{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X7XQ7B2XIZTKEJZEF5XT46XPDH","short_pith_number":"pith:X7XQ7B2X","schema_version":"1.0","canonical_sha256":"bfef0f87574666a227242f6f3e7aef19d8056e78d4489e0ebad5d23275e356e4","source":{"kind":"arxiv","id":"2411.16740","version":3},"attestation_state":"computed","paper":{"title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Dannong Xu, Jun Chen, Junjie Fei, Mohamed Elhoseiny","submitted_at":"2024-11-23T18:14:42Z","abstract_excerpt":"Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning over a large number of images. Existing benchmarks for multi-image question-answering are limited in scope, each question is paired with only up to 30 images, which does not fully capture the demands of large-scale retrieval tasks encountered in the real-world usages. To reduce these gaps, we introduce two document haystack benchmarks, dubbed DocHaystack and InfoHaystack, designed to evaluate LMM performance on large"},"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":"2411.16740","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T18:14:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5eed86b48b3c1d6f92cb9f9ebd47f3b957e06353b2bc7c578ae43eb0e521c04a","abstract_canon_sha256":"e766ac7c374538d5223fc396accdf525d74a50c34c311d1bc21f00086fa88192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:16.654198Z","signature_b64":"fP1wSwCxAls7HTpgMKZ4ZL9nP16grlGArjNz9WEeGDZ/nv0QeIILVp5wLDw3MRa7WcuWy9KejaeuM/q8Bu0OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfef0f87574666a227242f6f3e7aef19d8056e78d4489e0ebad5d23275e356e4","last_reissued_at":"2026-07-05T09:45:16.653700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:16.653700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Dannong Xu, Jun Chen, Junjie Fei, Mohamed Elhoseiny","submitted_at":"2024-11-23T18:14:42Z","abstract_excerpt":"Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning over a large number of images. Existing benchmarks for multi-image question-answering are limited in scope, each question is paired with only up to 30 images, which does not fully capture the demands of large-scale retrieval tasks encountered in the real-world usages. To reduce these gaps, we introduce two document haystack benchmarks, dubbed DocHaystack and InfoHaystack, designed to evaluate LMM performance on large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16740","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/2411.16740/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":"2411.16740","created_at":"2026-07-05T09:45:16.653760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16740v3","created_at":"2026-07-05T09:45:16.653760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16740","created_at":"2026-07-05T09:45:16.653760+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7XQ7B2XIZTK","created_at":"2026-07-05T09:45:16.653760+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7XQ7B2XIZTKEJZE","created_at":"2026-07-05T09:45:16.653760+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7XQ7B2X","created_at":"2026-07-05T09:45:16.653760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20869","citing_title":"Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH","json":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH.json","graph_json":"https://pith.science/api/pith-number/X7XQ7B2XIZTKEJZEF5XT46XPDH/graph.json","events_json":"https://pith.science/api/pith-number/X7XQ7B2XIZTKEJZEF5XT46XPDH/events.json","paper":"https://pith.science/paper/X7XQ7B2X"},"agent_actions":{"view_html":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH","download_json":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH.json","view_paper":"https://pith.science/paper/X7XQ7B2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16740&json=true","fetch_graph":"https://pith.science/api/pith-number/X7XQ7B2XIZTKEJZEF5XT46XPDH/graph.json","fetch_events":"https://pith.science/api/pith-number/X7XQ7B2XIZTKEJZEF5XT46XPDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH/action/storage_attestation","attest_author":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH/action/author_attestation","sign_citation":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH/action/citation_signature","submit_replication":"https://pith.science/pith/X7XQ7B2XIZTKEJZEF5XT46XPDH/action/replication_record"}},"created_at":"2026-07-05T09:45:16.653760+00:00","updated_at":"2026-07-05T09:45:16.653760+00:00"}