{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GIA5N5UPAQ52E74NJYRVNAP2RR","short_pith_number":"pith:GIA5N5UP","schema_version":"1.0","canonical_sha256":"3201d6f68f043ba27f8d4e235681fa8c79c14ed16b46fc6c4d9bbd53fb540f99","source":{"kind":"arxiv","id":"2502.14385","version":1},"attestation_state":"computed","paper":{"title":"Tradutor: Building a Variety Specific Translation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Al\\'ipio Jorge, Hugo Sousa, Ricardo Campos, Satya Almasian","submitted_at":"2025-02-20T09:20:59Z","abstract_excerpt":"Language models have become foundational to many widely used systems. However, these seemingly advantageous models are double-edged swords. While they excel in tasks related to resource-rich languages like English, they often lose the fine nuances of language forms, dialects, and varieties that are inherent to languages spoken in multiple regions of the world. Languages like European Portuguese are neglected in favor of their more popular counterpart, Brazilian Portuguese, leading to suboptimal performance in various linguistic tasks. To address this gap, we introduce the first open-source tra"},"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":"2502.14385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:20:59Z","cross_cats_sorted":[],"title_canon_sha256":"bafe710cfbb879c03c195bb564daa5cf84a72b2f85b3e5bf2287e54ae5aa6b7a","abstract_canon_sha256":"171bb55a12c172c2e66c7b763adac7de59ff80af4e0ef96b865264915e29223c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:25.564367Z","signature_b64":"D+dPbFS/bjm9C2DwCiMmoasTjJRZbbyxsVSQxOIONAiNwJXyTSMsgo34o8DdPSvDsPJtib5jYGFcBup4fwxfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3201d6f68f043ba27f8d4e235681fa8c79c14ed16b46fc6c4d9bbd53fb540f99","last_reissued_at":"2026-07-05T10:17:25.563766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:25.563766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tradutor: Building a Variety Specific Translation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Al\\'ipio Jorge, Hugo Sousa, Ricardo Campos, Satya Almasian","submitted_at":"2025-02-20T09:20:59Z","abstract_excerpt":"Language models have become foundational to many widely used systems. However, these seemingly advantageous models are double-edged swords. While they excel in tasks related to resource-rich languages like English, they often lose the fine nuances of language forms, dialects, and varieties that are inherent to languages spoken in multiple regions of the world. Languages like European Portuguese are neglected in favor of their more popular counterpart, Brazilian Portuguese, leading to suboptimal performance in various linguistic tasks. To address this gap, we introduce the first open-source tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14385","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/2502.14385/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":"2502.14385","created_at":"2026-07-05T10:17:25.563836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14385v1","created_at":"2026-07-05T10:17:25.563836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14385","created_at":"2026-07-05T10:17:25.563836+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIA5N5UPAQ52","created_at":"2026-07-05T10:17:25.563836+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIA5N5UPAQ52E74N","created_at":"2026-07-05T10:17:25.563836+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIA5N5UP","created_at":"2026-07-05T10:17:25.563836+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/GIA5N5UPAQ52E74NJYRVNAP2RR","json":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR.json","graph_json":"https://pith.science/api/pith-number/GIA5N5UPAQ52E74NJYRVNAP2RR/graph.json","events_json":"https://pith.science/api/pith-number/GIA5N5UPAQ52E74NJYRVNAP2RR/events.json","paper":"https://pith.science/paper/GIA5N5UP"},"agent_actions":{"view_html":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR","download_json":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR.json","view_paper":"https://pith.science/paper/GIA5N5UP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14385&json=true","fetch_graph":"https://pith.science/api/pith-number/GIA5N5UPAQ52E74NJYRVNAP2RR/graph.json","fetch_events":"https://pith.science/api/pith-number/GIA5N5UPAQ52E74NJYRVNAP2RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR/action/storage_attestation","attest_author":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR/action/author_attestation","sign_citation":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR/action/citation_signature","submit_replication":"https://pith.science/pith/GIA5N5UPAQ52E74NJYRVNAP2RR/action/replication_record"}},"created_at":"2026-07-05T10:17:25.563836+00:00","updated_at":"2026-07-05T10:17:25.563836+00:00"}