author":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5/action/author_attestation","sign_citation":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5/action/citation_signature","submit_replication":"https://pith.science/pith/4G7VHNFSWSQO24BMGIMFKZMFP5/action/replication_record"}},"created_at":"2026-07-05T11:46:51.386431+00:00","updated_at":"2026-07-05T11:46:51.386431+00:00"}