{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KEMPWTFMU5EJLSLRRAPW3FRROS","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":"12347c27c7aa1b0916edb72f774e843d5015cdc00a5009a71974484c1151898b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T22:54:12Z","title_canon_sha256":"b54c52cb39f2a0b11eed79b62fb206f309f7172c4173f55694f17a1a7d3fbdeb"},"schema_version":"1.0","source":{"id":"2403.18140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18140","created_at":"2026-07-05T11:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18140v2","created_at":"2026-07-05T11:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18140","created_at":"2026-07-05T11:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"KEMPWTFMU5EJ","created_at":"2026-07-05T11:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"KEMPWTFMU5EJLSLR","created_at":"2026-07-05T11:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"KEMPWTFM","created_at":"2026-07-05T11:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:8556038316d1e5f21d13dcb4cf93bafef1c9b0663e9c30d82e63b365c2663efa","target":"graph","created_at":"2026-07-05T11:43:54Z","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/2403.18140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The high compute cost associated with pretraining large language models limits their research. Two strategies have emerged to address this issue: domain specialization and pretraining with high-quality data. To explore these strategies, we specialized the Mistral-7B model with 1.9 billion unique tokens from reputable Brazilian legal sources and conducted few-shot evaluations on legal and general knowledge test suites. Our model, Juru, demonstrates the benefits of domain specialization by achieving improved performance on legal benchmarks, even with a reduced amount of pretraining data. However","authors_text":"Ramon Pires, Rodrigo Nogueira, Roseli Romero, Roseval Malaquias Junior","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T22:54:12Z","title":"Juru: Legal Brazilian Large Language Model from Reputable Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18140","kind":"arxiv","version":2},"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":"sha256:845686fcf4fcf9205a24ff14b163596338906fdba623287ba357a01b6bd42482","target":"record","created_at":"2026-07-05T11:43:54Z","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":"12347c27c7aa1b0916edb72f774e843d5015cdc00a5009a71974484c1151898b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T22:54:12Z","title_canon_sha256":"b54c52cb39f2a0b11eed79b62fb206f309f7172c4173f55694f17a1a7d3fbdeb"},"schema_version":"1.0","source":{"id":"2403.18140","kind":"arxiv","version":2}},"canonical_sha256":"5118fb4caca74895c971881f6d963174a8e6db3bef68d3b7ae69a30118a12a5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5118fb4caca74895c971881f6d963174a8e6db3bef68d3b7ae69a30118a12a5e","first_computed_at":"2026-07-05T11:43:54.907724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:54.907724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C4t0FPv79kx9TDtV8wdKCdet017miFnnNeaxUnDR9U3TgfCcBQ04Q6c9D9zEnVBHeT55amSSH8i5GEstrxo1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:54.908265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:845686fcf4fcf9205a24ff14b163596338906fdba623287ba357a01b6bd42482","sha256:8556038316d1e5f21d13dcb4cf93bafef1c9b0663e9c30d82e63b365c2663efa"],"state_sha256":"579d35b7d7a8319ea40bfbaf1807df287d238c964e10b433c06bfbc65e6e6df4"}