{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GZFP7VVDQZSFNP52IBS63JAW25","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":"df80902a8e2236edc6ef05b54501bd479bcef652fb36ec2b0a9ae059392e2dd0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T02:49:35Z","title_canon_sha256":"9c300af0733b4af0b18211e739ea83ebbd82ced80ab3a4ec8d3026028d531c5e"},"schema_version":"1.0","source":{"id":"2308.11878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11878","created_at":"2026-07-05T06:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11878v1","created_at":"2026-07-05T06:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11878","created_at":"2026-07-05T06:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"GZFP7VVDQZSF","created_at":"2026-07-05T06:43:56Z"},{"alias_kind":"pith_short_16","alias_value":"GZFP7VVDQZSFNP52","created_at":"2026-07-05T06:43:56Z"},{"alias_kind":"pith_short_8","alias_value":"GZFP7VVD","created_at":"2026-07-05T06:43:56Z"}],"graph_snapshots":[{"event_id":"sha256:e6e30264ecde33f24c7ce2e1758cf9b3ddda2c3513de2a6fb7e0f0dc47a73ae7","target":"graph","created_at":"2026-07-05T06:43:56Z","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/2308.11878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The strategy of training the model from scratch in a specific language or domain serves two essential purposes: i) enhancing performance in the particular linguistic or domain context, and ii) ensuring effective tokenization. The main limitation inherent to this approach lies in the associated cost, which can reach six to seven-digit dollar values, depending on the model size and the number of parameters involved.\n  The main solution to overcome the cost challenge is to rely on available pre-trained models, which, despite recent advancements such as the LLaMA and LLaMA-2 models, still demonstr","authors_text":"Celio Larcher, Marcos Piau, Paulo Finardi, Pedro Gengo, Piero Esposito, Vinicius Carid\\'a","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T02:49:35Z","title":"Cabrita: closing the gap for foreign languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11878","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":"sha256:2c01e9f244ae52dbd945db653e6bb270faab490870f5da2563b54260e31ca253","target":"record","created_at":"2026-07-05T06:43:56Z","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":"df80902a8e2236edc6ef05b54501bd479bcef652fb36ec2b0a9ae059392e2dd0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T02:49:35Z","title_canon_sha256":"9c300af0733b4af0b18211e739ea83ebbd82ced80ab3a4ec8d3026028d531c5e"},"schema_version":"1.0","source":{"id":"2308.11878","kind":"arxiv","version":1}},"canonical_sha256":"364affd6a3866456bfba4065eda416d76f9b053877141429cdbd5e6ce933286e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"364affd6a3866456bfba4065eda416d76f9b053877141429cdbd5e6ce933286e","first_computed_at":"2026-07-05T06:43:56.014685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:56.014685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qo4IBiVDKJTNMTEzFSJi82CEAfr1G32XM/wOtCfWn3Ah7dlpU9Cb/wQ6J75QUkF3rx4OZ0YH4mDPpl0gMorYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:56.015143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c01e9f244ae52dbd945db653e6bb270faab490870f5da2563b54260e31ca253","sha256:e6e30264ecde33f24c7ce2e1758cf9b3ddda2c3513de2a6fb7e0f0dc47a73ae7"],"state_sha256":"7c3f63b6c49b18e2964777af146b49f2d198d20ef82a7623b29b3e0529e5c318"}