{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MENTTJREUSZNW75IOJ7FVQSQ6B","short_pith_number":"pith:MENTTJRE","schema_version":"1.0","canonical_sha256":"611b39a624a4b2db7fa8727e5ac250f044b1253c216a00046472cc823122652f","source":{"kind":"arxiv","id":"2305.06721","version":2},"attestation_state":"computed","paper":{"title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ant\\'onio Branco, Henrique Lopes Cardoso, Jo\\~ao Rodrigues, Jo\\~ao Silva, Lu\\'is Gomes, Rodrigo Santos, Tom\\'as Os\\'orio","submitted_at":"2023-05-11T10:56:20Z","abstract_excerpt":"To advance the neural encoding of Portuguese (PT), and a fortiori the technological preparation of this language for the digital age, we developed a Transformer-based foundation model that sets a new state of the art in this respect for two of its variants, namely European Portuguese from Portugal (PT-PT) and American Portuguese from Brazil (PT-BR).\n  To develop this encoder, which we named Albertina PT-*, a strong model was used as a starting point, DeBERTa, and its pre-training was done over data sets of Portuguese, namely over data sets we gathered for PT-PT and PT-BR, and over the brWaC co"},"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":"2305.06721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T10:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"f2a3c4b5463ea8dc02ebde6d71344bb016c7f1fd0f3504d06d0b071240fd7c0b","abstract_canon_sha256":"b20de80d51c16f10406b0076347f2e3eab7b002621f9ed73951e45dc9f4b2947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:25.706692Z","signature_b64":"Vem5e06CUiXMF6xEMAnsBbADzuW4GIpnCUVeItsP8LVaueQKKna5wI+XtupCI4VZwTlP9ughkUuA5YaTyDJHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611b39a624a4b2db7fa8727e5ac250f044b1253c216a00046472cc823122652f","last_reissued_at":"2026-07-05T08:03:25.706284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:25.706284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ant\\'onio Branco, Henrique Lopes Cardoso, Jo\\~ao Rodrigues, Jo\\~ao Silva, Lu\\'is Gomes, Rodrigo Santos, Tom\\'as Os\\'orio","submitted_at":"2023-05-11T10:56:20Z","abstract_excerpt":"To advance the neural encoding of Portuguese (PT), and a fortiori the technological preparation of this language for the digital age, we developed a Transformer-based foundation model that sets a new state of the art in this respect for two of its variants, namely European Portuguese from Portugal (PT-PT) and American Portuguese from Brazil (PT-BR).\n  To develop this encoder, which we named Albertina PT-*, a strong model was used as a starting point, DeBERTa, and its pre-training was done over data sets of Portuguese, namely over data sets we gathered for PT-PT and PT-BR, and over the brWaC co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06721","kind":"arxiv","version":2},"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/2305.06721/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":"2305.06721","created_at":"2026-07-05T08:03:25.706345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06721v2","created_at":"2026-07-05T08:03:25.706345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06721","created_at":"2026-07-05T08:03:25.706345+00:00"},{"alias_kind":"pith_short_12","alias_value":"MENTTJREUSZN","created_at":"2026-07-05T08:03:25.706345+00:00"},{"alias_kind":"pith_short_16","alias_value":"MENTTJREUSZNW75I","created_at":"2026-07-05T08:03:25.706345+00:00"},{"alias_kind":"pith_short_8","alias_value":"MENTTJRE","created_at":"2026-07-05T08:03:25.706345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00086","citing_title":"NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18878","citing_title":"LegalBench-BR: A Benchmark for Evaluating Large Language Models on Brazilian Legal Decision Classification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B","json":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B.json","graph_json":"https://pith.science/api/pith-number/MENTTJREUSZNW75IOJ7FVQSQ6B/graph.json","events_json":"https://pith.science/api/pith-number/MENTTJREUSZNW75IOJ7FVQSQ6B/events.json","paper":"https://pith.science/paper/MENTTJRE"},"agent_actions":{"view_html":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B","download_json":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B.json","view_paper":"https://pith.science/paper/MENTTJRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06721&json=true","fetch_graph":"https://pith.science/api/pith-number/MENTTJREUSZNW75IOJ7FVQSQ6B/graph.json","fetch_events":"https://pith.science/api/pith-number/MENTTJREUSZNW75IOJ7FVQSQ6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B/action/storage_attestation","attest_author":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B/action/author_attestation","sign_citation":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B/action/citation_signature","submit_replication":"https://pith.science/pith/MENTTJREUSZNW75IOJ7FVQSQ6B/action/replication_record"}},"created_at":"2026-07-05T08:03:25.706345+00:00","updated_at":"2026-07-05T08:03:25.706345+00:00"}