{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XU6KE63W75T7J2TF6VIIQDJ6SI","short_pith_number":"pith:XU6KE63W","schema_version":"1.0","canonical_sha256":"bd3ca27b76ff67f4ea65f550880d3e92002dc9548104cb6873f05b66b2ea3e17","source":{"kind":"arxiv","id":"2505.01560","version":1},"attestation_state":"computed","paper":{"title":"AI agents may be worth the hype but not the resources (yet): An initial exploration of machine translation quality and costs in three language pairs in the legal and news domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gokhan Dogru, Vicent Briva Iglesias","submitted_at":"2025-05-02T20:02:13Z","abstract_excerpt":"Large language models (LLMs) and multi-agent orchestration are touted as the next leap in machine translation (MT), but their benefits relative to conventional neural MT (NMT) remain unclear. This paper offers an empirical reality check. We benchmark five paradigms, Google Translate (strong NMT baseline), GPT-4o (general-purpose LLM), o1-preview (reasoning-enhanced LLM), and two GPT-4o-powered agentic workflows (sequential three-stage and iterative refinement), on test data drawn from a legal contract and news prose in three English-source pairs: Spanish, Catalan and Turkish. Automatic evaluat"},"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":"2505.01560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T20:02:13Z","cross_cats_sorted":[],"title_canon_sha256":"2dc941b64b3edd2e5a70a72c657201dadf500d9c8754eb66f99d7f02fdb2766e","abstract_canon_sha256":"987c10008c158060c0062ce5def940c0922d9c460a3eddd0487a7c5fedc9882e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:00.011667Z","signature_b64":"QIh6VUbPMJFCxgUPgU2q4gk8uMSljgGyBACuATflgCS1PgeVEYHUtHbpQ+SZ5pUct9IaiFG4rDrEzZTAbcVoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3ca27b76ff67f4ea65f550880d3e92002dc9548104cb6873f05b66b2ea3e17","last_reissued_at":"2026-07-05T10:58:00.011182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:00.011182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI agents may be worth the hype but not the resources (yet): An initial exploration of machine translation quality and costs in three language pairs in the legal and news domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gokhan Dogru, Vicent Briva Iglesias","submitted_at":"2025-05-02T20:02:13Z","abstract_excerpt":"Large language models (LLMs) and multi-agent orchestration are touted as the next leap in machine translation (MT), but their benefits relative to conventional neural MT (NMT) remain unclear. This paper offers an empirical reality check. We benchmark five paradigms, Google Translate (strong NMT baseline), GPT-4o (general-purpose LLM), o1-preview (reasoning-enhanced LLM), and two GPT-4o-powered agentic workflows (sequential three-stage and iterative refinement), on test data drawn from a legal contract and news prose in three English-source pairs: Spanish, Catalan and Turkish. Automatic evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01560","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/2505.01560/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":"2505.01560","created_at":"2026-07-05T10:58:00.011239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01560v1","created_at":"2026-07-05T10:58:00.011239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01560","created_at":"2026-07-05T10:58:00.011239+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU6KE63W75T7","created_at":"2026-07-05T10:58:00.011239+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU6KE63W75T7J2TF","created_at":"2026-07-05T10:58:00.011239+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU6KE63W","created_at":"2026-07-05T10:58:00.011239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI","json":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI.json","graph_json":"https://pith.science/api/pith-number/XU6KE63W75T7J2TF6VIIQDJ6SI/graph.json","events_json":"https://pith.science/api/pith-number/XU6KE63W75T7J2TF6VIIQDJ6SI/events.json","paper":"https://pith.science/paper/XU6KE63W"},"agent_actions":{"view_html":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI","download_json":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI.json","view_paper":"https://pith.science/paper/XU6KE63W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01560&json=true","fetch_graph":"https://pith.science/api/pith-number/XU6KE63W75T7J2TF6VIIQDJ6SI/graph.json","fetch_events":"https://pith.science/api/pith-number/XU6KE63W75T7J2TF6VIIQDJ6SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI/action/storage_attestation","attest_author":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI/action/author_attestation","sign_citation":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI/action/citation_signature","submit_replication":"https://pith.science/pith/XU6KE63W75T7J2TF6VIIQDJ6SI/action/replication_record"}},"created_at":"2026-07-05T10:58:00.011239+00:00","updated_at":"2026-07-05T10:58:00.011239+00:00"}