datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
patch-aliasing-bayesian
Patch-Aliasing Bayesian Analysis Data
Raw and processed data from the Bayesian analysis of structural patch-aliasing in Chronos-Bolt Tiny.
Companion to the model weights at federicosabbadini/chronos-bolt-patch-aliasing-models.
Structure
clean_15model/ # 15 preregistered (P,S) configurations
full_22model/ # all 22 configurations (adds 7 robustness checks)
h1_fixed_offset/ # supplementary H1 analysis with fixed offset
Each run folder… See the full description on the dataset page: https://huggingface.co/datasets/federicosabbadini/patch-aliasing-bayesian.bayesian-benchmarksp2-etf-sv-inverse-bayesian-resultsbayesian-llm-safety-inference
Bayesian Latent Safety-Trait Dataset
Summary
This dataset supports Bayesian latent-trait analysis of language-model safety behavior.
It contains 90 benchmark-derived roots, three matched prompt variants per root, responses
from four target models over five runs, two independent LLM ratings per response, and one
human rating for a stratified 540-response calibration subset.
The three dimensions are harmful compliance, sycophancy, and agentic protocol violation.… See the full description on the dataset page: https://huggingface.co/datasets/Charly-X/bayesian-llm-safety-inference.p2-etf-bayesian-nonparametric-hdp-resultsrepro-evidence-icl-provably-bayesian
Evidence trail — In-Context Learning Is Provably Bayesian Inference
Full evidence for an automated claim-by-claim audit of
In-Context Learning Is Provably Bayesian Inference, produced by
Lemma, an AI-scientist pipeline built
for re:AGENT (Founders Inc, Aug 15–16 2026).
Verdict: 3 supported / 0 falsified / 3 inconclusive
of 6 extracted claims. Judge verdict: PASS (5/5).
Claim
Title
Verdict
C1
Risk Decomposition Identity
supported
C2
Coupled p-N Scaling of Bayes Gap… See the full description on the dataset page: https://huggingface.co/datasets/Papajams/repro-evidence-icl-provably-bayesian.p2-etf-svi-bayesian-resultsrepro-on-regret-bounds-of-thompson-sampling-for-bayesian-optimization-traces
Agent traces
Agent sessions published from a Trackio Logbook.
Bayesian_WSSbayesian-data-100-perResidual-Bayesian-AttentionThis collection contains six commonly used regression datasets from the UCI Machine Learning Repository.
1. California Housing
File: california_housing.csv
Samples: 20,640
Features: 8 (MedInc, HouseAge, AveRooms, AveBedrms, Population, AveOccup, Latitude, Longitude)
Target: Median house value
Source: Scikit-learn built-in dataset
2. Household Power Consumption
File: household_power_timeseries.csv
Samples: 17,520
Features: 7 (Global active/reactive power, Voltage… See the full description on the dataset page: https://huggingface.co/datasets/guanwencan/Residual-Bayesian-Attention.gemma-bayesian-training-preference-descriptiongemma-bayesian-trainingbayesian-social-deduction
Bayesian Social Deduction Dataset
Project Page | Arxiv | Github
Dataset Description
This dataset contains a collection of game logs from Avalon social deduction games, generated for the "Bayesian Social Deduction with Graph-Informed Language Models" paper. The dataset includes games played by various agents, including humans, and different AI models, providing a rich resource for analyzing strategic communication, deception, and cooperation.
The dataset is organized into… See the full description on the dataset page: https://huggingface.co/datasets/shahabrahimirad/bayesian-social-deduction.MAS3301-Bayesian-Statisticbayesian-data-training-alternategemma-bayesian-training-preference-description-random-questions-ablationgemma-bayesian-10-interactionsgemma-bayesian-training-random-questions-ablationbayesian-coherence-lm
Bayesian Coherence of LMs — Prompt Sets
Prompt sets for measuring the Bayesian-coherence of language models via the
incoherence certificate |log R| (local) and the cross-lingual/transitive cycle
ratio |log cycle| (global). A model's prompts induce an implicit joint
distribution over entities and relations; a model is coherent on a quartet iff
its loop of conditional inferences multiplies back to 1 (log R = 0).
Code: https://github.com/suchirsalhan/bayesian-coherence-lm… See the full description on the dataset page: https://huggingface.co/datasets/suchirsalhan/bayesian-coherence-lm.