{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RGAZL6Y3TXRPHISY3OQZZ65YAL","short_pith_number":"pith:RGAZL6Y3","schema_version":"1.0","canonical_sha256":"898195fb1b9de2f3a258dba19cfbb802d7105d59fe378cde4652ce180712d6bf","source":{"kind":"arxiv","id":"2412.20662","version":3},"attestation_state":"computed","paper":{"title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feiyang Xu, Mingyue Cheng, Qingyang Mao, Xin Li, Yitong Zhou","submitted_at":"2024-12-30T02:40:19Z","abstract_excerpt":"Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. Through in-depth evaluations, we find that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from this, we propose"},"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":"2412.20662","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T02:40:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d86aff7e2f7a1a20b274adaa45d18a8551aaaba93184415a32a177c01465bbe4","abstract_canon_sha256":"882d2403fc3f3636639630f3865bf95e12e2359f6e6d6e6e99882083de2f906f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:23.820224Z","signature_b64":"HagdMaBIvP8XcTGm2fev5EB2uujJ0/CO7rFWJ/V4fQUiye/LA8FSeKk/HOp4Tb+smoFZUGgs+MiQfdiLAGH7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"898195fb1b9de2f3a258dba19cfbb802d7105d59fe378cde4652ce180712d6bf","last_reissued_at":"2026-07-05T11:12:23.819671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:23.819671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feiyang Xu, Mingyue Cheng, Qingyang Mao, Xin Li, Yitong Zhou","submitted_at":"2024-12-30T02:40:19Z","abstract_excerpt":"Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. Through in-depth evaluations, we find that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from this, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20662","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/2412.20662/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":"2412.20662","created_at":"2026-07-05T11:12:23.819732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20662v3","created_at":"2026-07-05T11:12:23.819732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20662","created_at":"2026-07-05T11:12:23.819732+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGAZL6Y3TXRP","created_at":"2026-07-05T11:12:23.819732+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGAZL6Y3TXRPHISY","created_at":"2026-07-05T11:12:23.819732+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGAZL6Y3","created_at":"2026-07-05T11:12:23.819732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31550","citing_title":"Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13041","citing_title":"TableNet A Large-Scale Table Dataset with LLM-Powered Autonomous","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL","json":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL.json","graph_json":"https://pith.science/api/pith-number/RGAZL6Y3TXRPHISY3OQZZ65YAL/graph.json","events_json":"https://pith.science/api/pith-number/RGAZL6Y3TXRPHISY3OQZZ65YAL/events.json","paper":"https://pith.science/paper/RGAZL6Y3"},"agent_actions":{"view_html":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL","download_json":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL.json","view_paper":"https://pith.science/paper/RGAZL6Y3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20662&json=true","fetch_graph":"https://pith.science/api/pith-number/RGAZL6Y3TXRPHISY3OQZZ65YAL/graph.json","fetch_events":"https://pith.science/api/pith-number/RGAZL6Y3TXRPHISY3OQZZ65YAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL/action/storage_attestation","attest_author":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL/action/author_attestation","sign_citation":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL/action/citation_signature","submit_replication":"https://pith.science/pith/RGAZL6Y3TXRPHISY3OQZZ65YAL/action/replication_record"}},"created_at":"2026-07-05T11:12:23.819732+00:00","updated_at":"2026-07-05T11:12:23.819732+00:00"}