{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YUGKWHFY5P6ZVEXZTQBNV7L7JE","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":"2c9a9da11dcd850bc33d4c6ca77035544b08f48b5d5f01ab6ce2c1f8e0541f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T17:42:16Z","title_canon_sha256":"72015b579696727aebe6da0a54f983e86019a80baa6f006141e9a674074d1444"},"schema_version":"1.0","source":{"id":"2403.03883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03883","created_at":"2026-07-05T07:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03883v2","created_at":"2026-07-05T07:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03883","created_at":"2026-07-05T07:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"YUGKWHFY5P6Z","created_at":"2026-07-05T07:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"YUGKWHFY5P6ZVEXZ","created_at":"2026-07-05T07:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"YUGKWHFY","created_at":"2026-07-05T07:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:57be8406ba1ffc17b9e4b3af149a6dbbdda13e74ce104df8d766018a15bea12b","target":"graph","created_at":"2026-07-05T07:53:16Z","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/2403.03883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain. With 7 billion parameters, SaulLM-7B is the first LLM designed explicitly for legal text comprehension and generation. Leveraging the Mistral 7B architecture as its foundation, SaulLM-7B is trained on an English legal corpus of over 30 billion tokens. SaulLM-7B exhibits state-of-the-art proficiency in understanding and processing legal documents. Additionally, we present a novel instructional fine-tuning method that leverages legal datasets to further enhance SaulLM-7B's performance in legal task","authors_text":"Andre F. T. Martins, Caio Corro, Dominic Culver, Fabrizio Esposito, Malik Boudiaf, Michael Desa, Pierre Colombo, Rui Melo, Sofia Morgado, Telmo Pessoa Pires, Vera L\\'ucia Raposo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T17:42:16Z","title":"SaulLM-7B: A pioneering Large Language Model for Law"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03883","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:d8990c99cd4def250cfff96f2e1dc62c880c653b84d4d399f9d81944c3e6c413","target":"record","created_at":"2026-07-05T07:53:16Z","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":"2c9a9da11dcd850bc33d4c6ca77035544b08f48b5d5f01ab6ce2c1f8e0541f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T17:42:16Z","title_canon_sha256":"72015b579696727aebe6da0a54f983e86019a80baa6f006141e9a674074d1444"},"schema_version":"1.0","source":{"id":"2403.03883","kind":"arxiv","version":2}},"canonical_sha256":"c50cab1cb8ebfd9a92f99c02dafd7f491a657db07b60ec34139a4452a74718a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c50cab1cb8ebfd9a92f99c02dafd7f491a657db07b60ec34139a4452a74718a5","first_computed_at":"2026-07-05T07:53:16.205283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:16.205283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yT3bKg3s1deKdeZQ2y3n16RYbEXK5rbTLd9TssGQvPonMh7V9YhPLKS7ldifTf9QvU8sk6FQ1qLKZ67wpGgrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:16.205752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8990c99cd4def250cfff96f2e1dc62c880c653b84d4d399f9d81944c3e6c413","sha256:57be8406ba1ffc17b9e4b3af149a6dbbdda13e74ce104df8d766018a15bea12b"],"state_sha256":"efdc0c440b875aed133863409902b6bd86ab6a9d45f2df19ccc26fd91c29c739"}