{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MX37NWQR6CTCTI3HHLVEMH2565","short_pith_number":"pith:MX37NWQR","schema_version":"1.0","canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","source":{"kind":"arxiv","id":"2111.09453","version":3},"attestation_state":"computed","paper":{"title":"RoBERTuito: a pre-trained language model for social media text in Spanish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dami\\'an A. Furman, Franco Luque, Juan Manuel P\\'erez, Laura Alonso Alemany","submitted_at":"2021-11-18T00:10:25Z","abstract_excerpt":"Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for Natural Language Understanding tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks. However, for languages other than English such models are not widely available.\n  In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanis"},"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":"2111.09453","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e52945e963519395f10cf79d0ade3dc9e48d1d80850854f2bd3f54205f7adab6","abstract_canon_sha256":"33bccfb3b4f14b68be409175f8a8b41aac53cbfe182615c5e6dda12126486a2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:17.014769Z","signature_b64":"ryG6eEP3RpoUmjm1G+enNnd4IdZOiWkdlqEWGI05KaadSo5v3koviW5eBx9FKkR217hAJ83H2F6Uta2Ig8fGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","last_reissued_at":"2026-07-05T04:20:17.014268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:17.014268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoBERTuito: a pre-trained language model for social media text in Spanish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dami\\'an A. Furman, Franco Luque, Juan Manuel P\\'erez, Laura Alonso Alemany","submitted_at":"2021-11-18T00:10:25Z","abstract_excerpt":"Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for Natural Language Understanding tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks. However, for languages other than English such models are not widely available.\n  In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09453","kind":"arxiv","version":3},"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/2111.09453/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":"2111.09453","created_at":"2026-07-05T04:20:17.014335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09453v3","created_at":"2026-07-05T04:20:17.014335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09453","created_at":"2026-07-05T04:20:17.014335+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX37NWQR6CTC","created_at":"2026-07-05T04:20:17.014335+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX37NWQR6CTCTI3H","created_at":"2026-07-05T04:20:17.014335+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX37NWQR","created_at":"2026-07-05T04:20:17.014335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11750","citing_title":"Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565","json":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565.json","graph_json":"https://pith.science/api/pith-number/MX37NWQR6CTCTI3HHLVEMH2565/graph.json","events_json":"https://pith.science/api/pith-number/MX37NWQR6CTCTI3HHLVEMH2565/events.json","paper":"https://pith.science/paper/MX37NWQR"},"agent_actions":{"view_html":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565","download_json":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565.json","view_paper":"https://pith.science/paper/MX37NWQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09453&json=true","fetch_graph":"https://pith.science/api/pith-number/MX37NWQR6CTCTI3HHLVEMH2565/graph.json","fetch_events":"https://pith.science/api/pith-number/MX37NWQR6CTCTI3HHLVEMH2565/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/action/storage_attestation","attest_author":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/action/author_attestation","sign_citation":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/action/citation_signature","submit_replication":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/action/replication_record"}},"created_at":"2026-07-05T04:20:17.014335+00:00","updated_at":"2026-07-05T04:20:17.014335+00:00"}