{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MES3TZJFLYEWMGGC4WYL6LO2X6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"271e542b15858d01b3cc8b41824cc1a832194f65f073c8d4d2fcd81f542b2ba0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T17:58:35Z","title_canon_sha256":"6f1fa38c5176ed0749b29ec42c090e6f06fab3596c95511f6e8cc930d0b3a861"},"schema_version":"1.0","source":{"id":"2410.05261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05261","created_at":"2026-07-05T09:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05261v1","created_at":"2026-07-05T09:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05261","created_at":"2026-07-05T09:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"MES3TZJFLYEW","created_at":"2026-07-05T09:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"MES3TZJFLYEWMGGC","created_at":"2026-07-05T09:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"MES3TZJF","created_at":"2026-07-05T09:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:a1029e3422dbccfc9b0262d046bf3af26852a14281a0f5f3587d60f979525781","target":"graph","created_at":"2026-07-05T09:17:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.05261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Jihao Wu, Jiwen Zhang, Minghui Liao, Ya-Qi Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T17:58:35Z","title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05261","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f61797a57892fcaaefe06f410e3be0623aabfe8fc6ef81220410fea679df563c","target":"record","created_at":"2026-07-05T09:17:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"271e542b15858d01b3cc8b41824cc1a832194f65f073c8d4d2fcd81f542b2ba0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T17:58:35Z","title_canon_sha256":"6f1fa38c5176ed0749b29ec42c090e6f06fab3596c95511f6e8cc930d0b3a861"},"schema_version":"1.0","source":{"id":"2410.05261","kind":"arxiv","version":1}},"canonical_sha256":"6125b9e5255e096618c2e5b0bf2ddabf978b9a53d41f1376f1572a07fa1e35d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6125b9e5255e096618c2e5b0bf2ddabf978b9a53d41f1376f1572a07fa1e35d0","first_computed_at":"2026-07-05T09:17:04.499472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:04.499472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CV0q1oMA3qDIQXe2jw4vG/nZ30G2bElJDflZZoux99L3auPDIXwkxu4GnG/9jxvUa8y5tVYxAHGycak3se0PDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:04.500001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f61797a57892fcaaefe06f410e3be0623aabfe8fc6ef81220410fea679df563c","sha256:a1029e3422dbccfc9b0262d046bf3af26852a14281a0f5f3587d60f979525781"],"state_sha256":"b70c87ad46883c52a1c5f210ee8444b7da158b09909152424cc501429594d900"}