{"article":{"annotation":{"article_id":"atscale-benchmark-finds-semantic-layer-improves-seven-models","available_at":"2026-10-16T10:36:46.336433Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"d228939923f4f4bf6598da9356b6531ec1f82e0f724a1ebb123d81407028c338","input_sha256":"79259180c4081d963c8f72c21456ab4f0cd14f0f1100bae73f82a34511cf5bcb","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"US","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/"]}],"geometry":null,"id":"iso3166-1:US","kind":"country-or-area","labels":{"ar":"الولايات المتحدة الأمريكية","en":"United States of America","es":"Estados Unidos de América","fr":"États-Unis d’Amérique"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:20001298","confidence":null,"confidence_method":null,"evidence":[{"field":"en.title+en.summary","language":"en","note":"Subject suggested from the title or summary: AI","source_urls":["https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/"]}],"method":"controlled-rules-v1","rule_id":"artificial-intelligence","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=pt","category":"technology","content":{"key_points":[],"paragraphs":["Em 15 de outubro, a AtScale publicou resultados de uma avaliação de sete grandes modelos de linguagem no benchmark BIRD-Interact. A empresa afirmou que todos os modelos testados tiveram maior precisão nas 410 perguntas sobre dados empresariais quando usados com uma camada semântica, e que um modelo de pesos abertos se aproximou dos modelos de ponta.","Os resultados vêm da experiência da própria AtScale; a empresa os classifica como preliminares e informa que a equipe BIRD não os verificou. O teste compara consultas diretas a tabelas corporativas brutas com consultas baseadas em métricas de negócio definidas. Ele não demonstra que todas as empresas terão os mesmos ganhos."],"sections":[]},"corrections":[],"country":"US","data":{"blocks":[{"description":{"ar":"تقييم أتسكيل باستخدام BIRD-Interact","de":"AtScale-Auswertung mit BIRD-Interact","en":"AtScale BIRD-Interact evaluation","es":"Evaluación BIRD-Interact de AtScale","fr":"Évaluation BIRD-Interact d’AtScale","pt":"Avaliação BIRD-Interact da AtScale","tr":"AtScale’ın BIRD-Interact değerlendirmesi"},"id":"source-record","items":[{"date":"2026-10-15","description":{"ar":"سبعة نماذج و410 أسئلة عن بيانات الأعمال؛ وأُبلغ عن تحسن كل نموذج مع الطبقة الدلالية.","de":"Sieben Modelle und 410 Fragen zu Geschäftsdaten; für jedes Modell wurde mit der semantischen Ebene eine Verbesserung gemeldet.","en":"Seven models and 410 business-data questions; improvement with the semantic layer was reported for each model.","es":"Siete modelos y 410 preguntas sobre datos empresariales; se informó de mejoras con la capa semántica en todos.","fr":"Sept modèles et 410 questions sur des données métier; une amélioration avec la couche sémantique a été signalée pour chacun.","pt":"Sete modelos e 410 perguntas sobre dados empresariais; foi relatada melhora com a camada semântica em todos.","tr":"Yedi model ve 410 iş verisi sorusu; semantik katmanla her modelde iyileşme bildirildi."},"label":{"ar":"نطاق التقييم","de":"Umfang der Auswertung","en":"Evaluation scope","es":"Alcance de la evaluación","fr":"Périmètre de l’évaluation","pt":"Escopo da avaliação","tr":"Değerlendirme kapsamı"},"status":"occurred"}],"methodology":{"ar":"تعكس الأرقام التقييم الأولي للشركة؛ ولم يتحقق منها BIRD ولا تمثل نتائج مستقلة.","de":"Die Zahlen stammen aus der vorläufigen Auswertung des Unternehmens; BIRD hat sie nicht geprüft und sie sind keine unabhängigen Ergebnisse.","en":"Figures reflect the company’s preliminary evaluation; they are not verified by BIRD and are not independent results.","es":"Las cifras reflejan la evaluación preliminar de la empresa; BIRD no las ha verificado y no son resultados independientes.","fr":"Les chiffres reflètent l’évaluation préliminaire de l’entreprise; ils ne sont pas vérifiés par BIRD et ne constituent pas des résultats indépendants.","pt":"Os números refletem a avaliação preliminar da empresa; não foram verificados pelo BIRD e não são resultados independentes.","tr":"Değerler şirketin kendi ön değerlendirmesinden aktarılmıştır; BIRD tarafından doğrulanmamıştır ve bağımsız sonuç sayılmaz."},"sourceUrls":["https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/"],"title":{"ar":"أتسكيل: الطبقة الدلالية حسّنت النماذج السبعة المختبرة","de":"AtScale zufolge verbesserte die semantische Ebene alle sieben getesteten Modelle","en":"AtScale says semantic layer improved all seven AI models tested","es":"AtScale afirma que la capa semántica mejoró los siete modelos probados","fr":"AtScale affirme que la couche sémantique a amélioré les sept modèles testés","pt":"AtScale afirma que a camada semântica melhorou os sete modelos testados","tr":"AtScale: semantik katman test edilen yedi yapay zekâ modelini de iyileştirdi"},"type":"events","updatedAt":"2026-10-16T10:20:41+00:00"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models/data/source-record?lang=pt&format=csv","json":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models/data/source-record?lang=pt&format=json"},"id":"source-record"}],"data_types":["events"],"editorial_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-2ee32e2f-512a-55a4-add2-111f3e8508fa","event_period":"2026-10-15","event_period_basis":"event-or-reference-period","id":"atscale-benchmark-finds-semantic-layer-improves-seven-models","image":null,"importance":0.6,"language":"pt","modified_at":"2026-10-16T10:36:23+00:00","publication_basis":"publication-record","published_at":"2026-10-16T10:36:23+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"atscale-benchmark-finds-semantic-layer-improves-seven-models","sources":[{"checkedAt":"2026-10-16","name":"AtScale","publishedAt":"2026-10-15","url":"https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/"}],"summary":"A empresa relatou maior precisão de sete grandes modelos de linguagem em perguntas sobre dados empresariais com uma camada semântica.","text":"A empresa relatou maior precisão de sete grandes modelos de linguagem em perguntas sobre dados empresariais com uma camada semântica.\n\nEm 15 de outubro, a AtScale publicou resultados de uma avaliação de sete grandes modelos de linguagem no benchmark BIRD-Interact. A empresa afirmou que todos os modelos testados tiveram maior precisão nas 410 perguntas sobre dados empresariais quando usados com uma camada semântica, e que um modelo de pesos abertos se aproximou dos modelos de ponta.\n\nOs resultados vêm da experiência da própria AtScale; a empresa os classifica como preliminares e informa que a equipe BIRD não os verificou. O teste compara consultas diretas a tabelas corporativas brutas com consultas baseadas em métricas de negócio definidas. Ele não demonstra que todas as empresas terão os mesmos ganhos.","title":"AtScale afirma que a camada semântica melhorou os sete modelos testados","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=en","language":"en","url":"https://newsverum.com/en/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=es","language":"es","url":"https://newsverum.com/es/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=de","language":"de","url":"https://newsverum.com/de/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},{"api_url":"https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"}],"url":"https://newsverum.com/pt/news/atscale-benchmark-finds-semantic-layer-improves-seven-models"},"version":"1"}