{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R7V5KR2I7TH3IUWSNJ6DUBEXSP","short_pith_number":"pith:R7V5KR2I","schema_version":"1.0","canonical_sha256":"8febd54748fccfb452d26a7c3a049793ce7a7ff9a67206be23fee478773762e0","source":{"kind":"arxiv","id":"2308.02976","version":1},"attestation_state":"computed","paper":{"title":"Spanish Pre-trained BERT Model and Evaluation Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gabriel Chaperon, Hojin Kang, Jorge P\\'erez, Jos\\'e Ca\\~nete, Jou-Hui Ho, Rodrigo Fuentes","submitted_at":"2023-08-06T00:16:04Z","abstract_excerpt":"The Spanish language is one of the top 5 spoken languages in the world. Nevertheless, finding resources to train or evaluate Spanish language models is not an easy task. In this paper we help bridge this gap by presenting a BERT-based language model pre-trained exclusively on Spanish data. As a second contribution, we also compiled several tasks specifically for the Spanish language in a single repository much in the spirit of the GLUE benchmark. By fine-tuning our pre-trained Spanish model, we obtain better results compared to other BERT-based models pre-trained on multilingual corpora for mo"},"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":"2308.02976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-06T00:16:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e1a643f432a46ee9631c669dab052381d7a5b01b19bdafad8b9d242edc6dace","abstract_canon_sha256":"beaa23b21a1d02cc6a2d508c437471ffa516fcc52b46e36322372681cc97d763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:10.063630Z","signature_b64":"WPj1kB23ZtGIJs5HedUnLxMoS5ZiPuNjQzMMIts9tC7fUP0wP8gok/nxAl85r4y/fJXjyKa7Cy/gTQpWaTtgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8febd54748fccfb452d26a7c3a049793ce7a7ff9a67206be23fee478773762e0","last_reissued_at":"2026-07-05T06:38:10.063080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:10.063080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spanish Pre-trained BERT Model and Evaluation Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gabriel Chaperon, Hojin Kang, Jorge P\\'erez, Jos\\'e Ca\\~nete, Jou-Hui Ho, Rodrigo Fuentes","submitted_at":"2023-08-06T00:16:04Z","abstract_excerpt":"The Spanish language is one of the top 5 spoken languages in the world. Nevertheless, finding resources to train or evaluate Spanish language models is not an easy task. In this paper we help bridge this gap by presenting a BERT-based language model pre-trained exclusively on Spanish data. As a second contribution, we also compiled several tasks specifically for the Spanish language in a single repository much in the spirit of the GLUE benchmark. By fine-tuning our pre-trained Spanish model, we obtain better results compared to other BERT-based models pre-trained on multilingual corpora for mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02976","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/2308.02976/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":"2308.02976","created_at":"2026-07-05T06:38:10.063157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02976v1","created_at":"2026-07-05T06:38:10.063157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02976","created_at":"2026-07-05T06:38:10.063157+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7V5KR2I7TH3","created_at":"2026-07-05T06:38:10.063157+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7V5KR2I7TH3IUWS","created_at":"2026-07-05T06:38:10.063157+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7V5KR2I","created_at":"2026-07-05T06:38:10.063157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30152","citing_title":"Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21370","citing_title":"MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP","json":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP.json","graph_json":"https://pith.science/api/pith-number/R7V5KR2I7TH3IUWSNJ6DUBEXSP/graph.json","events_json":"https://pith.science/api/pith-number/R7V5KR2I7TH3IUWSNJ6DUBEXSP/events.json","paper":"https://pith.science/paper/R7V5KR2I"},"agent_actions":{"view_html":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP","download_json":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP.json","view_paper":"https://pith.science/paper/R7V5KR2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02976&json=true","fetch_graph":"https://pith.science/api/pith-number/R7V5KR2I7TH3IUWSNJ6DUBEXSP/graph.json","fetch_events":"https://pith.science/api/pith-number/R7V5KR2I7TH3IUWSNJ6DUBEXSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP/action/storage_attestation","attest_author":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP/action/author_attestation","sign_citation":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP/action/citation_signature","submit_replication":"https://pith.science/pith/R7V5KR2I7TH3IUWSNJ6DUBEXSP/action/replication_record"}},"created_at":"2026-07-05T06:38:10.063157+00:00","updated_at":"2026-07-05T06:38:10.063157+00:00"}