{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z5KJ4MF6TOQFX4HEFRAJTKKHQK","short_pith_number":"pith:Z5KJ4MF6","schema_version":"1.0","canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","source":{"kind":"arxiv","id":"2606.19096","version":1},"attestation_state":"computed","paper":{"title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Semedo, Diogo Gl\\'oria-Silva, Diogo Tavares, Jo\\~ao Cardeira, Jo\\~ao Magalh\\~aes, Manuel Letras da Luz, Rafael Ferreira","submitted_at":"2026-06-17T14:06:26Z","abstract_excerpt":"European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT focus on historical artifacts and literature. This work addresses modern OCR applications, introducing PorTEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction. To ascertain quality, we employ an annotation pipeline combining transcriptions from a frontier LVLM with exhaustive review by native speakers. We observe a sharp performance drop from synthetic to real world samples in most models, and find that, cu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.19096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T14:06:26Z","cross_cats_sorted":[],"title_canon_sha256":"b8e548a1b48fc879eaa5f31fd956e1cfb6335b99dc8030274615e857d940f172","abstract_canon_sha256":"de37a66ace6c1b9baa5a500510d79be2845fda49f7d9ec488ddd4104b5a7ee49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:56.489509Z","signature_b64":"bnXqcJ1vJCNplc4ZXZFxPs3Pe9gaG4mVz3n4tykuLNDV5iyP+hV5CRyndnbaom59F3/svFCqjjeh6it5CfrUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","last_reissued_at":"2026-06-19T16:11:56.489112Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:56.489112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Semedo, Diogo Gl\\'oria-Silva, Diogo Tavares, Jo\\~ao Cardeira, Jo\\~ao Magalh\\~aes, Manuel Letras da Luz, Rafael Ferreira","submitted_at":"2026-06-17T14:06:26Z","abstract_excerpt":"European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT focus on historical artifacts and literature. This work addresses modern OCR applications, introducing PorTEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction. To ascertain quality, we employ an annotation pipeline combining transcriptions from a frontier LVLM with exhaustive review by native speakers. We observe a sharp performance drop from synthetic to real world samples in most models, and find that, cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19096","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/2606.19096/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.19096","created_at":"2026-06-19T16:11:56.489172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19096v1","created_at":"2026-06-19T16:11:56.489172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19096","created_at":"2026-06-19T16:11:56.489172+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5KJ4MF6TOQF","created_at":"2026-06-19T16:11:56.489172+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5KJ4MF6TOQFX4HE","created_at":"2026-06-19T16:11:56.489172+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5KJ4MF6","created_at":"2026-06-19T16:11:56.489172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK","json":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK.json","graph_json":"https://pith.science/api/pith-number/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/graph.json","events_json":"https://pith.science/api/pith-number/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/events.json","paper":"https://pith.science/paper/Z5KJ4MF6"},"agent_actions":{"view_html":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK","download_json":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK.json","view_paper":"https://pith.science/paper/Z5KJ4MF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19096&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/action/storage_attestation","attest_author":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/action/author_attestation","sign_citation":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/action/citation_signature","submit_replication":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/action/replication_record"}},"created_at":"2026-06-19T16:11:56.489172+00:00","updated_at":"2026-06-19T16:11:56.489172+00:00"}