{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SJN27GVGOETUHW2RPYWALNGOLG","short_pith_number":"pith:SJN27GVG","schema_version":"1.0","canonical_sha256":"925baf9aa6712743db517e2c05b4ce599b55b4bffec174bd97cdd3d69173caef","source":{"kind":"arxiv","id":"2402.07681","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models \"Ad Referendum\": How Good Are They at Machine Translation in the Legal Domain?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gokhan Dogru, Joao Lucas Cavalheiro Camargo, Vicent Briva-Iglesias","submitted_at":"2024-02-12T14:40:54Z","abstract_excerpt":"This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a tradition-al neural machine translation (NMT) system across four language pairs in the legal domain. It combines automatic evaluation met-rics (AEMs) and human evaluation (HE) by professional transla-tors to assess translation ranking, fluency and adequacy. The re-sults indicate that while Google Translate generally outperforms LLMs in AEMs, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent tran"},"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":"2402.07681","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T14:40:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ca09b99587182eac048ca5858d4390aaa6e4cf0afea64ef43d2237b6aa2f21b","abstract_canon_sha256":"e5ba1d2ead705bbaaee0b080ef206156fd270f3391cf58bce2df67401a998ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:10.764507Z","signature_b64":"/+1zAl/Ht4UUIjPckofxar8raEnrYP0CUgh/bXIMLrhaE+e0/6wjLgtM4/HGeyAhR3oaOtJp+Vw+SCPIQOVZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925baf9aa6712743db517e2c05b4ce599b55b4bffec174bd97cdd3d69173caef","last_reissued_at":"2026-07-05T07:44:10.764111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:10.764111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models \"Ad Referendum\": How Good Are They at Machine Translation in the Legal Domain?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gokhan Dogru, Joao Lucas Cavalheiro Camargo, Vicent Briva-Iglesias","submitted_at":"2024-02-12T14:40:54Z","abstract_excerpt":"This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a tradition-al neural machine translation (NMT) system across four language pairs in the legal domain. It combines automatic evaluation met-rics (AEMs) and human evaluation (HE) by professional transla-tors to assess translation ranking, fluency and adequacy. The re-sults indicate that while Google Translate generally outperforms LLMs in AEMs, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07681","kind":"arxiv","version":1},"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/2402.07681/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":"2402.07681","created_at":"2026-07-05T07:44:10.764161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07681v1","created_at":"2026-07-05T07:44:10.764161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07681","created_at":"2026-07-05T07:44:10.764161+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJN27GVGOETU","created_at":"2026-07-05T07:44:10.764161+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJN27GVGOETUHW2R","created_at":"2026-07-05T07:44:10.764161+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJN27GVG","created_at":"2026-07-05T07:44:10.764161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21508","citing_title":"skLEP: A Slovak General Language Understanding Benchmark","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG","json":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG.json","graph_json":"https://pith.science/api/pith-number/SJN27GVGOETUHW2RPYWALNGOLG/graph.json","events_json":"https://pith.science/api/pith-number/SJN27GVGOETUHW2RPYWALNGOLG/events.json","paper":"https://pith.science/paper/SJN27GVG"},"agent_actions":{"view_html":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG","download_json":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG.json","view_paper":"https://pith.science/paper/SJN27GVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07681&json=true","fetch_graph":"https://pith.science/api/pith-number/SJN27GVGOETUHW2RPYWALNGOLG/graph.json","fetch_events":"https://pith.science/api/pith-number/SJN27GVGOETUHW2RPYWALNGOLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG/action/storage_attestation","attest_author":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG/action/author_attestation","sign_citation":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG/action/citation_signature","submit_replication":"https://pith.science/pith/SJN27GVGOETUHW2RPYWALNGOLG/action/replication_record"}},"created_at":"2026-07-05T07:44:10.764161+00:00","updated_at":"2026-07-05T07:44:10.764161+00:00"}