{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IA437WH2A7NQJ6IM6UG7K45GO2","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":"593d777839e755ed40b866da4a33d62580ae1a3818c31e959692ea21202816e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T16:26:52Z","title_canon_sha256":"11eb21b4abd48a36e1fb86f4bf7db524e9ac974c1e36edb4f79e793e56df8df0"},"schema_version":"1.0","source":{"id":"2503.22577","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22577","created_at":"2026-07-05T11:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22577v2","created_at":"2026-07-05T11:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22577","created_at":"2026-07-05T11:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"IA437WH2A7NQ","created_at":"2026-07-05T11:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"IA437WH2A7NQJ6IM","created_at":"2026-07-05T11:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"IA437WH2","created_at":"2026-07-05T11:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:1e735ccd60228ecb3d3e7ada917f09cca0c4e5f4a6d8f0fcb30cacf066ee1663","target":"graph","created_at":"2026-07-05T11:05:42Z","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/2503.22577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced Fidelity Loss (IFL) and stems from limited multimodal multilingual training data. To address this, we propose a continuous multilingual integration strategy that injects text-only multilingual data during visual instruction tuning, preserving the language model's original multilingual capabilities. Extensive evaluations demonstrate that our approach significantly","authors_text":"Aitor Gonzalez-Agirre, Carlos Escolano, I\\~naki Lacunza, I\\~nigo Pikabea, Javier Hernando, Marta Villegas, Oriol Pareras","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T16:26:52Z","title":"Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22577","kind":"arxiv","version":2},"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:ec64b526aca4ad4dcbac839ef5bd8faf145971f5a42786a249aa5483f809e0b0","target":"record","created_at":"2026-07-05T11:05:42Z","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":"593d777839e755ed40b866da4a33d62580ae1a3818c31e959692ea21202816e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T16:26:52Z","title_canon_sha256":"11eb21b4abd48a36e1fb86f4bf7db524e9ac974c1e36edb4f79e793e56df8df0"},"schema_version":"1.0","source":{"id":"2503.22577","kind":"arxiv","version":2}},"canonical_sha256":"4039bfd8fa07db04f90cf50df573a676a1b06171fcd4e567b74e0fefca33df4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4039bfd8fa07db04f90cf50df573a676a1b06171fcd4e567b74e0fefca33df4b","first_computed_at":"2026-07-05T11:05:42.710023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:42.710023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DCDEftl4XE0NW2rdOEJGkpi+GNgI83cd65IfL18Ixzd/MMhWB0flfsz1MAfQb3TnBx1s8gcFM2wAeKT7qIgfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:42.710648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22577","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec64b526aca4ad4dcbac839ef5bd8faf145971f5a42786a249aa5483f809e0b0","sha256:1e735ccd60228ecb3d3e7ada917f09cca0c4e5f4a6d8f0fcb30cacf066ee1663"],"state_sha256":"f301f1f82e6af5d98e33b88db261205e9d97e7ee4ebac2a6bda45cc8c69f7451"}