{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RDDPVBMFULRAJV7NBJPHFFPHCD","short_pith_number":"pith:RDDPVBMF","schema_version":"1.0","canonical_sha256":"88c6fa8585a2e204d7ed0a5e7295e710f97fd0a93ab005b3e8a2df258d203efd","source":{"kind":"arxiv","id":"2507.15882","version":2},"attestation_state":"computed","paper":{"title":"Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Goeric Huybrechts, Jack FitzGerald, Sai Muralidhar Jayanthi, Srikanth Ronanki, Srinivasan Veeravanallur","submitted_at":"2025-07-18T19:33:15Z","abstract_excerpt":"The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely due to a lack of suitable benchmarks. To address this, we introduce Document Haystack, a comprehensive benchmark designed to evaluate the performance of Vision Language Models (VLMs) on long, visually complex documents. Document Haystack features documents ranging from 5 to 200 pages and strategically inserts pure text or multimodal text+image \"needles\" at v"},"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":"2507.15882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T19:33:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"3a0542c02108681392e968707dc458f6836c5700130ce2840285e531acddf917","abstract_canon_sha256":"5da1440304b58136355acc3ad3084ef5cb95623e23bf0b51b5382224e480dcfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:27.522504Z","signature_b64":"Q/VdZdtXkFHq2HucmnNmv89Tu+PGL0PJPZXC0sdHGFrANh0xkx4HUFEqOs+1oeiCRHtfvkhhGpCndnREePZpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c6fa8585a2e204d7ed0a5e7295e710f97fd0a93ab005b3e8a2df258d203efd","last_reissued_at":"2026-07-05T11:48:27.521994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:27.521994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Goeric Huybrechts, Jack FitzGerald, Sai Muralidhar Jayanthi, Srikanth Ronanki, Srinivasan Veeravanallur","submitted_at":"2025-07-18T19:33:15Z","abstract_excerpt":"The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely due to a lack of suitable benchmarks. To address this, we introduce Document Haystack, a comprehensive benchmark designed to evaluate the performance of Vision Language Models (VLMs) on long, visually complex documents. Document Haystack features documents ranging from 5 to 200 pages and strategically inserts pure text or multimodal text+image \"needles\" at v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15882","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/2507.15882/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":"2507.15882","created_at":"2026-07-05T11:48:27.522052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15882v2","created_at":"2026-07-05T11:48:27.522052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15882","created_at":"2026-07-05T11:48:27.522052+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDDPVBMFULRA","created_at":"2026-07-05T11:48:27.522052+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDDPVBMFULRAJV7N","created_at":"2026-07-05T11:48:27.522052+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDDPVBMF","created_at":"2026-07-05T11:48:27.522052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD","json":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD.json","graph_json":"https://pith.science/api/pith-number/RDDPVBMFULRAJV7NBJPHFFPHCD/graph.json","events_json":"https://pith.science/api/pith-number/RDDPVBMFULRAJV7NBJPHFFPHCD/events.json","paper":"https://pith.science/paper/RDDPVBMF"},"agent_actions":{"view_html":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD","download_json":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD.json","view_paper":"https://pith.science/paper/RDDPVBMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15882&json=true","fetch_graph":"https://pith.science/api/pith-number/RDDPVBMFULRAJV7NBJPHFFPHCD/graph.json","fetch_events":"https://pith.science/api/pith-number/RDDPVBMFULRAJV7NBJPHFFPHCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD/action/storage_attestation","attest_author":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD/action/author_attestation","sign_citation":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD/action/citation_signature","submit_replication":"https://pith.science/pith/RDDPVBMFULRAJV7NBJPHFFPHCD/action/replication_record"}},"created_at":"2026-07-05T11:48:27.522052+00:00","updated_at":"2026-07-05T11:48:27.522052+00:00"}