{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XRC2AQVAM5TGE5CTGLR7CBEDKS","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":"debb07c642c3c0b5e526de83fc718966c1894e1b777a4a4929ea92ecea54e77f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-14T09:48:37Z","title_canon_sha256":"7f46a705ab2db43653937ba5fcfb1ddf7a29ecc999d609881200711e2187a432"},"schema_version":"1.0","source":{"id":"2404.09204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09204","created_at":"2026-07-05T08:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09204v1","created_at":"2026-07-05T08:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09204","created_at":"2026-07-05T08:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"XRC2AQVAM5TG","created_at":"2026-07-05T08:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"XRC2AQVAM5TGE5CT","created_at":"2026-07-05T08:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"XRC2AQVA","created_at":"2026-07-05T08:07:46Z"}],"graph_snapshots":[{"event_id":"sha256:dbc7fdd18fc95f89c3d4510d065d711ea746372dfd2639b674dd166acd42dcfc","target":"graph","created_at":"2026-07-05T08:07:46Z","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/2404.09204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information compression. In this paper, we present TextHawk, a MLLM that is specifically designed for document-oriented tasks, while preserving the general capabilities of MLLMs. TextHawk is aimed to explore efficient fine-grained perception by designing four dedicated components. Firstly, a ReSampling and ReArrangement (ReSA) module is proposed to reduce the redundancy i","authors_text":"Jihao Wu, Minghui Liao, Wei Zeng, Xiaoyu Zheng, Ya-Qi Yu, Yongxin Liao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-14T09:48:37Z","title":"TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09204","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":"sha256:3c756aeef34974fe45edd961ec208744f123b02ec5129830fb193e96b1439603","target":"record","created_at":"2026-07-05T08:07:46Z","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":"debb07c642c3c0b5e526de83fc718966c1894e1b777a4a4929ea92ecea54e77f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-14T09:48:37Z","title_canon_sha256":"7f46a705ab2db43653937ba5fcfb1ddf7a29ecc999d609881200711e2187a432"},"schema_version":"1.0","source":{"id":"2404.09204","kind":"arxiv","version":1}},"canonical_sha256":"bc45a042a0676662745332e3f10483548f7258efc4ea4911bc440d8b4cc7b2c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc45a042a0676662745332e3f10483548f7258efc4ea4911bc440d8b4cc7b2c3","first_computed_at":"2026-07-05T08:07:46.742259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:46.742259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4V193Ln+h6/J4TMXmzVGOukzGtDpyZOhMlZd5DrE7vKBWOzKSGjEbrmnxt9z+2YrYsU1hSL6uJUVCs+PdyLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:46.742808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c756aeef34974fe45edd961ec208744f123b02ec5129830fb193e96b1439603","sha256:dbc7fdd18fc95f89c3d4510d065d711ea746372dfd2639b674dd166acd42dcfc"],"state_sha256":"b86daaf6a0486e016d3f3a7fa7ee2fbb8c0b8f05f5e7145572342351d35466c2"}