{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GDSYIXQ7KBOXGJCU2GAONP7W4L","short_pith_number":"pith:GDSYIXQ7","schema_version":"1.0","canonical_sha256":"30e5845e1f505d732454d180e6bff6e2e20ea83a9fcae92eda5f24fa62287dc3","source":{"kind":"arxiv","id":"2412.18424","version":3},"attestation_state":"computed","paper":{"title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bo Zheng, Chao Deng, Cheng-Lin Liu, Jiale Yuan, Jian Xu, Jun Song, Peijie Wang, Pi Bu, Xiao-Hui Li, Yuan Gao, Zhong-Zhi Li","submitted_at":"2024-12-24T13:39:32Z","abstract_excerpt":"Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks. However, existing document understanding benchmarks have been limited to handling only a small number of pages and fail to provide a comprehensive analysis of layout elements locating. In this paper, we first define three primary task categories: Long Document Understanding, numerical Reasoning, and cross-element Locating, and then propose a comprehensive benchmark, LongDocURL, integrating above t"},"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":"2412.18424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T13:39:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"75359ea2daeb97476a09df285a90dfb424136230f29641282e1203eefc2dddca","abstract_canon_sha256":"5ac4f19795df5b3f0c0bd3a8c72b8373ea40d3b15ea9f96ad90d7520638349e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:14.262896Z","signature_b64":"WXRvPmOdKhx6DYxKL1kkI9eG4IEMdp9V+KIHRGLB8cNGCfpH8Q8mntbHCln0G3AEKcXwC6pLqC6PJgl3tlQBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e5845e1f505d732454d180e6bff6e2e20ea83a9fcae92eda5f24fa62287dc3","last_reissued_at":"2026-07-05T11:37:14.262373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:14.262373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bo Zheng, Chao Deng, Cheng-Lin Liu, Jiale Yuan, Jian Xu, Jun Song, Peijie Wang, Pi Bu, Xiao-Hui Li, Yuan Gao, Zhong-Zhi Li","submitted_at":"2024-12-24T13:39:32Z","abstract_excerpt":"Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks. However, existing document understanding benchmarks have been limited to handling only a small number of pages and fail to provide a comprehensive analysis of layout elements locating. In this paper, we first define three primary task categories: Long Document Understanding, numerical Reasoning, and cross-element Locating, and then propose a comprehensive benchmark, LongDocURL, integrating above t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18424","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/2412.18424/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":"2412.18424","created_at":"2026-07-05T11:37:14.262434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18424v3","created_at":"2026-07-05T11:37:14.262434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18424","created_at":"2026-07-05T11:37:14.262434+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDSYIXQ7KBOX","created_at":"2026-07-05T11:37:14.262434+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDSYIXQ7KBOXGJCU","created_at":"2026-07-05T11:37:14.262434+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDSYIXQ7","created_at":"2026-07-05T11:37:14.262434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15253","citing_title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","ref_index":2,"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":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12882","citing_title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L","json":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L.json","graph_json":"https://pith.science/api/pith-number/GDSYIXQ7KBOXGJCU2GAONP7W4L/graph.json","events_json":"https://pith.science/api/pith-number/GDSYIXQ7KBOXGJCU2GAONP7W4L/events.json","paper":"https://pith.science/paper/GDSYIXQ7"},"agent_actions":{"view_html":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L","download_json":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L.json","view_paper":"https://pith.science/paper/GDSYIXQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18424&json=true","fetch_graph":"https://pith.science/api/pith-number/GDSYIXQ7KBOXGJCU2GAONP7W4L/graph.json","fetch_events":"https://pith.science/api/pith-number/GDSYIXQ7KBOXGJCU2GAONP7W4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L/action/storage_attestation","attest_author":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L/action/author_attestation","sign_citation":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L/action/citation_signature","submit_replication":"https://pith.science/pith/GDSYIXQ7KBOXGJCU2GAONP7W4L/action/replication_record"}},"created_at":"2026-07-05T11:37:14.262434+00:00","updated_at":"2026-07-05T11:37:14.262434+00:00"}