{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LJH5IMUJKABEXLRYU3J2VS56FF","short_pith_number":"pith:LJH5IMUJ","schema_version":"1.0","canonical_sha256":"5a4fd4328950024bae38a6d3aacbbe297d1b224dec12cfde07e5499a98340921","source":{"kind":"arxiv","id":"2309.16844","version":2},"attestation_state":"computed","paper":{"title":"DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyson Andrade, Israel Campiotti, Matheus Rodrigues, Rafael Azevedo, Yuri Albuquerque","submitted_at":"2023-09-28T20:53:25Z","abstract_excerpt":"This paper presents an approach for adapting the DebertaV3 XSmall model pre-trained in English for Brazilian Portuguese natural language processing (NLP) tasks. A key aspect of the methodology involves a multistep training process to ensure the model is effectively tuned for the Portuguese language. Initial datasets from Carolina and BrWac are preprocessed to address issues like emojis, HTML tags, and encodings. A Portuguese-specific vocabulary of 50,000 tokens is created using SentencePiece. Rather than training from scratch, the weights of the pre-trained English model are used to initialize"},"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":"2309.16844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-28T20:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"e869257b91d4976e516d6859270350939b4181a14c7e987f64d046ee48d26e0c","abstract_canon_sha256":"d2b61bbf972ac77039be313e035f8df3c13d5e01d76fb41c412a2233e7c320bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:17.059276Z","signature_b64":"Yg/vjQnJI4loSQCHWRXU/sb0KxAc7qeS3p/MZrxBdTD4LoP+vj+4stihiYG6OXJqBtVZr0Zk4AlkV+/Pwg7aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a4fd4328950024bae38a6d3aacbbe297d1b224dec12cfde07e5499a98340921","last_reissued_at":"2026-07-05T07:07:17.058857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:17.058857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyson Andrade, Israel Campiotti, Matheus Rodrigues, Rafael Azevedo, Yuri Albuquerque","submitted_at":"2023-09-28T20:53:25Z","abstract_excerpt":"This paper presents an approach for adapting the DebertaV3 XSmall model pre-trained in English for Brazilian Portuguese natural language processing (NLP) tasks. A key aspect of the methodology involves a multistep training process to ensure the model is effectively tuned for the Portuguese language. Initial datasets from Carolina and BrWac are preprocessed to address issues like emojis, HTML tags, and encodings. A Portuguese-specific vocabulary of 50,000 tokens is created using SentencePiece. Rather than training from scratch, the weights of the pre-trained English model are used to initialize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16844","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/2309.16844/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":"2309.16844","created_at":"2026-07-05T07:07:17.058923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16844v2","created_at":"2026-07-05T07:07:17.058923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16844","created_at":"2026-07-05T07:07:17.058923+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJH5IMUJKABE","created_at":"2026-07-05T07:07:17.058923+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJH5IMUJKABEXLRY","created_at":"2026-07-05T07:07:17.058923+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJH5IMUJ","created_at":"2026-07-05T07:07:17.058923+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/LJH5IMUJKABEXLRYU3J2VS56FF","json":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF.json","graph_json":"https://pith.science/api/pith-number/LJH5IMUJKABEXLRYU3J2VS56FF/graph.json","events_json":"https://pith.science/api/pith-number/LJH5IMUJKABEXLRYU3J2VS56FF/events.json","paper":"https://pith.science/paper/LJH5IMUJ"},"agent_actions":{"view_html":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF","download_json":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF.json","view_paper":"https://pith.science/paper/LJH5IMUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16844&json=true","fetch_graph":"https://pith.science/api/pith-number/LJH5IMUJKABEXLRYU3J2VS56FF/graph.json","fetch_events":"https://pith.science/api/pith-number/LJH5IMUJKABEXLRYU3J2VS56FF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF/action/storage_attestation","attest_author":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF/action/author_attestation","sign_citation":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF/action/citation_signature","submit_replication":"https://pith.science/pith/LJH5IMUJKABEXLRYU3J2VS56FF/action/replication_record"}},"created_at":"2026-07-05T07:07:17.058923+00:00","updated_at":"2026-07-05T07:07:17.058923+00:00"}