datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
FabricationGuard-linearprobe-qwen36-27b
🛡️ FabricationGuard — Linear Probe for Qwen3.6-27B
Activation-probe fabrication detection for Qwen3.6-27B. AUROC 0.88 cross-task on SimpleQA, -88% confident-wrong rate reduction in mitigation mode, ~1ms scoring latency.
This is the OpenInterp FabricationGuard production probe — derived from a multi-feature linear probe on the residual stream at layer 31, trained on a multi-benchmark hallucination corpus, validated cross-task on held-out splits.
Value
Base model… See the full description on the dataset page: https://huggingface.co/datasets/caiovicentino1/FabricationGuard-linearprobe-qwen36-27b.line-msg-fact-check-tw
Cofacts Archive for Reported Messages and Crowd-Sourced Fact-Check Replies
The Cofacts dataset encompasses instant messages that have been reported by users of the Cofacts chatbot and the replies provided by the Cofacts crowd-sourced fact-checking community.
Attribution to the Community
This dataset is a result of contributions from both Cofacts LINE chatbot users and the community fact checkers.
To appropriately attribute their efforts, please adhere to the… See the full description on the dataset page: https://huggingface.co/datasets/Cofacts/line-msg-fact-check-tw.ReasoningGuard-linearprobe-qwen36-27b
🧠 ReasonGuard v0.2 — Linear Probe at L55 / mid_think on Qwen3.6-27B
v0.2 update (2026-04-29) — multi-bench training thesis FALSIFIED.
v0.2 trained on combined GSM8K + StrategyQA + MATH (455 samples, 45.8% halu rate) — same methodology that gave FabricationGuard cross-task AUROC 0.882. Within-bench improved on GSM8K (0.888 → 0.908). Cross-domain transfer still fails: StrategyQA 0.612, MATH 0.500 (chance). Position-of-faithfulness in the deep residual stream is more strongly… See the full description on the dataset page: https://huggingface.co/datasets/caiovicentino1/ReasoningGuard-linearprobe-qwen36-27b.LinearEquationsThe linear equations in this dataset are in the form:
zy + ay + b + n = py + dy + c + r
with integer coefficients ranging from -10 to 10.