{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:49:49.716Z","data":{"recordId":"wsa_9hg6qzza9sms","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/FINAL-Bench/Darwin-27B-ZTC","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-27T01:40:35.745Z","detectedPublishedAt":"2026-10-08T04:11:03.000Z","rights":"original"}],"claims":[{"id":"8f819293-554d-4ed7-b857-5f63bcf6f7c1","kind":"capability","statement":"The model returns a full probability distribution over the options of each question.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"**A zero-token decision engine from the Darwin family.** Darwin-27B-ZTC reads a piece of state and a set of typed questions, and returns a full probability distribution over the options of every question.","rights":"original"}}]},{"id":"be4879f6-d925-461f-a3d7-bf8eb12dc4c1","kind":"capability","statement":"It generates no tokens and uses one forward pass per question.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"It does this in one forward pass per question.","rights":"original"}}]},{"id":"10388077-5162-4a1d-be7b-f352aaa464a4","kind":"availability","statement":"The repository includes BF16 backbone weights, a readout head, configuration files, tokenizer files, and inference code.","citations":[{"source":1,"supportProbability":0.93,"supports":true,"quote":null}]},{"id":"82100339-87d2-4bb3-8352-67b3ee98c3a2","kind":"deployment","statement":"Inference requires a GPU with space for about 54 GB of BF16 weights.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"It needs `torch`, `transformers` (Qwen3.5 support), `safetensors` and `pillow`, and a GPU with space for about 54 GB of BF16 weights.","rights":"original"}}]},{"id":"a59d5d6c-820f-4db8-9715-87e6ef9768b1","kind":"recommendation-relevant","statement":"On the listed Typed Decisions test run, the model scored 0.743 accuracy across 2,000 decisions.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null}]}]},"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."}}}