{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PVFJYNQYQ7BNOEP2P7J6VO7AW4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8b68b1d7c6aba53edf7692b8ff49caac33e5096a0714cd14471b3e62a4f3d713","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:44:47Z","title_canon_sha256":"60038f84843b5c22d158d189f0f214deadf0330454148b003ea965ebcbde3f87"},"schema_version":"1.0","source":{"id":"2606.22722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22722","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22722v1","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22722","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"PVFJYNQYQ7BN","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"PVFJYNQYQ7BNOEP2","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"PVFJYNQY","created_at":"2026-06-23T02:13:45Z"}],"graph_snapshots":[{"event_id":"sha256:82352a0a6b797c47ce4355f38d9e958e4d99bf27e8abf21dc4f50866f834134e","target":"graph","created_at":"2026-06-23T02:13:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.22722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Giovana Kerche Bon\\'as, Jo\\~ao Guilherme Alves Santos, Thales Sales Almeida, Thiago Laitz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:44:47Z","title":"moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22722","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a21e8d3e6ab8dc6048a27688bf19fea000aa26159f09fb89d22be75acede5139","target":"record","created_at":"2026-06-23T02:13:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8b68b1d7c6aba53edf7692b8ff49caac33e5096a0714cd14471b3e62a4f3d713","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:44:47Z","title_canon_sha256":"60038f84843b5c22d158d189f0f214deadf0330454148b003ea965ebcbde3f87"},"schema_version":"1.0","source":{"id":"2606.22722","kind":"arxiv","version":1}},"canonical_sha256":"7d4a9c361887c2d711fa7fd3eabbe0b73264f74f55ac24c43225ddc562165bc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d4a9c361887c2d711fa7fd3eabbe0b73264f74f55ac24c43225ddc562165bc8","first_computed_at":"2026-06-23T02:13:45.693222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:45.693222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3g3Gbu1ISZHJDOnYU/E54J7FmEru/OWFwzbVG8Th9rBrawmqZfc97ACuY/RH7Yqev35WFmLm8MXqKV9oU07eDw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:45.693613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a21e8d3e6ab8dc6048a27688bf19fea000aa26159f09fb89d22be75acede5139","sha256:82352a0a6b797c47ce4355f38d9e958e4d99bf27e8abf21dc4f50866f834134e"],"state_sha256":"897b5a656bc9781068681aa250bd8b9cb9c84bfdee202fec5acf23075102cf29"}