{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PWHX6VI5WMWJH2JWTHS2ZG2CJD","short_pith_number":"pith:PWHX6VI5","canonical_record":{"source":{"id":"2605.16409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:16:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e922a3c9eb27aa1b909ef9efb03fcf6bc6284cc304c1e5cad3188199c6efe32c","abstract_canon_sha256":"1467b4a6f38c1b810756d2b0e75674d4aa4d1419c47682de77f5010bd08a60a9"},"schema_version":"1.0"},"canonical_sha256":"7d8f7f551db32c93e93699e5ac9b4248e5e0e95c29ad56e993cbe55c58d3dfdc","source":{"kind":"arxiv","id":"2605.16409","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16409","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16409v1","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16409","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"PWHX6VI5WMWJ","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"PWHX6VI5WMWJH2JW","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"PWHX6VI5","created_at":"2026-05-20T00:02:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PWHX6VI5WMWJH2JWTHS2ZG2CJD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:16:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e922a3c9eb27aa1b909ef9efb03fcf6bc6284cc304c1e5cad3188199c6efe32c","abstract_canon_sha256":"1467b4a6f38c1b810756d2b0e75674d4aa4d1419c47682de77f5010bd08a60a9"},"schema_version":"1.0"},"canonical_sha256":"7d8f7f551db32c93e93699e5ac9b4248e5e0e95c29ad56e993cbe55c58d3dfdc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:20.858889Z","signature_b64":"J22LcN8K9sRXJ8EfEexL7BccStSb6n4hydKPPK0OFxseLttvxoBA5O6M0u3tckKY7ijI+geH32DLN5YQNfZEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8f7f551db32c93e93699e5ac9b4248e5e0e95c29ad56e993cbe55c58d3dfdc","last_reissued_at":"2026-05-20T00:02:20.858100Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:20.858100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16409","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":"2026-05-20T00:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KI2/VQ0tMcRt2S70kc9T8ZCxgJ3KnGfbHKhX4bdWLGQTYf/zSVZU4zqSfWZNNSjyZWljw0bpc0pT1TrX5yIeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:12:04.314461Z"},"content_sha256":"7bd1266a4fbbce412a69b4adbef48c833e97656388701086db4753c8772cf405","schema_version":"1.0","event_id":"sha256:7bd1266a4fbbce412a69b4adbef48c833e97656388701086db4753c8772cf405"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PWHX6VI5WMWJH2JWTHS2ZG2CJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haoyu Ren, Qinwu Xu, Xin Liu, Yifan Jiang","submitted_at":"2026-05-13T14:16:39Z","abstract_excerpt":"Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion, and complex typography.\n  We present an OCR-aware multilingual multimodal training framework that combines (i) large-scale synthetic OCR-to-translation data generation, (ii) OCR-aware supervised fine-tuning (SFT) with LoRA adaptation, and (iii) structured visual chain-of-thought (CoT) prompting for reasoning under uncertain visual conditions. Using a LLaMA-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16409","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/2605.16409/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:41:56.569081Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.597685Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4a550e23c85cb324dd490469da8acbc1a8231187a2cc2b108863fa7e4d9489a7"},"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":"2026-05-20T00:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VFepBOtmFe3nsANkFB1P8oxh3GfqjQoF4ywkryL0za3HBQotOPVbWm/c3y+TnaYCbae+N2LvSih8GVJS18yxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:12:04.315252Z"},"content_sha256":"b8748146cc2e47b1e534cf59a17cfe64afde713c3f84945e27d937fe5028d91d","schema_version":"1.0","event_id":"sha256:b8748146cc2e47b1e534cf59a17cfe64afde713c3f84945e27d937fe5028d91d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/bundle.json","state_url":"https://pith.science/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/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":"2026-05-25T11:12:04Z","links":{"resolver":"https://pith.science/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD","bundle":"https://pith.science/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/bundle.json","state":"https://pith.science/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWHX6VI5WMWJH2JWTHS2ZG2CJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PWHX6VI5WMWJH2JWTHS2ZG2CJD","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":"1467b4a6f38c1b810756d2b0e75674d4aa4d1419c47682de77f5010bd08a60a9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:16:39Z","title_canon_sha256":"e922a3c9eb27aa1b909ef9efb03fcf6bc6284cc304c1e5cad3188199c6efe32c"},"schema_version":"1.0","source":{"id":"2605.16409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16409","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16409v1","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16409","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"PWHX6VI5WMWJ","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"PWHX6VI5WMWJH2JW","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"PWHX6VI5","created_at":"2026-05-20T00:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:b8748146cc2e47b1e534cf59a17cfe64afde713c3f84945e27d937fe5028d91d","target":"graph","created_at":"2026-05-20T00:02:20Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:41:56.569081Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.597685Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16409/integrity.json","findings":[],"snapshot_sha256":"4a550e23c85cb324dd490469da8acbc1a8231187a2cc2b108863fa7e4d9489a7","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion, and complex typography.\n  We present an OCR-aware multilingual multimodal training framework that combines (i) large-scale synthetic OCR-to-translation data generation, (ii) OCR-aware supervised fine-tuning (SFT) with LoRA adaptation, and (iii) structured visual chain-of-thought (CoT) prompting for reasoning under uncertain visual conditions. Using a LLaMA-bas","authors_text":"Haoyu Ren, Qinwu Xu, Xin Liu, Yifan Jiang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:16:39Z","title":"Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16409","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":"sha256:7bd1266a4fbbce412a69b4adbef48c833e97656388701086db4753c8772cf405","target":"record","created_at":"2026-05-20T00:02:20Z","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":"1467b4a6f38c1b810756d2b0e75674d4aa4d1419c47682de77f5010bd08a60a9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:16:39Z","title_canon_sha256":"e922a3c9eb27aa1b909ef9efb03fcf6bc6284cc304c1e5cad3188199c6efe32c"},"schema_version":"1.0","source":{"id":"2605.16409","kind":"arxiv","version":1}},"canonical_sha256":"7d8f7f551db32c93e93699e5ac9b4248e5e0e95c29ad56e993cbe55c58d3dfdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d8f7f551db32c93e93699e5ac9b4248e5e0e95c29ad56e993cbe55c58d3dfdc","first_computed_at":"2026-05-20T00:02:20.858100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:20.858100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J22LcN8K9sRXJ8EfEexL7BccStSb6n4hydKPPK0OFxseLttvxoBA5O6M0u3tckKY7ijI+geH32DLN5YQNfZEBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:20.858889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bd1266a4fbbce412a69b4adbef48c833e97656388701086db4753c8772cf405","sha256:b8748146cc2e47b1e534cf59a17cfe64afde713c3f84945e27d937fe5028d91d"],"state_sha256":"adb72c73c3a365011aa37db017067bcb440e3135582bc429400eec8a33e46dff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhdMocjFvDUuwT4wH/dkM+1JCCZWzoRUinEywrQMMQpvHZRSdPSSncWjjNJetucA5eHRYZmFWq+od7Es+jwIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:12:04.319172Z","bundle_sha256":"cac1c32ee1dc00ecc693256d982d1abf12b184b476f52a511458e87aeb96fc2f"}}