{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WPPN43XZZTOAJUYQHLGLFCINML","short_pith_number":"pith:WPPN43XZ","canonical_record":{"source":{"id":"2502.16586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T14:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"56127b73a9f73e137c84733931bc73e28657923bfa8b47eb7ca9c7b26505eeb5","abstract_canon_sha256":"63f4f5694616483758535658263eb6bc96cb19c9b8d9c7bf4930dc1f16ae3b24"},"schema_version":"1.0"},"canonical_sha256":"b3dede6ef9ccdc04d3103accb2890d62ef2b415a23dec8c117dd381585191ddd","source":{"kind":"arxiv","id":"2502.16586","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16586","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16586v1","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16586","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"WPPN43XZZTOA","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"WPPN43XZZTOAJUYQ","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"WPPN43XZ","created_at":"2026-07-05T10:18:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WPPN43XZZTOAJUYQHLGLFCINML","target":"record","payload":{"canonical_record":{"source":{"id":"2502.16586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T14:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"56127b73a9f73e137c84733931bc73e28657923bfa8b47eb7ca9c7b26505eeb5","abstract_canon_sha256":"63f4f5694616483758535658263eb6bc96cb19c9b8d9c7bf4930dc1f16ae3b24"},"schema_version":"1.0"},"canonical_sha256":"b3dede6ef9ccdc04d3103accb2890d62ef2b415a23dec8c117dd381585191ddd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:55.977088Z","signature_b64":"8fFajMxT2DB8eYfENbMnjyXubHUOkyORLuK3n+iPdpS7Q4WRdurv4WUWv2wpjNKBn1Ev/eefhxVNOXXLDxjiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3dede6ef9ccdc04d3103accb2890d62ef2b415a23dec8c117dd381585191ddd","last_reissued_at":"2026-07-05T10:18:55.976540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:55.976540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.16586","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":"2026-07-05T10:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JE4qBwRpHm6YshgH6ZbALlaLdTQdg7DsUY0QU9dg2GSg0uNJby0F0pDKavz0Qm7NHKtxYXj3bIPQ/dFxk+GkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:43:40.683506Z"},"content_sha256":"49b5078cb46ffbb0869d3be2cc1e14dc0ab10a5283a07fed36ac8f7ace23c7af","schema_version":"1.0","event_id":"sha256:49b5078cb46ffbb0869d3be2cc1e14dc0ab10a5283a07fed36ac8f7ace23c7af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WPPN43XZZTOAJUYQHLGLFCINML","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boming Chen, Chen Duan, Hao Sun, Jiayao Ma, Junfeng Luo, Kai Zhou, Pei Fu, Qianyi Jiang, Tongkun Guan, Zhentao Guo, Zining Wang","submitted_at":"2025-02-23T14:24:51Z","abstract_excerpt":"The recent emergence of Multi-modal Large Language Models (MLLMs) has introduced a new dimension to the Text-rich Image Understanding (TIU) field, with models demonstrating impressive and inspiring performance. However, their rapid evolution and widespread adoption have made it increasingly challenging to keep up with the latest advancements. To address this, we present a systematic and comprehensive survey to facilitate further research on TIU MLLMs. Initially, we outline the timeline, architecture, and pipeline of nearly all TIU MLLMs. Then, we review the performance of selected models on ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16586","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/2502.16586/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":"2026-07-05T10:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4gD5L4QAppDjCxSNZF3CQTIIfWay/w/h2wj4wiw7t9PzPcWTF4e1CdmocHd/rcmsK8Vc8Lv813VdWYzffoCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:43:40.684454Z"},"content_sha256":"9f8eb8c05a30883fd4766378af0fa13a796e1ab48a8ac2c0afdf14154f9d0080","schema_version":"1.0","event_id":"sha256:9f8eb8c05a30883fd4766378af0fa13a796e1ab48a8ac2c0afdf14154f9d0080"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WPPN43XZZTOAJUYQHLGLFCINML/bundle.json","state_url":"https://pith.science/pith/WPPN43XZZTOAJUYQHLGLFCINML/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WPPN43XZZTOAJUYQHLGLFCINML/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":"2026-08-10T12:43:40Z","links":{"resolver":"https://pith.science/pith/WPPN43XZZTOAJUYQHLGLFCINML","bundle":"https://pith.science/pith/WPPN43XZZTOAJUYQHLGLFCINML/bundle.json","state":"https://pith.science/pith/WPPN43XZZTOAJUYQHLGLFCINML/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WPPN43XZZTOAJUYQHLGLFCINML/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WPPN43XZZTOAJUYQHLGLFCINML","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":"63f4f5694616483758535658263eb6bc96cb19c9b8d9c7bf4930dc1f16ae3b24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T14:24:51Z","title_canon_sha256":"56127b73a9f73e137c84733931bc73e28657923bfa8b47eb7ca9c7b26505eeb5"},"schema_version":"1.0","source":{"id":"2502.16586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16586","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16586v1","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16586","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"WPPN43XZZTOA","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"WPPN43XZZTOAJUYQ","created_at":"2026-07-05T10:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"WPPN43XZ","created_at":"2026-07-05T10:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:9f8eb8c05a30883fd4766378af0fa13a796e1ab48a8ac2c0afdf14154f9d0080","target":"graph","created_at":"2026-07-05T10:18:55Z","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/2502.16586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent emergence of Multi-modal Large Language Models (MLLMs) has introduced a new dimension to the Text-rich Image Understanding (TIU) field, with models demonstrating impressive and inspiring performance. However, their rapid evolution and widespread adoption have made it increasingly challenging to keep up with the latest advancements. To address this, we present a systematic and comprehensive survey to facilitate further research on TIU MLLMs. Initially, we outline the timeline, architecture, and pipeline of nearly all TIU MLLMs. Then, we review the performance of selected models on ma","authors_text":"Boming Chen, Chen Duan, Hao Sun, Jiayao Ma, Junfeng Luo, Kai Zhou, Pei Fu, Qianyi Jiang, Tongkun Guan, Zhentao Guo, Zining Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T14:24:51Z","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16586","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":"sha256:49b5078cb46ffbb0869d3be2cc1e14dc0ab10a5283a07fed36ac8f7ace23c7af","target":"record","created_at":"2026-07-05T10:18:55Z","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":"63f4f5694616483758535658263eb6bc96cb19c9b8d9c7bf4930dc1f16ae3b24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T14:24:51Z","title_canon_sha256":"56127b73a9f73e137c84733931bc73e28657923bfa8b47eb7ca9c7b26505eeb5"},"schema_version":"1.0","source":{"id":"2502.16586","kind":"arxiv","version":1}},"canonical_sha256":"b3dede6ef9ccdc04d3103accb2890d62ef2b415a23dec8c117dd381585191ddd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3dede6ef9ccdc04d3103accb2890d62ef2b415a23dec8c117dd381585191ddd","first_computed_at":"2026-07-05T10:18:55.976540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:55.976540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8fFajMxT2DB8eYfENbMnjyXubHUOkyORLuK3n+iPdpS7Q4WRdurv4WUWv2wpjNKBn1Ev/eefhxVNOXXLDxjiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:55.977088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49b5078cb46ffbb0869d3be2cc1e14dc0ab10a5283a07fed36ac8f7ace23c7af","sha256:9f8eb8c05a30883fd4766378af0fa13a796e1ab48a8ac2c0afdf14154f9d0080"],"state_sha256":"47768e7183ff2200b8a1da967dbddd62b5c1441fea518a61efcaf127fdbbced3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnKceq9jWULX+c4h3ywViTMqmA99RTln90k+u1blHLm3i97UGgcR/Uz522jNGFVn7wLzcL4TBlTOyb1QnLg6Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:43:40.690868Z","bundle_sha256":"1271774d53772babfdb9cc33589fecf816a2bf614a53a7fd90d664782fb687cb"}}