{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y5WVQSNYO3FYRBO3OJTQI26I6Y","short_pith_number":"pith:Y5WVQSNY","canonical_record":{"source":{"id":"2404.09797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"a1d009e7e9fd99a0c21133555cdf02865037c8a9353969e6ddbd53bdfbaa28d9","abstract_canon_sha256":"e558a2cf7efeda1727fcc44cb3a677603a0507ba6247957e7888d24b71a0b904"},"schema_version":"1.0"},"canonical_sha256":"c76d5849b876cb8885db7267046bc8f63bc0e94458cc2c95e7c54193e7e90ad0","source":{"kind":"arxiv","id":"2404.09797","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09797","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09797v1","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09797","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"Y5WVQSNYO3FY","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_16","alias_value":"Y5WVQSNYO3FYRBO3","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_8","alias_value":"Y5WVQSNY","created_at":"2026-07-05T08:08:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y5WVQSNYO3FYRBO3OJTQI26I6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"a1d009e7e9fd99a0c21133555cdf02865037c8a9353969e6ddbd53bdfbaa28d9","abstract_canon_sha256":"e558a2cf7efeda1727fcc44cb3a677603a0507ba6247957e7888d24b71a0b904"},"schema_version":"1.0"},"canonical_sha256":"c76d5849b876cb8885db7267046bc8f63bc0e94458cc2c95e7c54193e7e90ad0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:11.762588Z","signature_b64":"+UR1ibI584ux/m1FgQCshNZehmKbVnhmFLsrG9Y3b3BkRJhIinZfm3b12yShMni55+8O3VnCqAdLaDoP1GO0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c76d5849b876cb8885db7267046bc8f63bc0e94458cc2c95e7c54193e7e90ad0","last_reissued_at":"2026-07-05T08:08:11.762133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:11.762133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09797","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:08:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BtaiV8CcbvjVFHkHSD0StgUQsQKgxwNHp2FARMmiJlrdKw6jqTkQiBFbxnracMnW/wIGa3trcAEnvP41ywpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:15:50.748136Z"},"content_sha256":"15e594b5aa0491cf37a487a26a1015f5b1a8213f5bac82a374798f80b4c0cb56","schema_version":"1.0","event_id":"sha256:15e594b5aa0491cf37a487a26a1015f5b1a8213f5bac82a374798f80b4c0cb56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y5WVQSNYO3FYRBO3OJTQI26I6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bozhi Luan, Hao Feng, Hong Chen, Houqiang Li, Wengang Zhou, Yonghui Wang","submitted_at":"2024-04-15T13:54:35Z","abstract_excerpt":"The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images, challenges persist in fully leveraging the potential of LMMs, and existing methods struggle with effectively processing high-resolution images. In this work, we propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding. TextCoT utilizes the captioning ability of LMMs to grasp the global context of the image and the grounding capability to examine local textual regions. This allows for the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09797","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/2404.09797/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:08:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/6RqCTEYYsFAGGt6Ow8gXeDFfxD692DQRQwzLGex4KVnLvBpPXEX1GBJgrTE+pIBtcirr0eo2Ng5FwtFDlEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:15:50.748628Z"},"content_sha256":"aa0ac1b7033ee28cb27c90d8c90cd661fec49c7b7716ea285240c984169d2fdf","schema_version":"1.0","event_id":"sha256:aa0ac1b7033ee28cb27c90d8c90cd661fec49c7b7716ea285240c984169d2fdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/bundle.json","state_url":"https://pith.science/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T02:15:50Z","links":{"resolver":"https://pith.science/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y","bundle":"https://pith.science/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/bundle.json","state":"https://pith.science/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5WVQSNYO3FYRBO3OJTQI26I6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5WVQSNYO3FYRBO3OJTQI26I6Y","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":"e558a2cf7efeda1727fcc44cb3a677603a0507ba6247957e7888d24b71a0b904","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:54:35Z","title_canon_sha256":"a1d009e7e9fd99a0c21133555cdf02865037c8a9353969e6ddbd53bdfbaa28d9"},"schema_version":"1.0","source":{"id":"2404.09797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09797","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09797v1","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09797","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"Y5WVQSNYO3FY","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_16","alias_value":"Y5WVQSNYO3FYRBO3","created_at":"2026-07-05T08:08:11Z"},{"alias_kind":"pith_short_8","alias_value":"Y5WVQSNY","created_at":"2026-07-05T08:08:11Z"}],"graph_snapshots":[{"event_id":"sha256:aa0ac1b7033ee28cb27c90d8c90cd661fec49c7b7716ea285240c984169d2fdf","target":"graph","created_at":"2026-07-05T08:08:11Z","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/2404.09797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images, challenges persist in fully leveraging the potential of LMMs, and existing methods struggle with effectively processing high-resolution images. In this work, we propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding. TextCoT utilizes the captioning ability of LMMs to grasp the global context of the image and the grounding capability to examine local textual regions. This allows for the ","authors_text":"Bozhi Luan, Hao Feng, Hong Chen, Houqiang Li, Wengang Zhou, Yonghui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:54:35Z","title":"TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09797","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":"sha256:15e594b5aa0491cf37a487a26a1015f5b1a8213f5bac82a374798f80b4c0cb56","target":"record","created_at":"2026-07-05T08:08:11Z","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":"e558a2cf7efeda1727fcc44cb3a677603a0507ba6247957e7888d24b71a0b904","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:54:35Z","title_canon_sha256":"a1d009e7e9fd99a0c21133555cdf02865037c8a9353969e6ddbd53bdfbaa28d9"},"schema_version":"1.0","source":{"id":"2404.09797","kind":"arxiv","version":1}},"canonical_sha256":"c76d5849b876cb8885db7267046bc8f63bc0e94458cc2c95e7c54193e7e90ad0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c76d5849b876cb8885db7267046bc8f63bc0e94458cc2c95e7c54193e7e90ad0","first_computed_at":"2026-07-05T08:08:11.762133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:11.762133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+UR1ibI584ux/m1FgQCshNZehmKbVnhmFLsrG9Y3b3BkRJhIinZfm3b12yShMni55+8O3VnCqAdLaDoP1GO0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:11.762588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15e594b5aa0491cf37a487a26a1015f5b1a8213f5bac82a374798f80b4c0cb56","sha256:aa0ac1b7033ee28cb27c90d8c90cd661fec49c7b7716ea285240c984169d2fdf"],"state_sha256":"8523dd8258113a55522f503e8c7da7121d8d001897d49ecc96b600400b58a28e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2A4AEQWMJW0erMQ7PSQDjQr6cnzNnk1zGQIHlLb2M30cAv00qH2I6B2PZhZtRsWBoCKaCl44vst9rbWI3xtlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:15:50.753616Z","bundle_sha256":"1b9c0fd69e67be76de2a008eb434eee3960ea8c015a86d37d5f2cff98b15c0d7"}}