{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MES3TZJFLYEWMGGC4WYL6LO2X6","short_pith_number":"pith:MES3TZJF","schema_version":"1.0","canonical_sha256":"6125b9e5255e096618c2e5b0bf2ddabf978b9a53d41f1376f1572a07fa1e35d0","source":{"kind":"arxiv","id":"2410.05261","version":1},"attestation_state":"computed","paper":{"title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jihao Wu, Jiwen Zhang, Minghui Liao, Ya-Qi Yu","submitted_at":"2024-10-07T17:58:35Z","abstract_excerpt":"Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel in both tasks simultaneously. Moreover, previous LVLMs with fine-grained perception cost thousands of tokens per image, making them resource-intensive. We present TextHawk2, a bilingual LVLM featuring efficient fine-grained perception and demonstrating cutting-edge performance across general-purpose, OCR, and grounding tasks with 16 times fewer image tokens. "},"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":"2410.05261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T17:58:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f1fa38c5176ed0749b29ec42c090e6f06fab3596c95511f6e8cc930d0b3a861","abstract_canon_sha256":"271e542b15858d01b3cc8b41824cc1a832194f65f073c8d4d2fcd81f542b2ba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:04.500001Z","signature_b64":"CV0q1oMA3qDIQXe2jw4vG/nZ30G2bElJDflZZoux99L3auPDIXwkxu4GnG/9jxvUa8y5tVYxAHGycak3se0PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6125b9e5255e096618c2e5b0bf2ddabf978b9a53d41f1376f1572a07fa1e35d0","last_reissued_at":"2026-07-05T09:17:04.499472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:04.499472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jihao Wu, Jiwen Zhang, Minghui Liao, Ya-Qi Yu","submitted_at":"2024-10-07T17:58:35Z","abstract_excerpt":"Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel in both tasks simultaneously. Moreover, previous LVLMs with fine-grained perception cost thousands of tokens per image, making them resource-intensive. We present TextHawk2, a bilingual LVLM featuring efficient fine-grained perception and demonstrating cutting-edge performance across general-purpose, OCR, and grounding tasks with 16 times fewer image tokens. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05261","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/2410.05261/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":"2410.05261","created_at":"2026-07-05T09:17:04.499539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05261v1","created_at":"2026-07-05T09:17:04.499539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05261","created_at":"2026-07-05T09:17:04.499539+00:00"},{"alias_kind":"pith_short_12","alias_value":"MES3TZJFLYEW","created_at":"2026-07-05T09:17:04.499539+00:00"},{"alias_kind":"pith_short_16","alias_value":"MES3TZJFLYEWMGGC","created_at":"2026-07-05T09:17:04.499539+00:00"},{"alias_kind":"pith_short_8","alias_value":"MES3TZJF","created_at":"2026-07-05T09:17:04.499539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19307","citing_title":"MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09861","citing_title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13029","citing_title":"Visual Preference Optimization with Rubric Rewards","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":286,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6","json":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6.json","graph_json":"https://pith.science/api/pith-number/MES3TZJFLYEWMGGC4WYL6LO2X6/graph.json","events_json":"https://pith.science/api/pith-number/MES3TZJFLYEWMGGC4WYL6LO2X6/events.json","paper":"https://pith.science/paper/MES3TZJF"},"agent_actions":{"view_html":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6","download_json":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6.json","view_paper":"https://pith.science/paper/MES3TZJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05261&json=true","fetch_graph":"https://pith.science/api/pith-number/MES3TZJFLYEWMGGC4WYL6LO2X6/graph.json","fetch_events":"https://pith.science/api/pith-number/MES3TZJFLYEWMGGC4WYL6LO2X6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6/action/storage_attestation","attest_author":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6/action/author_attestation","sign_citation":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6/action/citation_signature","submit_replication":"https://pith.science/pith/MES3TZJFLYEWMGGC4WYL6LO2X6/action/replication_record"}},"created_at":"2026-07-05T09:17:04.499539+00:00","updated_at":"2026-07-05T09:17:04.499539+00:00"}