{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z5KJ4MF6TOQFX4HEFRAJTKKHQK","short_pith_number":"pith:Z5KJ4MF6","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"},"canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","source":{"kind":"arxiv","id":"2606.19096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19096","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19096v1","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19096","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z5KJ4MF6TOQF","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"Z5KJ4MF6TOQFX4HE","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"Z5KJ4MF6","created_at":"2026-06-19T16:11:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z5KJ4MF6TOQFX4HEFRAJTKKHQK","target":"record","payload":{"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"},"canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","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"},"source_kind":"arxiv","source_id":"2606.19096","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":"2026-06-19T16:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXKLBOpdtaAurNuIo4B3mPfBu4xSfqe3/lpsXWmImQck9yp65KAjwlCM3N3BHFKed8oBDE96XUalfi6wAa9rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T03:23:07.908670Z"},"content_sha256":"9b6c67ae97d0ed223677982f568ab9abe2d1d856ccfd40c7f5e3a6ef89da1a0a","schema_version":"1.0","event_id":"sha256:9b6c67ae97d0ed223677982f568ab9abe2d1d856ccfd40c7f5e3a6ef89da1a0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z5KJ4MF6TOQFX4HEFRAJTKKHQK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0SjvuMrffj0Vllb//rAyfy6lNv0OA0Hc1mKM2uS/JrFKZdo5UcMed8e2WNFEu65T1AcHlyLIXM9Wg5PDrzBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T03:23:07.909296Z"},"content_sha256":"10d23610afba84f92dfe08d87c23b481eeeb110368d5f46a89a1a1f5734c8107","schema_version":"1.0","event_id":"sha256:10d23610afba84f92dfe08d87c23b481eeeb110368d5f46a89a1a1f5734c8107"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/bundle.json","state_url":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/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":"2026-07-02T03:23:07Z","links":{"resolver":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK","bundle":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/bundle.json","state":"https://pith.science/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5KJ4MF6TOQFX4HEFRAJTKKHQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z5KJ4MF6TOQFX4HEFRAJTKKHQK","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":"de37a66ace6c1b9baa5a500510d79be2845fda49f7d9ec488ddd4104b5a7ee49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T14:06:26Z","title_canon_sha256":"b8e548a1b48fc879eaa5f31fd956e1cfb6335b99dc8030274615e857d940f172"},"schema_version":"1.0","source":{"id":"2606.19096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19096","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19096v1","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19096","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z5KJ4MF6TOQF","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"Z5KJ4MF6TOQFX4HE","created_at":"2026-06-19T16:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"Z5KJ4MF6","created_at":"2026-06-19T16:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:10d23610afba84f92dfe08d87c23b481eeeb110368d5f46a89a1a1f5734c8107","target":"graph","created_at":"2026-06-19T16:11:56Z","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/2606.19096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Semedo, Diogo Gl\\'oria-Silva, Diogo Tavares, Jo\\~ao Cardeira, Jo\\~ao Magalh\\~aes, Manuel Letras da Luz, Rafael Ferreira","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T14:06:26Z","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19096","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":"sha256:9b6c67ae97d0ed223677982f568ab9abe2d1d856ccfd40c7f5e3a6ef89da1a0a","target":"record","created_at":"2026-06-19T16:11:56Z","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":"de37a66ace6c1b9baa5a500510d79be2845fda49f7d9ec488ddd4104b5a7ee49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T14:06:26Z","title_canon_sha256":"b8e548a1b48fc879eaa5f31fd956e1cfb6335b99dc8030274615e857d940f172"},"schema_version":"1.0","source":{"id":"2606.19096","kind":"arxiv","version":1}},"canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf549e30be9ba05bf0e42c4099a94782a05eaf34589b3c8e2d4279a7cc5e4db4","first_computed_at":"2026-06-19T16:11:56.489112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:56.489112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnXqcJ1vJCNplc4ZXZFxPs3Pe9gaG4mVz3n4tykuLNDV5iyP+hV5CRyndnbaom59F3/svFCqjjeh6it5CfrUDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:56.489509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b6c67ae97d0ed223677982f568ab9abe2d1d856ccfd40c7f5e3a6ef89da1a0a","sha256:10d23610afba84f92dfe08d87c23b481eeeb110368d5f46a89a1a1f5734c8107"],"state_sha256":"37512cdc4baf40fd9f2779fb829a41ced37e7ef263923d8dff1a2b3c5a89ff77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNqqZdFhGN+n4oT5Ns1hIG9k2WoeAcuVoQS0mZ5dZ610Jns3QumISevxuQegS4URKmYMFzaZUSebjQP0zeuUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T03:23:07.912685Z","bundle_sha256":"d3f094b433c54bc41910d5dfe45fc975d1cd2926db65a250649a877ce9b8aad8"}}