{"id":"70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7","title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","argument":"Authors Iaroslav Chelombitko and Mika Hämäläinen ask whether rule-based resources improve machine translation from Komi-Zyrian, Moksha, Erzya and Udmurt into English, and whether models benefit more from analyses supplied in the prompt or tools they call through the Model Context Protocol (MCP). In a manual evaluation, an expert linguist judged every English output from the strongest model across three conditions. Accepted translations rose from 13 to 43 out of 272 when analyses were put in the prompt, and to 55 with tools attached. The authors attribute the gain to the bilingual dictionary: for Udmurt, whose dictionary has no English side, the prompt condition brought no gain; for the other languages, an English gloss reached the prompt for 74 to 80% of source words. The comparison also exposes a practical hurdle: tool calling was harder to get working than prompt injection. Of 31 open-weight models, 14 never called a tool, usually because they could not produce a usable call, and half of calls made named an unsupported language. The authors release the data set, model outputs and tool-call logs. The abstract does not give enough detail to assess how these results vary across models or translation settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract reports manual judgments by an expert linguist but does not provide the evaluation criteria or further methodological detail. The results described are for the strongest model under three conditions; the abstract does not establish how results generalize across other models or translation settings.","speaker":{"name":"Chelombitko, Iaroslav, Hämäläinen, Mika","roleAtSource":"Article author"},"source":{"title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.19439","publishedAt":"2026-11-14","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors compare prompt-supplied analyses with model-called tools for translating four endangered Uralic languages into English.","excerpt":"We ask whether giving a model access to these resources improves machine translation from the four languages into English, and whether it matters how the access is provided","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"In manual evaluation of 816 outputs across three conditions, accepted translations rose from 13 to 43 out of 272 with prompt-supplied analyses, and to 55 with tools attached.","excerpt":"With the analyses in the prompt, the number of accepted translations rises from 13 to 43 out of 272; with the tools attached it rises to 55.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"The authors say the gains came from the bilingual dictionary; Udmurt's dictionary lacks an English side and its prompt-based condition brought no gain.","excerpt":"The gain comes from the bilingual dictionary. For Udmurt, whose dictionary has no English side, the prompt-based condition brings no gain at all","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"Tool use was unreliable among the 31 open-weight models tested: 14 never called a tool, and half of calls made named an unsupported language.","excerpt":"Of 31 open-weight models, 14 never call a tool, 11 of them because they cannot produce a usable call, and half of the calls that are made name a language the toolkit does not support.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"The authors state that they release the data set, model outputs and tool-call logs.","excerpt":"We release the data set, every model output and all tool-call logs.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.19439","checkedAt":"2026-11-17T11:48:10.423Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would the results hold across models and translation settings beyond the strongest model evaluated here?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","summary":"Authors Iaroslav Chelombitko and Mika Hämäläinen ask whether rule-based resources improve machine translation from Komi-Zyrian, Moksha, Erzya and Udmurt into English, and whether models benefit more from analyses supplied in the prompt or tools they call through the Model Context Protocol (MCP). In a manual evaluation, an expert linguist judged every English output from the strongest model across three conditions. Accepted translations rose from 13 to 43 out of 272 when analyses were put in the prompt, and to 55 with tools attached. The authors attribute the gain to the bilingual dictionary: for Udmurt, whose dictionary has no English side, the prompt condition brought no gain; for the other languages, an English gloss reached the prompt for 74 to 80% of source words. The comparison also exposes a practical hurdle: tool calling was harder to get working than prompt injection. Of 31 open-weight models, 14 never called a tool, usually because they could not produce a usable call, and half of calls made named an unsupported language. The authors release the data set, model outputs and tool-call logs. The abstract does not give enough detail to assess how these results vary across models or translation settings.","question":"Would the results hold across models and translation settings beyond the strongest model evaluated here?","claims":[{"text":"The authors compare prompt-supplied analyses with model-called tools for translating four endangered Uralic languages into English.","excerpt":"We ask whether giving a model access to these resources improves machine translation from the four languages into English, and whether it matters how the access is provided","support":"source-stated"},{"text":"In manual evaluation of 816 outputs across three conditions, accepted translations rose from 13 to 43 out of 272 with prompt-supplied analyses, and to 55 with tools attached.","excerpt":"With the analyses in the prompt, the number of accepted translations rises from 13 to 43 out of 272; with the tools attached it rises to 55.","support":"source-stated"},{"text":"The authors say the gains came from the bilingual dictionary; Udmurt's dictionary lacks an English side and its prompt-based condition brought no gain.","excerpt":"The gain comes from the bilingual dictionary. For Udmurt, whose dictionary has no English side, the prompt-based condition brings no gain at all","support":"source-stated"},{"text":"Tool use was unreliable among the 31 open-weight models tested: 14 never called a tool, and half of calls made named an unsupported language.","excerpt":"Of 31 open-weight models, 14 never call a tool, 11 of them because they cannot produce a usable call, and half of the calls that are made name a language the toolkit does not support.","support":"source-stated"},{"text":"The authors state that they release the data set, model outputs and tool-call logs.","excerpt":"We release the data set, every model output and all tool-call logs.","support":"source-stated"}],"limitations":["The abstract reports manual judgments by an expert linguist but does not provide the evaluation criteria or further methodological detail.","The results described are for the strongest model under three conditions; the abstract does not establish how results generalize across other models or translation settings."],"mediaId":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","correctionReason":null,"id":"70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7","publicationId":"240cb954-61aa-408c-8f77-5eff57263087","version":1,"sourceUrl":"https://arxiv.org/abs/2611.19439","sourceTitle":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-14","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-17T08:30:57.271Z","createdAt":"2026-11-17T11:16:46.380Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","kind":"article","url":"https://arxiv.org/abs/2611.19439","sourceUrl":"https://arxiv.org/abs/2611.19439","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-17T11:05:39.610Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.19439","checkedAt":"2026-11-17T11:48:10.423Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v9","mediaId":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","confidence":0.6499999999999999,"provider":"typesafe","model":"jev-1.13.0","inputHash":"d84042c14f4e39aa8f19690fd19bb71848515aa294878ea24c591e4172904c24","decidedAt":"2026-11-17T11:05:42.587Z"},"provenance":{"textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observationId":"938f2c27a90cc6d8a2088db3ebe0466980a972d7ad86c8355416a1d81820807c","retrievedAt":"2026-11-17T11:05:39.289Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"153fefbe-e9de-4cee-8205-3a7a8decb20c"},"reviewer":{"model":"gpt-6-luna","runId":"68f132e3-d475-4c6f-812b-225ea1a62cea"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-17T11:16:46.380Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Chelombitko, Iaroslav","url":null,"kind":"unknown"},{"name":"Hämäläinen, Mika","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Chelombitko, Iaroslav","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chelombitko, Iaroslav","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.19439","locator":"head/meta[name=author|citation_author]"},"assertionId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-17T11:48:10.423Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","sourceUrl":"https://arxiv.org/abs/2611.19439","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z"}},{"actor":{"name":"Hämäläinen, Mika","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Hämäläinen, Mika","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.19439","locator":"head/meta[name=author|citation_author]"},"assertionId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-17T11:48:10.423Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","sourceUrl":"https://arxiv.org/abs/2611.19439","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.19439","snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z","basis":"publisher-page-metadata","sourceLinks":41,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7/source"}},"canonicalUrl":"https://escapemeridian.com/readings/do-rule-based-tools-help-llms-translate-endangered-uralic-70920e8b","formats":{"html":"/readings/do-rule-based-tools-help-llms-translate-endangered-uralic-70920e8b","markdown":"/readings/do-rule-based-tools-help-llms-translate-endangered-uralic-70920e8b.md","json":"/readings/do-rule-based-tools-help-llms-translate-endangered-uralic-70920e8b.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"conditions":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-tool-use","name":"Tool use","explanation":"A model's ability to operate other software, such as a search engine, a calculator or a code runner, while it works.","referenceUrl":"https://docs.anthropic.com/en/docs/build-with-claude/tool-use/overview"},{"id":"term-prompt-injection","name":"Prompt injection","explanation":"Hidden instructions placed in a document, email or web page that try to take control of an AI system reading it.","referenceUrl":"https://en.wikipedia.org/wiki/Prompt_injection"},{"id":"term-open-weights","name":"Open weights","explanation":"A model whose trained numbers are published so others can download, run and inspect it; the license and training data may still be restricted.","referenceUrl":"https://opensource.org/ai/open-weights"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7","revision":"240cb954-61aa-408c-8f77-5eff57263087","revisionKind":"publication-id","title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","url":"https://escapemeridian.com/readings/do-rule-based-tools-help-llms-translate-endangered-uralic-70920e8b"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.19439","revision":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","revisionKind":"sha256-source-text","title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","url":"https://arxiv.org/abs/2611.19439"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."},"revisions":[{"id":"70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7","title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","argument":"Authors Iaroslav Chelombitko and Mika Hämäläinen ask whether rule-based resources improve machine translation from Komi-Zyrian, Moksha, Erzya and Udmurt into English, and whether models benefit more from analyses supplied in the prompt or tools they call through the Model Context Protocol (MCP). In a manual evaluation, an expert linguist judged every English output from the strongest model across three conditions. Accepted translations rose from 13 to 43 out of 272 when analyses were put in the prompt, and to 55 with tools attached. The authors attribute the gain to the bilingual dictionary: for Udmurt, whose dictionary has no English side, the prompt condition brought no gain; for the other languages, an English gloss reached the prompt for 74 to 80% of source words. The comparison also exposes a practical hurdle: tool calling was harder to get working than prompt injection. Of 31 open-weight models, 14 never called a tool, usually because they could not produce a usable call, and half of calls made named an unsupported language. The authors release the data set, model outputs and tool-call logs. The abstract does not give enough detail to assess how these results vary across models or translation settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract reports manual judgments by an expert linguist but does not provide the evaluation criteria or further methodological detail. The results described are for the strongest model under three conditions; the abstract does not establish how results generalize across other models or translation settings.","speaker":{"name":"Chelombitko, Iaroslav, Hämäläinen, Mika","roleAtSource":"Article author"},"source":{"title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.19439","publishedAt":"2026-11-14","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors compare prompt-supplied analyses with model-called tools for translating four endangered Uralic languages into English.","excerpt":"We ask whether giving a model access to these resources improves machine translation from the four languages into English, and whether it matters how the access is provided","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"In manual evaluation of 816 outputs across three conditions, accepted translations rose from 13 to 43 out of 272 with prompt-supplied analyses, and to 55 with tools attached.","excerpt":"With the analyses in the prompt, the number of accepted translations rises from 13 to 43 out of 272; with the tools attached it rises to 55.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"The authors say the gains came from the bilingual dictionary; Udmurt's dictionary lacks an English side and its prompt-based condition brought no gain.","excerpt":"The gain comes from the bilingual dictionary. For Udmurt, whose dictionary has no English side, the prompt-based condition brings no gain at all","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"Tool use was unreliable among the 31 open-weight models tested: 14 never called a tool, and half of calls made named an unsupported language.","excerpt":"Of 31 open-weight models, 14 never call a tool, 11 of them because they cannot produce a usable call, and half of the calls that are made name a language the toolkit does not support.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"},{"text":"The authors state that they release the data set, model outputs and tool-call logs.","excerpt":"We release the data set, every model output and all tool-call logs.","url":"https://arxiv.org/abs/2611.19439","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.19439","checkedAt":"2026-11-17T11:48:10.423Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would the results hold across models and translation settings beyond the strongest model evaluated here?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","summary":"Authors Iaroslav Chelombitko and Mika Hämäläinen ask whether rule-based resources improve machine translation from Komi-Zyrian, Moksha, Erzya and Udmurt into English, and whether models benefit more from analyses supplied in the prompt or tools they call through the Model Context Protocol (MCP). In a manual evaluation, an expert linguist judged every English output from the strongest model across three conditions. Accepted translations rose from 13 to 43 out of 272 when analyses were put in the prompt, and to 55 with tools attached. The authors attribute the gain to the bilingual dictionary: for Udmurt, whose dictionary has no English side, the prompt condition brought no gain; for the other languages, an English gloss reached the prompt for 74 to 80% of source words. The comparison also exposes a practical hurdle: tool calling was harder to get working than prompt injection. Of 31 open-weight models, 14 never called a tool, usually because they could not produce a usable call, and half of calls made named an unsupported language. The authors release the data set, model outputs and tool-call logs. The abstract does not give enough detail to assess how these results vary across models or translation settings.","question":"Would the results hold across models and translation settings beyond the strongest model evaluated here?","claims":[{"text":"The authors compare prompt-supplied analyses with model-called tools for translating four endangered Uralic languages into English.","excerpt":"We ask whether giving a model access to these resources improves machine translation from the four languages into English, and whether it matters how the access is provided","support":"source-stated"},{"text":"In manual evaluation of 816 outputs across three conditions, accepted translations rose from 13 to 43 out of 272 with prompt-supplied analyses, and to 55 with tools attached.","excerpt":"With the analyses in the prompt, the number of accepted translations rises from 13 to 43 out of 272; with the tools attached it rises to 55.","support":"source-stated"},{"text":"The authors say the gains came from the bilingual dictionary; Udmurt's dictionary lacks an English side and its prompt-based condition brought no gain.","excerpt":"The gain comes from the bilingual dictionary. For Udmurt, whose dictionary has no English side, the prompt-based condition brings no gain at all","support":"source-stated"},{"text":"Tool use was unreliable among the 31 open-weight models tested: 14 never called a tool, and half of calls made named an unsupported language.","excerpt":"Of 31 open-weight models, 14 never call a tool, 11 of them because they cannot produce a usable call, and half of the calls that are made name a language the toolkit does not support.","support":"source-stated"},{"text":"The authors state that they release the data set, model outputs and tool-call logs.","excerpt":"We release the data set, every model output and all tool-call logs.","support":"source-stated"}],"limitations":["The abstract reports manual judgments by an expert linguist but does not provide the evaluation criteria or further methodological detail.","The results described are for the strongest model under three conditions; the abstract does not establish how results generalize across other models or translation settings."],"mediaId":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","correctionReason":null,"id":"70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7","publicationId":"240cb954-61aa-408c-8f77-5eff57263087","version":1,"sourceUrl":"https://arxiv.org/abs/2611.19439","sourceTitle":"Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-14","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-17T08:30:57.271Z","createdAt":"2026-11-17T11:16:46.380Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","kind":"article","url":"https://arxiv.org/abs/2611.19439","sourceUrl":"https://arxiv.org/abs/2611.19439","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-17T11:05:39.610Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.19439","checkedAt":"2026-11-17T11:48:10.423Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v9","mediaId":"be54431a1d04429257615a723c2c66f49714663bf6a60027a12b213bfc1fd056","confidence":0.6499999999999999,"provider":"typesafe","model":"jev-1.13.0","inputHash":"d84042c14f4e39aa8f19690fd19bb71848515aa294878ea24c591e4172904c24","decidedAt":"2026-11-17T11:05:42.587Z"},"provenance":{"textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observationId":"938f2c27a90cc6d8a2088db3ebe0466980a972d7ad86c8355416a1d81820807c","retrievedAt":"2026-11-17T11:05:39.289Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"153fefbe-e9de-4cee-8205-3a7a8decb20c"},"reviewer":{"model":"gpt-6-luna","runId":"68f132e3-d475-4c6f-812b-225ea1a62cea"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-17T11:16:46.380Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Chelombitko, Iaroslav","url":null,"kind":"unknown"},{"name":"Hämäläinen, Mika","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Chelombitko, Iaroslav","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chelombitko, Iaroslav","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.19439","locator":"head/meta[name=author|citation_author]"},"assertionId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-17T11:48:10.423Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","sourceUrl":"https://arxiv.org/abs/2611.19439","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z"}},{"actor":{"name":"Hämäläinen, Mika","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Hämäläinen, Mika","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.19439","locator":"head/meta[name=author|citation_author]"},"assertionId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-17T11:48:10.423Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","sourceUrl":"https://arxiv.org/abs/2611.19439","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.19439","snapshotId":"dc0a693ffda4cb0dca17d100611ea18cb902051a6bb00e06f38c9f30cb0a693b","contentSha256":"5e6ca451265eaaf1cc35583b4a6ea776d3fd9f19fa273708b66286a67b726caf","textHash":"88b20186373670ead76fa324ec50625240efec1912b2835ace2aac52042f493e","observedAt":"2026-11-17T11:48:10.423Z","basis":"publisher-page-metadata","sourceLinks":41,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/70920e8b2f17f167c94ce4c374f26a4e3bfced7c5d142ff3b9b141c5df639df7/source"}}}],"audits":[{"publicationId":"240cb954-61aa-408c-8f77-5eff57263087","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly names Iaroslav Chelombitko and Mika Hämäläinen as the authors. It keeps the findings attributed to their arXiv paper, including the dictionary explanation ('The authors attribute the gain').","excerpt":"Authors:Iaroslav Chelombitko, Mika Hämäläinen"},{"dimension":"summary","status":"uncertain","explanation":"The figures are faithful, but a non-specialist may not follow the central terms. 'Rule-based resources' is never explained, and the reading drops the abstract's examples (finite-state analysers, constraint grammars, bilingual dictionaries). 'Open-weight models', 'English gloss' and 'prompt injection' are also unexplained; the last can be misread as the security attack, though here it means writing analyses into the prompt. The reading also never says why the result matters: these languages have mature rule-based resources that models do not use. Smallest repair: name the three resource types and that language models do not use them, and add plain glosses or tooltips for open-weight, gloss and prompt injection.","excerpt":"among them finite-state analysers, constraint grammars and bilingual dictionaries, which language models do not use"},{"dimension":"date","status":"pass","explanation":"The originalPublished value of 2026-11-14 matches the v1 submission date shown on the arXiv page. The feed date is later.","excerpt":"[Submitted on 14 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim matches the abstract. This covers the 13, 43 and 55 out of 272 accepted translations, the 816 sentences, the dictionary explanation and the Udmurt exception, the 74 to 80% gloss coverage, and the 14 of 31 models that never called a tool (11 unable to produce a usable call). It also covers the release of the data set, outputs and logs. 'Usually' fairly renders 11 of 14. The question and limitations are framed as open issues, not claims.","excerpt":"Of 31 open-weight models, 14 never call a tool, 11 of them because they cannot produce a usable call"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page for this paper. It is the direct original source.","excerpt":null}],"createdAt":"2026-11-17T11:16:46.380Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}