{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:54VVB7JIDG4GL26CKT3I5LUY54","short_pith_number":"pith:54VVB7JI","schema_version":"1.0","canonical_sha256":"ef2b50fd2819b865ebc254f68eae98ef37794a23cd694709bf6e98620031d5c4","source":{"kind":"arxiv","id":"2406.01326","version":2},"attestation_state":"computed","paper":{"title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Hao Feng, Hao Liu, Houqiang Li, Jingqun Tang, Lei Liao, Qi Liu, Shu Wei, Weichao Zhao, Wengang Zhou, YongJie Ye","submitted_at":"2024-06-03T13:54:05Z","abstract_excerpt":"Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-specific architectures and objectives for individual tasks, resulting in modal isolation and intricate workflows. In this paper, we present a novel large vision-language model, TabPedia, equipped with a concept synergy mechanism. In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts. This unified framework allows TabPedia to sea"},"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":"2406.01326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T13:54:05Z","cross_cats_sorted":[],"title_canon_sha256":"96c19462ded787b700c2753627eac44c64296ab36324a20e34f497e0142ab0de","abstract_canon_sha256":"9580e5ca23583ff9b642dc72581d73abcf37dcfd2e82375923244e5eb9dbc2e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:10.002211Z","signature_b64":"cjUzJwveTDkWh+6AbX08dpG8VXc8j5PKKYy+snnlP6sbwRrkjbgk6VKRJPkmIqb6QxSNl3F5MtzGosDw4MnDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef2b50fd2819b865ebc254f68eae98ef37794a23cd694709bf6e98620031d5c4","last_reissued_at":"2026-07-05T09:19:10.001729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:10.001729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Hao Feng, Hao Liu, Houqiang Li, Jingqun Tang, Lei Liao, Qi Liu, Shu Wei, Weichao Zhao, Wengang Zhou, YongJie Ye","submitted_at":"2024-06-03T13:54:05Z","abstract_excerpt":"Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-specific architectures and objectives for individual tasks, resulting in modal isolation and intricate workflows. In this paper, we present a novel large vision-language model, TabPedia, equipped with a concept synergy mechanism. In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts. This unified framework allows TabPedia to sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01326","kind":"arxiv","version":2},"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/2406.01326/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":"2406.01326","created_at":"2026-07-05T09:19:10.001790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01326v2","created_at":"2026-07-05T09:19:10.001790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01326","created_at":"2026-07-05T09:19:10.001790+00:00"},{"alias_kind":"pith_short_12","alias_value":"54VVB7JIDG4G","created_at":"2026-07-05T09:19:10.001790+00:00"},{"alias_kind":"pith_short_16","alias_value":"54VVB7JIDG4GL26C","created_at":"2026-07-05T09:19:10.001790+00:00"},{"alias_kind":"pith_short_8","alias_value":"54VVB7JI","created_at":"2026-07-05T09:19:10.001790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04272","citing_title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09671","citing_title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54","json":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54.json","graph_json":"https://pith.science/api/pith-number/54VVB7JIDG4GL26CKT3I5LUY54/graph.json","events_json":"https://pith.science/api/pith-number/54VVB7JIDG4GL26CKT3I5LUY54/events.json","paper":"https://pith.science/paper/54VVB7JI"},"agent_actions":{"view_html":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54","download_json":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54.json","view_paper":"https://pith.science/paper/54VVB7JI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01326&json=true","fetch_graph":"https://pith.science/api/pith-number/54VVB7JIDG4GL26CKT3I5LUY54/graph.json","fetch_events":"https://pith.science/api/pith-number/54VVB7JIDG4GL26CKT3I5LUY54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54/action/storage_attestation","attest_author":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54/action/author_attestation","sign_citation":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54/action/citation_signature","submit_replication":"https://pith.science/pith/54VVB7JIDG4GL26CKT3I5LUY54/action/replication_record"}},"created_at":"2026-07-05T09:19:10.001790+00:00","updated_at":"2026-07-05T09:19:10.001790+00:00"}