{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PVFJYNQYQ7BNOEP2P7J6VO7AW4","short_pith_number":"pith:PVFJYNQY","schema_version":"1.0","canonical_sha256":"7d4a9c361887c2d711fa7fd3eabbe0b73264f74f55ac24c43225ddc562165bc8","source":{"kind":"arxiv","id":"2606.22722","version":1},"attestation_state":"computed","paper":{"title":"moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Giovana Kerche Bon\\'as, Jo\\~ao Guilherme Alves Santos, Thales Sales Almeida, Thiago Laitz","submitted_at":"2026-06-21T23:44:47Z","abstract_excerpt":"Encoder-only transformer models remain essential for production NLP pipelines. We introduce moBERTo, a Portuguese adaptation of ModernBERT obtained through continued pretraining of the ModernBERT-base checkpoint on 60 billion tokens (5 epochs over a 12-billion-token corpus curated from FineWeb2 and filtered with educational and STEM classifiers). We preserve the original architecture, including rotary positional embeddings, alternating local-global attention, flash attention, and unpadding. We evaluate moBERTo across information retrieval (including long-context retrieval at up to 8,192 tokens"},"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":"2606.22722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"60038f84843b5c22d158d189f0f214deadf0330454148b003ea965ebcbde3f87","abstract_canon_sha256":"8b68b1d7c6aba53edf7692b8ff49caac33e5096a0714cd14471b3e62a4f3d713"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:45.693613Z","signature_b64":"3g3Gbu1ISZHJDOnYU/E54J7FmEru/OWFwzbVG8Th9rBrawmqZfc97ACuY/RH7Yqev35WFmLm8MXqKV9oU07eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d4a9c361887c2d711fa7fd3eabbe0b73264f74f55ac24c43225ddc562165bc8","last_reissued_at":"2026-06-23T02:13:45.693222Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:45.693222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Giovana Kerche Bon\\'as, Jo\\~ao Guilherme Alves Santos, Thales Sales Almeida, Thiago Laitz","submitted_at":"2026-06-21T23:44:47Z","abstract_excerpt":"Encoder-only transformer models remain essential for production NLP pipelines. We introduce moBERTo, a Portuguese adaptation of ModernBERT obtained through continued pretraining of the ModernBERT-base checkpoint on 60 billion tokens (5 epochs over a 12-billion-token corpus curated from FineWeb2 and filtered with educational and STEM classifiers). We preserve the original architecture, including rotary positional embeddings, alternating local-global attention, flash attention, and unpadding. We evaluate moBERTo across information retrieval (including long-context retrieval at up to 8,192 tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22722","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/2606.22722/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":"2606.22722","created_at":"2026-06-23T02:13:45.693283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22722v1","created_at":"2026-06-23T02:13:45.693283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22722","created_at":"2026-06-23T02:13:45.693283+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVFJYNQYQ7BN","created_at":"2026-06-23T02:13:45.693283+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVFJYNQYQ7BNOEP2","created_at":"2026-06-23T02:13:45.693283+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVFJYNQY","created_at":"2026-06-23T02:13:45.693283+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/PVFJYNQYQ7BNOEP2P7J6VO7AW4","json":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4.json","graph_json":"https://pith.science/api/pith-number/PVFJYNQYQ7BNOEP2P7J6VO7AW4/graph.json","events_json":"https://pith.science/api/pith-number/PVFJYNQYQ7BNOEP2P7J6VO7AW4/events.json","paper":"https://pith.science/paper/PVFJYNQY"},"agent_actions":{"view_html":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4","download_json":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4.json","view_paper":"https://pith.science/paper/PVFJYNQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22722&json=true","fetch_graph":"https://pith.science/api/pith-number/PVFJYNQYQ7BNOEP2P7J6VO7AW4/graph.json","fetch_events":"https://pith.science/api/pith-number/PVFJYNQYQ7BNOEP2P7J6VO7AW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4/action/storage_attestation","attest_author":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4/action/author_attestation","sign_citation":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4/action/citation_signature","submit_replication":"https://pith.science/pith/PVFJYNQYQ7BNOEP2P7J6VO7AW4/action/replication_record"}},"created_at":"2026-06-23T02:13:45.693283+00:00","updated_at":"2026-06-23T02:13:45.693283+00:00"}