{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-31T03:35:37.195Z","data":{"recordId":"wsa_yjg4cjy96ppc","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/davanstrien/ultrabert-380m-curation","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-31T00:47:44.559Z","detectedPublishedAt":"2026-10-28T14:59:01.000Z","rights":"original"}],"claims":[{"id":"924ef1d6-2fe4-4502-9d62-a21d0af033a3","kind":"capability","statement":"The model returns probabilities for options in choice, yes/no (noul), and ordered-level (score) questions.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"ec8a492e-6107-4d43-9c54-afe95cce6acf","kind":"capability","statement":"It is intended for curation questions about web pages, prompts, maths problems, and library records.","citations":[{"source":1,"supportProbability":0.95,"supports":true,"quote":{"text":"| Good at           | curation questions on web pages, prompts, maths problems and library records: topic, format, educational value, difficulty, task type, validity, catalogue class…","rights":"original"}}]},{"id":"4294000b-5d2f-484c-961b-0fa4f195772e","kind":"availability","statement":"The model, training data, and training recipe are released publicly.","citations":[{"source":1,"supportProbability":0.86,"supports":true,"quote":{"text":"A 380M-parameter decision model for data curation, with **its training data and the recipe that made it, both","rights":"original"}}]},{"id":"233f2a42-d9a9-4963-b8c6-ff186c77e861","kind":"deployment","statement":"The Jev / System One API can run on CPU or GPU.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"In Python, without the server: `from jev_api import system_one; system_one(state, questions)`.","rights":"original"}}]},{"id":"6280a246-6358-426c-a5e4-07a4b551bc7c","kind":"recommendation-relevant","statement":"The model was tested in English only, and its API refuses inputs over 4,096 tokens.","citations":[{"source":1,"supportProbability":0.95,"supports":true,"quote":{"text":"- **Length.** The API refuses inputs over 4,096 tokens (the training length); the fast path truncates at 2,048","rights":"original"}}]},{"id":"27378273-be31-44bb-a9fc-a4f3bc336847","kind":"recommendation-relevant","statement":"The release describes the model as a curation specialist, not a general decision model.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"A specialist, not a general decision model                                                                                                                                                                            |","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}