{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2MSP2DJNZ2B5VA33RIVJXA2O45","short_pith_number":"pith:2MSP2DJN","canonical_record":{"source":{"id":"2507.08309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T05:02:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fbc45aef23da68c8e399b655c8bfd82cea0fe47ace1706a010234980f109b47a","abstract_canon_sha256":"6a5be4e43e2612ef4fb084d60d1079c8e93756d463491fd5cf19547e296f98d1"},"schema_version":"1.0"},"canonical_sha256":"d324fd0d2dce83da837b8a2a9b834ee74bc2f831f79b4ec24aa5ca0b060696e3","source":{"kind":"arxiv","id":"2507.08309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08309","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08309v1","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08309","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_12","alias_value":"2MSP2DJNZ2B5","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_16","alias_value":"2MSP2DJNZ2B5VA33","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_8","alias_value":"2MSP2DJN","created_at":"2026-07-05T11:35:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2MSP2DJNZ2B5VA33RIVJXA2O45","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T05:02:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fbc45aef23da68c8e399b655c8bfd82cea0fe47ace1706a010234980f109b47a","abstract_canon_sha256":"6a5be4e43e2612ef4fb084d60d1079c8e93756d463491fd5cf19547e296f98d1"},"schema_version":"1.0"},"canonical_sha256":"d324fd0d2dce83da837b8a2a9b834ee74bc2f831f79b4ec24aa5ca0b060696e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:21.120343Z","signature_b64":"IaQgssuLNLMIIdBvm2dbgYMf9A8H2Ub9eemGpUpg9g5S/PNqi37XHdquzIpvuvtU1YSjiXjT8Dtr3/DsgHNeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d324fd0d2dce83da837b8a2a9b834ee74bc2f831f79b4ec24aa5ca0b060696e3","last_reissued_at":"2026-07-05T11:35:21.119848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:21.119848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08309","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":"2026-07-05T11:35:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJHkYiy/sIrDzs3iEmZZUwTXyrALYBEoIxqah05gjSYsJGDShll+ovDrN7kZbYT2g8iuXXK+Oa6e5u+em1yGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:57:34.902055Z"},"content_sha256":"6f9c21af71cbf04870c8f25e6e67cfb6f5bb4ef87aed9b4e1b9ae685a92a36e6","schema_version":"1.0","event_id":"sha256:6f9c21af71cbf04870c8f25e6e67cfb6f5bb4ef87aed9b4e1b9ae685a92a36e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2MSP2DJNZ2B5VA33RIVJXA2O45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Lu Xiang, Yang Zhao, Yaping Zhang, Yupu Liang, Yu Zhou, Zhiyang Zhang, Zhiyuan Chen","submitted_at":"2025-07-11T05:02:06Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model's existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08309","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/2507.08309/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":"2026-07-05T11:35:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sNDW12RukEnQkmPm7Im9+uvPTvYD02CThLBk3RCRmQHuapnMBj4cvw5Vzu+rUDrwRZ/0jfKRGFQI89UK3coCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:57:34.902565Z"},"content_sha256":"0b492c769003943c415f3c93a5bd3fc256ef2b10791dff68cf90a19d563ba1dc","schema_version":"1.0","event_id":"sha256:0b492c769003943c415f3c93a5bd3fc256ef2b10791dff68cf90a19d563ba1dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/bundle.json","state_url":"https://pith.science/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/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":"2026-08-04T04:57:34Z","links":{"resolver":"https://pith.science/pith/2MSP2DJNZ2B5VA33RIVJXA2O45","bundle":"https://pith.science/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/bundle.json","state":"https://pith.science/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MSP2DJNZ2B5VA33RIVJXA2O45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2MSP2DJNZ2B5VA33RIVJXA2O45","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":"6a5be4e43e2612ef4fb084d60d1079c8e93756d463491fd5cf19547e296f98d1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T05:02:06Z","title_canon_sha256":"fbc45aef23da68c8e399b655c8bfd82cea0fe47ace1706a010234980f109b47a"},"schema_version":"1.0","source":{"id":"2507.08309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08309","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08309v1","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08309","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_12","alias_value":"2MSP2DJNZ2B5","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_16","alias_value":"2MSP2DJNZ2B5VA33","created_at":"2026-07-05T11:35:21Z"},{"alias_kind":"pith_short_8","alias_value":"2MSP2DJN","created_at":"2026-07-05T11:35:21Z"}],"graph_snapshots":[{"event_id":"sha256:0b492c769003943c415f3c93a5bd3fc256ef2b10791dff68cf90a19d563ba1dc","target":"graph","created_at":"2026-07-05T11:35:21Z","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/2507.08309/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 strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model's existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR p","authors_text":"Chengqing Zong, Lu Xiang, Yang Zhao, Yaping Zhang, Yupu Liang, Yu Zhou, Zhiyang Zhang, Zhiyuan Chen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T05:02:06Z","title":"Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08309","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":"sha256:6f9c21af71cbf04870c8f25e6e67cfb6f5bb4ef87aed9b4e1b9ae685a92a36e6","target":"record","created_at":"2026-07-05T11:35:21Z","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":"6a5be4e43e2612ef4fb084d60d1079c8e93756d463491fd5cf19547e296f98d1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T05:02:06Z","title_canon_sha256":"fbc45aef23da68c8e399b655c8bfd82cea0fe47ace1706a010234980f109b47a"},"schema_version":"1.0","source":{"id":"2507.08309","kind":"arxiv","version":1}},"canonical_sha256":"d324fd0d2dce83da837b8a2a9b834ee74bc2f831f79b4ec24aa5ca0b060696e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d324fd0d2dce83da837b8a2a9b834ee74bc2f831f79b4ec24aa5ca0b060696e3","first_computed_at":"2026-07-05T11:35:21.119848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:21.119848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IaQgssuLNLMIIdBvm2dbgYMf9A8H2Ub9eemGpUpg9g5S/PNqi37XHdquzIpvuvtU1YSjiXjT8Dtr3/DsgHNeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:21.120343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f9c21af71cbf04870c8f25e6e67cfb6f5bb4ef87aed9b4e1b9ae685a92a36e6","sha256:0b492c769003943c415f3c93a5bd3fc256ef2b10791dff68cf90a19d563ba1dc"],"state_sha256":"bb075c9f33542342ede7cb8acc42724bb51a5c8110bb4a417b295fd322553d0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cinZkm1ooKHBIoQYXcB5MLFMy+ySYmOHuxI5f2T+EZ2AaZOZA0TaQa2NHb/Hx1B+DBWRGr5qfny002C7FH6fBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:57:34.906555Z","bundle_sha256":"f88c34fb8149ec592bf550f5fa34df1e6b6a92d17ecb7e172db28cd2b95539a5"}}