datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
autocode-fresh-cf
AutoCode-RL fresh-CF
Executable training problems for AutoCode-RL: Reinforcement Learning for
Code with Verifiable Synthetic Data. A frozen GPT-5.5 setter constructs
harder and easier variants and verification packages; a separate GPT-OSS-20B
solver learns from binary program-execution rewards.
View
Problems
Description
originals
226
Source Codeforces tasks with generated verification packages
enhance
84
Harder generated variants
simplify
63
Easier generated… See the full description on the dataset page: https://huggingface.co/datasets/anonymous1926/autocode-fresh-cf.Agent-ValueBench
Agent-ValueBench
Agent-ValueBench constitutes the first comprehensive benchmark dedicated to evaluating the underlying values of autonomous agents. It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that span 28 value systems (332 dimensions).
This Hugging Face release contains both structured JSONL tables for dataset viewing and Croissant metadata generation, and the original raw benchmark artifacts.
Repository Structure… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-nips2026/Agent-ValueBench.anonymous-datasetCTSpinoPelvic1K
CTSpinoPelvic1K
A fused spine + pelvis 3D CT segmentation dataset built by patient-level
crosswalk between three public sources:
TCIA CT COLONOGRAPHY — DICOM CT volumes (prone + supine per patient)
CTSpine1K (COLONOG subset) — VerSe-convention vertebral label masks
CTPelvic1K dataset2 — sacrum + bilateral hip label masks
Annotations are placed onto the TCIA CT volume with the highest bone
coverage (HU > 200), separately per anatomy. For ~650 patients both
annotations land on the… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-neurips-ED/CTSpinoPelvic1K.lig-rebuttal-data
LIG Rebuttal Data
Anonymous data release for COLM 2026 paper: The Latent Intelligence Gap
Tiers
Tier
Contents
Size
Sufficient for
1 Results
Aggregate JSONs
~5 MB
Verify every number in rebuttal
2 Matched
Per-problem trajectories (K=32)
~700 MB
Reproduce all baselines
3 Embeddings
Last-layer hidden states
~5 GB
Reproduce IWC, verifier
Models
Model
Parameters
Benchmarks
Qwen2.5-7B-Instruct
7B
GSM8K, GPQA, AIME24, AIME25… See the full description on the dataset page: https://huggingface.co/datasets/Anonymousblind/lig-rebuttal-data.MemGUI-3K
MemGUI-3K
Anonymous Project Page | Anonymous Code | Model
MemGUI-3K is a memory-intensive mobile GUI agent trajectory dataset for training and analyzing agents that proactively manage long-horizon context. It contains teacher rollouts from MemGUI-Agent using the ConAct Context-as-Action paradigm, where the agent emits both GUI actions and context actions for history folding and UI memory management.
Code, data processing scripts, model training scripts, and evaluation tools are… See the full description on the dataset page: https://huggingface.co/datasets/memgui-agent-anonymous/MemGUI-3K.insight-ladder-imo2024
Insight Ladder - IMO 2024 Hint-Annotated Diagnostic Substrate
Supplementary dataset for "The Insight Ladder: Quantifying the Search-Execution Gap in LLM Mathematical Reasoning" (NeurIPS 2026 Evaluations & Datasets Track, double-blind submission).
Overview
A high-density diagnostic substrate for studying search failure vs execution failure in LLM mathematical proof generation. Covers 31 IMO 2024 Shortlist problems with:
4-level hint hierarchy (L1 domain, L2 first step, L3… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-insightladder-2026/insight-ladder-imo2024.GenixerForShikra-DatasetsPaper: Genixer: Empowering Multimodal Large Language Model as a Powerful Data Generator (ECCV 2024)
Arxiv: https://arxiv.org/abs/2312.06731
Description: syn_lcs_filtered60.jsonl and syn_sbu_filtered60.jsonl are two synthetic datasets produced by our Genixer_S model for advancing grounding-based multimodal understanding.
knowfeat
KnowFeat: Data, Features, and Provenance Cards
This repository contains the datasets, engineered features, domain knowledge inputs, and provenance cards for the KnowFeat paper on knowledge-guided automated feature engineering with large language models.
Repository Structure
data/
public/ # 7 public benchmark datasets (CSV)
simecny/ # Compressed transaction data (CSV.GZ)
inputs/
public_datasets/ # Domain knowledge JSONs for each dataset… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-7219/knowfeat.Geminon
AnonymousContinuousBench — Geminon (2025_09)
Configs
index — splits: public, sensitive
corpus_large — splits: train, val, test
corpus_medium — splits: train, val, test
corpus_small — splits: train, val, test
qa_small — splits: public_val, public_test, sensitive_val, sensitive_test
qa_medium — splits: public_val, public_test, sensitive_val, sensitive_test
Loading
from datasets importload_dataset
ds = load_dataset("AnonymousContinuousBench/Geminon", "index"… See the full description on the dataset page: https://huggingface.co/datasets/AnonymousContinuousBench/Geminon.SKILLRET
SkillRet Benchmark
SkillRet is a retrieval benchmark for matching natural-language user requests to
agent skills. Each retrieval document is a full agent skill, represented by its
name, short description, and full Markdown skill body. Each query describes a
realistic user request that requires one or more relevant skills.
The benchmark is built from public agent skills indexed from GitHub and contains
synthetic train and evaluation queries generated through a self-instruct-style… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-ed-benchmark/SKILLRET.Assay-aware-BindingDB
Assay-aware BindingDB
Assay-aware BindingDB is a collection of protein–ligand binding
records organized by experimental assay type. Each row represents a BindingDB
reactant set and includes its measured affinity, source publication, original
experimental context, and an assay-specific structured description.
The complete dataset remains available as the full split. Four assay
configurations provide direct access to ITC, SPR, FPA, or RBA records, and 40
training-compatible… See the full description on the dataset page: https://huggingface.co/datasets/anonymousapple/Assay-aware-BindingDB.IO-Bench
IO-Bench
IO-Bench is a 155-example evaluation dataset for mathematical economics reasoning. Each record contains a standalone economics question, a reference answer, a machine-comparable answer field, symbolic answer metadata where applicable, and review status metadata.
Unless otherwise noted, the dataset materials in this repository are licensed under the Creative Commons Attribution-NoDerivatives 4.0 International License (CC BY-ND 4.0). See LICENSE for details.… See the full description on the dataset page: https://huggingface.co/datasets/Anonymous-zxcvbnm/IO-Bench.Strudel-Synth
Strudel-Synth
Strudel-Synth is a synthetic corpus of 21,174 (MIDI, Strudel) pairs for
training and evaluating MIDI-to-Strudel decompilation, introduced in
Decomposer: Learning to Decompile Symbolic Music to Programs.
🎹 Live demo: anonymousgiraffe/decomposer-demo
🤗 Model: anonymousgiraffe/Decomposer-Qwen3-8B
Each pair consists of a Strudel program distilled from Claude-Opus-4.6 (conditioned on independently sampled musical and code-style seeds) and the MIDI produced by… See the full description on the dataset page: https://huggingface.co/datasets/anonymousgiraffe/Strudel-Synth.training_datasetCLIP4MCH3DBenchHierarchical 3D Benmark
This is an annotation dataset for 3D quality evaluation, including Object-Level, Part-Level and Material-Subject annotations.
We also release 3D assets generated from new 3D generative models that are not included in 3DGen-Bench dataset.
SurvCancel
SurvCancel
SurvCancel is an anonymized longitudinal dataset for dynamic passenger
cancellation prediction in on-demand ride-sharing systems. Each JSONL record is
one focal order with static trip attributes, a terminal outcome, and an ordered
sequence of pre-pickup system snapshots. Snapshots are sampled every 10 seconds
and include the focal order state, surrounding active orders, available
vehicles, and the matched vehicle when present.
This release is intentionally flat: the four… See the full description on the dataset page: https://huggingface.co/datasets/survcancel-anonymous/SurvCancel.AHaBench
Usage Guideline
This dataset and accompanying code are released under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.You may copy, share, and adapt the materials for non-commercial research and educational purposes, provided that you:
Give proper credit to the authors.
Include a link to the license.
Clearly indicate any modifications.
👉 Commercial use is strictly prohibited without prior written consent from the authors.… See the full description on the dataset page: https://huggingface.co/datasets/anonymous9268/AHaBench.horizonmath
HorizonMath
HorizonMath is a benchmark of research-level mathematical problems for measuring progress in reasoning toward mathematical discovery with automatic verification.
Files
data/problems_full.json
data/problems_full.jsonl
data/baselines.json
data/baselines.jsonl
croissant.json
Loading
from datasets import load_dataset
problems = load_dataset(
"anonymousAIresearcher/horizonmath",
name="problems",
split="train",
)
baselines = load_dataset(… See the full description on the dataset page: https://huggingface.co/datasets/anonymousAIresearcher/horizonmath.PuzzleCodeBench
Dataset Card
Overview
This dataset contains the anchor split for public browsing and experimentation.
Transfer Split
transfer.jsonl is the hidden evaluation split. It is used to run generated solver code on unseen instances for benchmark evaluation, and is intentionally not exposed in the public viewer split configuration.
license: cc-by-4.0
TempoMed-Bench-MCQ
TempoMed-Bench-MCQ
Data Overview
TempoMed-Bench-MCQ is a multiple-choice question benchmark designed to evaluate temporal awareness in medical large language models. Each instance is constructed from a pair of medical guidelines: an up-to-date guideline and an oudated guideline. The question asks about the recommendation according to the up-to-date guideline, while the answer choices include the up-to-date recommendation, the outdated recommendation, plausible distractors… See the full description on the dataset page: https://huggingface.co/datasets/anonymous2509/TempoMed-Bench-MCQ.mobiplant
Dataset Card for MoBiPlant
Dataset Summary
MoBiPlant is a multiple-choice question-answering dataset curated by plant molecular biologists worldwide. It comprises two merged versions:
Expert MoBiPlant: 565 expert-level questions authored by leading researchers.
Synthetic MoBiPlant: 1,075 questions generated by large language models from papers in top plant science journals.
Each example consists of a question about plant molecular biology, a set of answer options, and… See the full description on the dataset page: https://huggingface.co/datasets/anonymousSub10/mobiplant.bng
Beyond N-Grams (BNG)
Dataset Summary
This dataset is designed to study language trends over time. It combines multi-source metadata, aggregated review signals, and LLM-generated features to enable hypothesis-driven and exploratory research on how narrative and reception characteristics evolve over time.
The dataset does not contain original book text. Instead, it uses LLM-generated proxy content and derived features to approximate semantic and evaluative… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-bng/bng.UVQA
Overview
Using dense textual descriptions from Docci, we generate 10-choice multiple-choice VQA pairs with GPT-4o, followed by human verification.
Dataset Detail
1. Large Answer Space
Using 10 answer choices:
Reduces random guessing probability
Enables more reliable evaluation
2. Data Statistics
Statistic
Value
Total QA pairs
36,241
Train split
23,905
Test split
12,336
Choices per question
10
QA pairs per… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-2684/UVQA.ICLR26_anonymousprompt-sensitivity-codegen
Anonymous Prompt Sensitivity Dataset
This package contains model generations and evaluation outcomes for an anonymized
submission on prompt sensitivity in few-shot code generation.
What is included
prompt_sensitivity_dataset.jsonl: one row per generated sample
prompt_sensitivity_dataset.csv: tabular view of the same rows
prompt_sensitivity_dataset.parquet: columnar copy when parquet support is available
prompt_variant_spec.json: machine-readable description of the prompt… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-acl26/prompt-sensitivity-codegen.CFAcsvae