{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUGKWHFY5P6ZVEXZTQBNV7L7JE","short_pith_number":"pith:YUGKWHFY","schema_version":"1.0","canonical_sha256":"c50cab1cb8ebfd9a92f99c02dafd7f491a657db07b60ec34139a4452a74718a5","source":{"kind":"arxiv","id":"2403.03883","version":2},"attestation_state":"computed","paper":{"title":"SaulLM-7B: A pioneering Large Language Model for Law","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2024-03-06T17:42:16Z","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"},"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":"2403.03883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T17:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"72015b579696727aebe6da0a54f983e86019a80baa6f006141e9a674074d1444","abstract_canon_sha256":"2c9a9da11dcd850bc33d4c6ca77035544b08f48b5d5f01ab6ce2c1f8e0541f96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:16.205752Z","signature_b64":"yT3bKg3s1deKdeZQ2y3n16RYbEXK5rbTLd9TssGQvPonMh7V9YhPLKS7ldifTf9QvU8sk6FQ1qLKZ67wpGgrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50cab1cb8ebfd9a92f99c02dafd7f491a657db07b60ec34139a4452a74718a5","last_reissued_at":"2026-07-05T07:53:16.205283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:16.205283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SaulLM-7B: A pioneering Large Language Model for Law","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2024-03-06T17:42:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03883","kind":"arxiv","version":2},"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/2403.03883/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":"2403.03883","created_at":"2026-07-05T07:53:16.205338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03883v2","created_at":"2026-07-05T07:53:16.205338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03883","created_at":"2026-07-05T07:53:16.205338+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUGKWHFY5P6Z","created_at":"2026-07-05T07:53:16.205338+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUGKWHFY5P6ZVEXZ","created_at":"2026-07-05T07:53:16.205338+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUGKWHFY","created_at":"2026-07-05T07:53:16.205338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11245","citing_title":"Position: Hippocampal Explicit Memory Is the Cornerstone for AGI","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31464","citing_title":"Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02010","citing_title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27331","citing_title":"Maat: The Agentic Legal Research Assistant for Competition Protection","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00898","citing_title":"Citation Grounding Measures the Oracle: Graph Coverage Determines Reported LLM Hallucination Rates in Law","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00405","citing_title":"From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21076","citing_title":"GradeLegal: Automated Grading for German Legal Cases","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08022","citing_title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27415","citing_title":"ChipLingo: A Systematic Training Framework for Large Language Models in EDA","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05532","citing_title":"A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02557","citing_title":"VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02010","citing_title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE","json":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE.json","graph_json":"https://pith.science/api/pith-number/YUGKWHFY5P6ZVEXZTQBNV7L7JE/graph.json","events_json":"https://pith.science/api/pith-number/YUGKWHFY5P6ZVEXZTQBNV7L7JE/events.json","paper":"https://pith.science/paper/YUGKWHFY"},"agent_actions":{"view_html":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE","download_json":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE.json","view_paper":"https://pith.science/paper/YUGKWHFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03883&json=true","fetch_graph":"https://pith.science/api/pith-number/YUGKWHFY5P6ZVEXZTQBNV7L7JE/graph.json","fetch_events":"https://pith.science/api/pith-number/YUGKWHFY5P6ZVEXZTQBNV7L7JE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE/action/storage_attestation","attest_author":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE/action/author_attestation","sign_citation":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE/action/citation_signature","submit_replication":"https://pith.science/pith/YUGKWHFY5P6ZVEXZTQBNV7L7JE/action/replication_record"}},"created_at":"2026-07-05T07:53:16.205338+00:00","updated_at":"2026-07-05T07:53:16.205338+00:00"}