{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GUIW2FNGEZSO3QV5G3P7WW6KHD","short_pith_number":"pith:GUIW2FNG","schema_version":"1.0","canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","source":{"kind":"arxiv","id":"2402.19014","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqiang Jiang, Haoyu Cao, Mingming Gong, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu, Yunfei Wu, Zhihao Guo","submitted_at":"2024-02-29T10:17:27Z","abstract_excerpt":"Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU is specifically concerned with text-rich scenarios containing abundant document elements. Nevertheless, the importance of fine-grained features remains largely unexplored within the community of LVLMs, leading to suboptimal performance in text-rich scenarios. In this paper, we abbreviate it as the fine-grained feature collapse issue. With the aim of filling "},"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":"2402.19014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T10:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"81d273afc34c76bb311a25fbd44d81e84d385f50bff3683976bc1cd180fe19b9","abstract_canon_sha256":"95365a156ac60a804acb0a45d5a16aa93f66e1834cf490689fb559ac6a6291a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:31.266849Z","signature_b64":"d6/PdzoqGbxOLaRypdGdAQjO6J2zts3+BVQdik0+hL1YABERZTePKzzyCBPgHzjoMDypm7yi9HVar3aqg2hDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35116d15a62664edc2bd36dffb5bca38e48f2491fe77cd33d2a2f3f30fcc7412","last_reissued_at":"2026-07-05T07:50:31.266375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:31.266375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqiang Jiang, Haoyu Cao, Mingming Gong, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu, Yunfei Wu, Zhihao Guo","submitted_at":"2024-02-29T10:17:27Z","abstract_excerpt":"Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU is specifically concerned with text-rich scenarios containing abundant document elements. Nevertheless, the importance of fine-grained features remains largely unexplored within the community of LVLMs, leading to suboptimal performance in text-rich scenarios. In this paper, we abbreviate it as the fine-grained feature collapse issue. With the aim of filling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19014","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/2402.19014/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":"2402.19014","created_at":"2026-07-05T07:50:31.266437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19014v1","created_at":"2026-07-05T07:50:31.266437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19014","created_at":"2026-07-05T07:50:31.266437+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUIW2FNGEZSO","created_at":"2026-07-05T07:50:31.266437+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUIW2FNGEZSO3QV5","created_at":"2026-07-05T07:50:31.266437+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUIW2FNG","created_at":"2026-07-05T07:50:31.266437+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/GUIW2FNGEZSO3QV5G3P7WW6KHD","json":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD.json","graph_json":"https://pith.science/api/pith-number/GUIW2FNGEZSO3QV5G3P7WW6KHD/graph.json","events_json":"https://pith.science/api/pith-number/GUIW2FNGEZSO3QV5G3P7WW6KHD/events.json","paper":"https://pith.science/paper/GUIW2FNG"},"agent_actions":{"view_html":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD","download_json":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD.json","view_paper":"https://pith.science/paper/GUIW2FNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19014&json=true","fetch_graph":"https://pith.science/api/pith-number/GUIW2FNGEZSO3QV5G3P7WW6KHD/graph.json","fetch_events":"https://pith.science/api/pith-number/GUIW2FNGEZSO3QV5G3P7WW6KHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/action/storage_attestation","attest_author":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/action/author_attestation","sign_citation":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/action/citation_signature","submit_replication":"https://pith.science/pith/GUIW2FNGEZSO3QV5G3P7WW6KHD/action/replication_record"}},"created_at":"2026-07-05T07:50:31.266437+00:00","updated_at":"2026-07-05T07:50:31.266437+00:00"}