{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CT5BSZ7777YKOQ7JMEKPKOSBBY","short_pith_number":"pith:CT5BSZ77","schema_version":"1.0","canonical_sha256":"14fa1967fffff0a743e96114f53a410e2be6e6c691326a5c9b26cd66acdfd47c","source":{"kind":"arxiv","id":"2412.18367","version":6},"attestation_state":"computed","paper":{"title":"Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Houda Bouamor, Iman Ouzzani, Jiarui Liu, Lechen Zhang, Mona Diab, Tianyue Ou, Wenkai Li, Zhijing Jin","submitted_at":"2024-12-24T11:50:18Z","abstract_excerpt":"The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. We introduce GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms are translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset's quality is benchmarked against existing resources, demonstrating superior translation accuracy through"},"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":"2412.18367","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T11:50:18Z","cross_cats_sorted":[],"title_canon_sha256":"c0eb98ff2eb6e03317f48e03b97e3f2bce124b67e2f669c511ad885dcb426719","abstract_canon_sha256":"fece391b7eeba985f199e6eace7c58be62ca0509a35d1f982c7915eed55f4986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:17.665668Z","signature_b64":"JIrgGYNjS7OMEL9TAJO4EAHhBnEuzQC2GiCIvC25mkyYnvCm6ufff9a0LwCxKPar0pcBHXuAaIDKkMTlR1WlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14fa1967fffff0a743e96114f53a410e2be6e6c691326a5c9b26cd66acdfd47c","last_reissued_at":"2026-07-05T11:13:17.665172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:17.665172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Houda Bouamor, Iman Ouzzani, Jiarui Liu, Lechen Zhang, Mona Diab, Tianyue Ou, Wenkai Li, Zhijing Jin","submitted_at":"2024-12-24T11:50:18Z","abstract_excerpt":"The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. We introduce GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms are translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset's quality is benchmarked against existing resources, demonstrating superior translation accuracy through"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18367","kind":"arxiv","version":6},"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/2412.18367/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":"2412.18367","created_at":"2026-07-05T11:13:17.665225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18367v6","created_at":"2026-07-05T11:13:17.665225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18367","created_at":"2026-07-05T11:13:17.665225+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT5BSZ7777YK","created_at":"2026-07-05T11:13:17.665225+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT5BSZ7777YKOQ7J","created_at":"2026-07-05T11:13:17.665225+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT5BSZ77","created_at":"2026-07-05T11:13:17.665225+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/CT5BSZ7777YKOQ7JMEKPKOSBBY","json":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY.json","graph_json":"https://pith.science/api/pith-number/CT5BSZ7777YKOQ7JMEKPKOSBBY/graph.json","events_json":"https://pith.science/api/pith-number/CT5BSZ7777YKOQ7JMEKPKOSBBY/events.json","paper":"https://pith.science/paper/CT5BSZ77"},"agent_actions":{"view_html":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY","download_json":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY.json","view_paper":"https://pith.science/paper/CT5BSZ77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18367&json=true","fetch_graph":"https://pith.science/api/pith-number/CT5BSZ7777YKOQ7JMEKPKOSBBY/graph.json","fetch_events":"https://pith.science/api/pith-number/CT5BSZ7777YKOQ7JMEKPKOSBBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY/action/storage_attestation","attest_author":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY/action/author_attestation","sign_citation":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY/action/citation_signature","submit_replication":"https://pith.science/pith/CT5BSZ7777YKOQ7JMEKPKOSBBY/action/replication_record"}},"created_at":"2026-07-05T11:13:17.665225+00:00","updated_at":"2026-07-05T11:13:17.665225+00:00"}