{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04173", "kind": "paper", "url": "https://arxiv.org/abs/2609.04173"}], "categories": ["General AI", "Speech & Audio", "cs.CL"], "description": {"en": "A collection of human-authored and peer-reviewed examples in text, image, audio, and video that break leading machine translation models, with handcrafted verification rules for each example."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04173", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04173", "title": "Last Translation Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.04173", "modality": null, "name": "Last Translation Benchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_last-translation-benchmark_d81900c1", "origin_source": "arxiv", "recognition_confidence": "0.45", "record_sha256": "a2afc76e60f2468aedda21ce173133d6b2ca1f490c77be14a92bec1a4ee34570", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-07T00:42:15.394147Z", "source_url": "https://arxiv.org/abs/2609.04173"}, "publisher": null, "released": "2026-09-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04173", "source_url": "https://arxiv.org/abs/2609.04173"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04173", "source": "claire_radar", "source_benchmark_id": "2609.04173", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-09-04", "attemptedAt": "2026-09-04T06:36:46.783164Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2609.04173", "observedAt": "2026-09-04T06:36:46.783164Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-04T06:36:46.783164Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The paper lacks artifact links and details are insufficient to assess likely attention within the first week.", "score": 0}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-07T00:42:15.394147Z", "inputHash": "2f1729f2ddb6e1c6c0971ffff1e4feb8baa274943f0f1d080eebeff4cadc4d52", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models.", "canonicalNameSource": "abstract", "decisionReason": "No artifact evidence or public link is provided, and the abstract does not confirm a released dataset or evaluation code, so the existence of a publicly reusable benchmark is unclear.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-07T00:42:15.394147Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A collection of human-authored and peer-reviewed examples in text, image, audio, and video that break leading machine translation models, with handcrafted verification rules for each example.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models."}, "familyId": "bmf_308de371cd6c", "firstSeenAt": "2026-09-04", "heat": null, "id": "bm_last-translation-benchmark_d81900c1", "indexedAt": "2026-09-04T06:13:54.443310Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.04173", "pdf": "https://arxiv.org/pdf/2609.04173", "project": null, "report": "https://arxiv.org/abs/2609.04173"}, "metrics": [], "motivation": "For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases.", "name": "Last Translation Benchmark", "oneLine": "A collection of human-authored and peer-reviewed examples in text, image, audio, and video that break leading machine translation models, with handcrafted verification rules for each example.", "paperTitle": "Last Translation Benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04173", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-04T06:13:54.443310Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.3, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.19460147417678111, "value": 2}}, "confidence": "Low", "coverage": 0.3, "rank": null, "score": 41}, "method": "attention-ranking-v13", "rank": null, "score": 41}, "90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.19460147417678111, "value": 2}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 45}, "method": "attention-ranking-v13", "rank": null, "score": 45}, "today": {"confidence": "Low", "coverage": 0.45, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 1, "historyDate": "2026-09-03", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": 0.5, "percentile": 0.5, "value": 2}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.7, "role": "bonus", "value": 70}}, "confidence": "Low", "coverage": 0.45, "rank": 3, "score": 55}, "method": "attention-ranking-v13", "rank": 3, "score": 55}}, "readiness": "Paper only", "recognitionConfidence": 0.45, "relation": "evaluates_only", "releasedAt": "2026-09-03", "source": {"authors": ["Vil\\'em Zouhar and Niyati Bafna and Mukund Choudhary and Maike Z\\\"ufle and Sara Rajaee and Pinzhen Chen and Jannis Vamvas and Sara Papi and Ona de Gibert and Bhavitvya Malik and Eliya Habba and Orfeas Menis Mastromichalakis and Patr\\'icia Schmidtov\\'a and Michelle Wastl and Sheriff Issaka and Leshem Choshen and Stella Biderman and Antonis Anastasopoulos and Jan Niehues and Rico Sennrich and Mrinmaya Sachan and Ond\\v{r}ej Bojar and Kenton Murray and J\\\"org Tiedemann and Alham Fikri Aji and Philipp Koehn and Christof Monz and Alexandra Birch and Sowmya Vajjala and Chalamalasetti Kranti and Cristina Espa\\~na-Bonet and Nobin Sarwar and David Kacz\\'er and Shunta Asano and Malik Marmonier and Daban Q. Jaff and Vaisakhi Mishra and Hend Al- Khalifa and Gabriele Sarti and Sourajit Saha and Nils Rehlinger and Juan Daniel Cuervo Villa and Jonathan Tonglet and Saugata Purkayastha and Dominik Mach\\'a\\v{c}ek and Jagannathan Ramanujam and Heejin Do and Zuzana Nadova and Fred Philippy and Fabian Retkowski and Maria Lymperaiou and Silvia Casola and Hanna Yukhymenko and Shubhashis Roy Dipta and Sangwon Ryu and Andr\\'es Jerez and Ron Keinan and Shuaib Shuaib Yusuf and Avantica Vempati and Maria Carmen Staiano and Sukannya Purkayastha and Adrian Cosma and Vitalii Babenko and Erivan Inan and Aviral Nigam and Wafa Aissa and Fatima Haouari and Venkata Prasanth Kumar Gummadi and Mehdi Jafarzadeh and Valentin Scourneau and Lukas Edman and Kaiser Sun and Shaomu Tan and Mohammad Sadegh Gholizadeh and Johannes-Rudolf David and Dipankar Srirag and Javier Garc\\'ia Gilabert and Ruta Binkyte and Manar Ali and Ana-Maria Bucur and Sabry E. Farrag and Youssef Saber and Yihong Liu and Jean Maillard and Cojocaru Nicoleta and Xiaochuang Yuan and Sina Ahmadi and Philipp Mondorf and Kaustubh Dhole and Roman Wixinger and Shenbin Qian and Manuel Tuor and Sergey Troshin and Jonathan Yahav and Fida Mohammad Thoker and Amir Arsalan Rezapour and Lance Calvin Lim Gamboa and Manon Reusens and K\\\"atriin Kukk and Koel Dutta Chowdhury and Giuseppe Gallipoli and Christian Hoang and Shaswati Saha and Seth Aycock and Jan Koco\\'n and Bo Chen and Linh Vu and Vatsal Venkatkrishna and Arafat Ahsan and Luan Thanh Nguyen and Hassan Soliman and Daryna Dementieva and Theresia Veronika Rampisela and Ngoc Quynh Tram Do and Marius Huber and Kazuki Egashira and Azmine Toushik Wasi and Vladislav Poritski and Mike Zhang and Deep Shah and Paul Gavrikov and Luis Frentzen Salim and David Africa and R. Damanhuri and Bello Umar Bello and Anumit Garg and Gengyu Rao and Pawan Sasanka Ammanamanchi and Kamile Dementaviciute and Andrianos Michail and L D M S Sai Teja and Dawei Zhu and Yi Fan and Wei Liu and Farhan Farsi and Elias Herranen and Sankalan Pal Chowdhury and Karen Sanchez and Farzad Shami and Ashok Urlana and Zimu Wang and Tomasz Limisiewicz and Priyaranjan Pattnayak and Marii Ojastu and Hongbin Na and Emilian Radoi and Chenyi Zhao and Carlos Hinojosa and Andrea Gregor de Varda and Zaid Alyafeai and Reem Alzahrani and Nehal Kathrotia and Alex Fl\\\"uckiger and Ulysses Sekai Tully Carr and Jimson Paulo Layacan and Guy Kaplan and Ritwik Tiwari and Rishit Dagli and Oksana Volchek and Isaac R Caswell and Bowen Yi and Blanka K\\\"ov\\'er and Amir Hossein Yari and Aicha Chorana and Zhengxiang Wang and Selja Ker\\\"anen and Samuel Simko and Joy Olusanya and Jenny Chim and Enzo Doyen and Vivek Harsha Lakkamaneni and Sophia Conrad and Pouya Sadeghi and Panayiotis Panayiotou and Luis Lara and Jannatul Nayem and Eran Yahav and Debanshu Das and Antonia Karamolegkou and Anmol Goel and Aishik Mandal and Tommaso Cerruti and Raoyuan Zhao and Mykola Haltiuk and Thura Aung and Naser Almousa and Amir Hossein Kargaran and Rachel Bawden and Qiaoyuan Zheng and Mateusz Lango and Beni Egressy and Fidel Rodr\\'iguez Vel\\'asquez and Natchapon Jongwiriyanurak and Minh Ngoc Do and Marco Gaido and Lena Libon and Dzmitry Kuzmin and Badal Nyalang and Antoine Taroni and Andrei Niculae and Abdulaziz Nura Kani and Rushikesh Zawar and Marek \\v{S}uppa and Beatrice Savoldi and Andreas Simons and Rayyan Merchant and Ilai Yaron Levy and Francesco Pinto and Ziyi Yang and Yolanda Xavier and Samuel Frontull and Muhammad Ravi Shulthan Habibi and Kenneth Enevoldsen and Harris Abdul Majid and Francesca Padovani and Tim Graf and Tatiana Bielakova and Sharifa Djurabaeva and Shaoxiong Ji and Raia Abu Ahmad and Pavel Stepachev and Jirui Qi and Ayush Sunil Munot and Alireza Pakniat and Ayla Rigouts Terryn and Yuxing Lu and Yurii Paniv and Xiyan Fu and Tosin Adewumi and Sunisth Kumar and St\\'ephane J.P.S. Thunus and Shree Harsha Bokkahalli Satish and Shayan Bali and Prakhar Gupta and Papa Abdou Karim Karou Diallo and Matija Akrap and Marko Culjak and Krist\\'yna Onderkov\\'a and Joseph Attieh and Esrael Teferi Tensay and Elisabeth Fittschen and Beno\\^it Sagot and Jingwei Ni and Yu Fan"], "categories": ["cs.CL"], "id": "2609.04173", "title": "Last Translation Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04173"}, "sourceUpdatedAt": "2026-09-03T17:54:45Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It targets the saturation of standard machine translation benchmarks and the unreliability of automatic metrics by providing actionable failure-case evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
