{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MHXCB3HKJLB52B4RPV63IPZ425","short_pith_number":"pith:MHXCB3HK","schema_version":"1.0","canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","source":{"kind":"arxiv","id":"2411.06176","version":1},"attestation_state":"computed","paper":{"title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaoqun Liu, Hou Pong Chan, Lidong Bing, Liying Cheng, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, Yew Ken Chia","submitted_at":"2024-11-09T13:30:38Z","abstract_excerpt":"The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are very time-consuming for humans to read thoroughly. Hence, there is an urgent need to develop effective and automated methods to aid humans in this task. In this work, we introduce M-LongDoc, a benchmark of 851 samples, and an automated framework to evaluate the performance of large multimodal models. We further propose a retrieval-aware tuning approach for e"},"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":"2411.06176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"595ac568dfec5393f2023a857a674feac4230c3d6dbea4b1db8a69b2f1083608","abstract_canon_sha256":"be309505cec26675851e3448b7661c1d4bf0b6b8ad579ab222b1eecb06231c05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:42.517297Z","signature_b64":"EbfTS1WlEhgnfFE/5whzIqo3RCeHfEVh94VRrtWcDwgHRmoqxLmDvs99r6mLhTyDotJN11K5n/v1tl6fc2IuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","last_reissued_at":"2026-07-05T09:33:42.516790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:42.516790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaoqun Liu, Hou Pong Chan, Lidong Bing, Liying Cheng, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, Yew Ken Chia","submitted_at":"2024-11-09T13:30:38Z","abstract_excerpt":"The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are very time-consuming for humans to read thoroughly. Hence, there is an urgent need to develop effective and automated methods to aid humans in this task. In this work, we introduce M-LongDoc, a benchmark of 851 samples, and an automated framework to evaluate the performance of large multimodal models. We further propose a retrieval-aware tuning approach for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06176","kind":"arxiv","version":1},"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/2411.06176/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":"2411.06176","created_at":"2026-07-05T09:33:42.516848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06176v1","created_at":"2026-07-05T09:33:42.516848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06176","created_at":"2026-07-05T09:33:42.516848+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHXCB3HKJLB5","created_at":"2026-07-05T09:33:42.516848+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHXCB3HKJLB52B4R","created_at":"2026-07-05T09:33:42.516848+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHXCB3HK","created_at":"2026-07-05T09:33:42.516848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14928","citing_title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24530","citing_title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23813","citing_title":"ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425","json":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425.json","graph_json":"https://pith.science/api/pith-number/MHXCB3HKJLB52B4RPV63IPZ425/graph.json","events_json":"https://pith.science/api/pith-number/MHXCB3HKJLB52B4RPV63IPZ425/events.json","paper":"https://pith.science/paper/MHXCB3HK"},"agent_actions":{"view_html":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425","download_json":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425.json","view_paper":"https://pith.science/paper/MHXCB3HK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06176&json=true","fetch_graph":"https://pith.science/api/pith-number/MHXCB3HKJLB52B4RPV63IPZ425/graph.json","fetch_events":"https://pith.science/api/pith-number/MHXCB3HKJLB52B4RPV63IPZ425/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/action/storage_attestation","attest_author":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/action/author_attestation","sign_citation":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/action/citation_signature","submit_replication":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/action/replication_record"}},"created_at":"2026-07-05T09:33:42.516848+00:00","updated_at":"2026-07-05T09:33:42.516848+00:00"}