{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7YLAPUHDLAG3Y5R2BG3ZIQAEFY","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":"3a1556bf51fb9166682c11b905f319df3c922c380bc23f4a6949962df92fb65f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:06:15Z","title_canon_sha256":"52e26c1e6f2a8946e3468b678e7f9bf7fe9955e8ec8777dd896ae009e61f9927"},"schema_version":"1.0","source":{"id":"2605.29476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29476","created_at":"2026-05-29T01:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29476v1","created_at":"2026-05-29T01:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29476","created_at":"2026-05-29T01:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"7YLAPUHDLAG3","created_at":"2026-05-29T01:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"7YLAPUHDLAG3Y5R2","created_at":"2026-05-29T01:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"7YLAPUHD","created_at":"2026-05-29T01:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:01777c2ed6d2d4d9d136c63fcdf52ef288f31045064673ad865ed61ab03003e7","target":"graph","created_at":"2026-05-29T01:05:41Z","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/2605.29476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents a comparative evaluation of machine translation systems applied to images containing textual information, a task that lies at the intersection of computer vision and natural language processing. The study compares three main paradigms: modular pipelines that separate text detection, recognition, and translation; multi-modal large language models (MLLMs) capable of processing both image and text jointly; and an end-to-end model, Translatotron-V, which directly generates translated images. The modular systems employ state-of-the-art OCR (docTR) combined with multilingual LLMs ","authors_text":"Blai Puchol, Francisco Casacuberta, Miguel Domingo, Sergio G\\'omez Gonz\\'alez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:06:15Z","title":"Comparative Evaluation of Machine Translation Systems on Images with Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29476","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":"sha256:21acfc01384f6fa792fe66c1b937efa470939cc3890f9aa831c147d7b92b23b4","target":"record","created_at":"2026-05-29T01:05:41Z","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":"3a1556bf51fb9166682c11b905f319df3c922c380bc23f4a6949962df92fb65f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:06:15Z","title_canon_sha256":"52e26c1e6f2a8946e3468b678e7f9bf7fe9955e8ec8777dd896ae009e61f9927"},"schema_version":"1.0","source":{"id":"2605.29476","kind":"arxiv","version":1}},"canonical_sha256":"fe1607d0e3580dbc763a09b79440042e268d9d2d7bf3ffc0305fc3eca4395778","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe1607d0e3580dbc763a09b79440042e268d9d2d7bf3ffc0305fc3eca4395778","first_computed_at":"2026-05-29T01:05:41.580887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:41.580887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HdZnQavxkZUuGMaUuImH8TUc2SblusVkakQxVllgBtM2H+WI4d1VKN7UTkh9Gx76hmc+eojsPJYTpGZaso+JCA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:41.581564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21acfc01384f6fa792fe66c1b937efa470939cc3890f9aa831c147d7b92b23b4","sha256:01777c2ed6d2d4d9d136c63fcdf52ef288f31045064673ad865ed61ab03003e7"],"state_sha256":"a6b0e933759fd56abb9a74e2716af4c411ca4926fa6ec35f5e914d6af09b6459"}