datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
patentmatch-temporal-clean-benchmark
PatentMatch Temporal and Component-Clean Extension
Status
Private research preview. Patent text files have not yet been uploaded.
Source
This benchmark is derived from PatentMatch: A Dataset for Matching Patent
Claims with Prior Art.
Paper: https://arxiv.org/abs/2012.13919
Official project: https://hpi.de/naumann/s/patentmatch
Source repository: https://github.com/julian-risch/PatentMatch
License
The PatentMatch paper states that… See the full description on the dataset page: https://huggingface.co/datasets/yongminyoo91/patentmatch-temporal-clean-benchmark.temporal-nli@inproceedings{thukral-etal-2021-probing,
title = "Probing Language Models for Understanding of Temporal Expressions",
author = "Thukral, Shivin and
Kukreja, Kunal and
Kavouras, Christian",
booktitle = "Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url =… See the full description on the dataset page: https://huggingface.co/datasets/tasksource/temporal-nli.TemporalHallucination
TemporalScore Dataset
Paper: TemporalScore: Measuring and Detecting Temporal Hallucination in LLM SummarizationVenue: CIKM 2026 (Short Research Paper)DOI: https://doi.org/10.1145/3799682.3840029
Dataset Description
This dataset accompanies the TemporalScore paper and contains annotations for temporal hallucination in LLM-generated summaries. Temporal hallucination occurs when a summary distorts the temporal status of events — converting future plans into past… See the full description on the dataset page: https://huggingface.co/datasets/hussain-s/TemporalHallucination.state-continuity-temporal-coherence-worldmodel-v01
Dataset
ClarusC64/state-continuity-temporal-coherence-worldmodel-v01
This dataset tests one capability.
Can a model preserve a coherent world state across time.
Core rule
The world has memory.
Once something changeslater descriptions must reflect that change.
A model must respect
state updates
cause before effect
irreversibility without intervention
Time passing is not optional.
Canonical labels
WITHIN_SCOPE
OUT_OF_SCOPE
Files… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/state-continuity-temporal-coherence-worldmodel-v01.telco-churn-7k
Telco Churn 7k
A 7,043-row customer-retention dataset drawn from a U.S. telecom provider. Each record profiles one account with 21 concise attributes and a Churn flag (Yes / No) indicating whether the customer left within the last month. The schema is:
customerID – unique subscriber identifier
gender – {Female, Male}
SeniorCitizen – {0, 1}
Partner, Dependents – {Yes, No}
tenure – months of service (0–72)
PhoneService, MultipleLines – {Yes, No, No phone service}… See the full description on the dataset page: https://huggingface.co/datasets/temporaldrift777/telco-churn-7k.temporal-narrative-integrity-v0.1What this dataset tests
Whether a narrative preserves time orderand does not invent causality across reversed events.
Required outputs
timeline_events
temporal_inconsistencies
causal_claim_violations
required_timeline_questions
Typical failures
swapping order to strengthen a story
implying cause without timestamps
postdating evidence citations
Suggested prompt wrapper
System
You extract timelines and detect temporal integrity failures.
User
Source text{source_text}… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/temporal-narrative-integrity-v0.1.temporal-drift-invariants-v0.1
What this dataset tests
Time moves.
Assumptions decay.
You must notice.
Why it exists
Many replies treat yesterday as today.
That breaks decisions.
This set checks whether you detect drift and hold invariants.
Data format
Each row contains
timeline_context
user_message
drift_pressure
constraints
failure_modes_to_avoid
target_behaviors
gold_checklist
Feed the model
timeline_context
user_message
constraints
Score for
drift detection
time… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/temporal-drift-invariants-v0.1.clinical-temporal-narrative-integrity-v0.1What this dataset tests
Whether a clinical narrative preserves time orderand does not invent causality that violates timestamps.
Required outputs
timeline events
temporal inconsistencies
causal timeline violations
required timeline clarifications
Typical failures
discharge justified by results not yet available
endpoint prespecification claims contradicted by registry dates
medication blamed for symptoms that predate dosing
Suggested prompt wrapper
System
You extract… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-narrative-integrity-v0.1.clinical-temporal-5node-pressure-buf-lag-cpl-safety-escalation-reg-hold-v0.1
What this repo does
This dataset tests whether a model can detect a safety signal escalation forming over time and predict whether the program crosses into regulatory hold lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents a short temporal window (t0–t3) across program months. It includes time-series values for safety pressure, pharmacovigilance buffer, governance… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-safety-escalation-reg-hold-v0.1.temporal_cookbook_db
🧠 Temporal Cookbook DB
A multi-table dataset designed to represent structured, relational data used in event extraction, temporal reasoning, and fact representation pipelines. Originally built as an SQLite database and converted into CSVs for hosting on the Hugging Face Hub.
The data tables are created from processing a subset of data from jlh-ibm/earnings_call and covered comapnies AMD and Nvidia.
📦 Dataset Structure
This dataset is organized as multiple… See the full description on the dataset page: https://huggingface.co/datasets/TomoroAI/temporal_cookbook_db.ai-temporal-5node-pressure-buf-lag-cpl-alignment-goal-drift-v0.1
What this repo does
This dataset tests whether a model can detect an alignment cascade forming over time by reading a short ordered window of signals and predicting whether goal drift lock-in occurs by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) for an AI system under alignment pressure. It includes time-series values for optimization… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-temporal-5node-pressure-buf-lag-cpl-alignment-goal-drift-v0.1.temporal_splitinfrastructure-temporal-5node-pressure-buf-lag-cpl-grid-stress-blackout-v0.1
What this repo does
This dataset tests whether a model can detect a power grid stress cascade forming over time and predict whether blackout lock-in occurs by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents a short time window (t0–t3) of grid stress conditions including demand pressure, reserve buffer margin, response lag, and interconnect coupling tightness. The label marks… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/infrastructure-temporal-5node-pressure-buf-lag-cpl-grid-stress-blackout-v0.1.robotics-temporal-action-sequencing-v0.1What this dataset tests
Whether actions occur in the correct order
Whether prerequisite steps are respected
Whether unsafe ordering is detected
Why this exists
Robots often fail by doing the right actionsin the wrong order
This set detects temporal incoherence
Data format
planned_sequence
executed_sequence
observed_result
Task
Emit one sequencing label
Give a short explanation
Sequencing pressures
ordering_error
premature_force
missing_tilt
loop_error… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/robotics-temporal-action-sequencing-v0.1.temporal_qatemporal-ood
Temporal OOD Dataset for TCR-pMHC Binding Prediction
Dataset Description
The Temporal OOD (Out-of-Distribution) Dataset evaluates TCR-pMHC binding prediction models under temporal shift. This dataset contains SARS-CoV-2 T cell receptor sequences collected during the COVID-19 pandemic, providing a natural test of model generalization to time-lagged data.
Key Features
Temporal Shift Testing: Data collected after training set construction
COVID-19 Focus:… See the full description on the dataset page: https://huggingface.co/datasets/YYJMAY/temporal-ood.clinical-temporal-5node-pressure-buf-lag-cpl-mfg-drift-supply-disruption-v0.1
What this repo does
This dataset tests whether a model can detect manufacturing drift forming over time and predict whether the program crosses into supply disruption lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents a short temporal window (t0–t3) across program months. It includes time-series values for pressure (deviations and schedule stress), buffer capacity… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-mfg-drift-supply-disruption-v0.1.ai-temporal-5node-pressure-buf-lag-cpl-multiagent-coordination-v0.1
What this repo does
This dataset tests whether a model can detect a multi-agent coordination cascade forming over time by reading a short ordered window of signals and predicting whether coordination lock-in occurs by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) for a multi-agent system under coordination stress. It includes time-series… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-temporal-5node-pressure-buf-lag-cpl-multiagent-coordination-v0.1.ai-temporal-5node-pressure-buf-lag-cpl-deploy-drift-reg-escalation-v0.1
What this repo does
This dataset tests whether a model can detect a cross-domain cascade forming over time where deployment drift and rising incidents couple with media and regulatory pressure, and predict whether the system crosses into regulatory escalation lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) for an AI deployment… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-temporal-5node-pressure-buf-lag-cpl-deploy-drift-reg-escalation-v0.1.clinical-temporal-5node-pressure-buf-lag-cpl-ph2-drift-ph3-collapse-v0.1
What this repo does
This dataset tests whether a model can detect a drug development program drifting over time from Phase II signal instability into Phase III collapse lock-in by reading a short ordered window of signals and predicting whether the program crosses into cascade lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) across… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-ph2-drift-ph3-collapse-v0.1.temporal_dataclinical-temporal-5node-pressure-buf-lag-cpl-competitive-landscape-v0.1
What this repo does
This dataset tests whether a model can detect manufacturing drift forming over time and predict whether the program crosses into supply disruption lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents a short temporal window (t0–t3) across program months. It includes time-series values for pressure (deviations and schedule stress), buffer capacity… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-competitive-landscape-v0.1.clinical-temporal-5node-pressure-buf-lag-cpl-program-lockin-v0.1
What this repo does
This dataset tests whether a model can detect a drug development program entering composite instability across recruitment, safety, manufacturing, and competitive pressure over time, and predict whether the program crosses into lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents a short temporal window (t0–t3) across program quarters. It summarizes… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-program-lockin-v0.1.clinical-temporal-5node-pressure-buf-lag-cpl-icu-deterioration-shock-v0.1
What this repo does
This dataset tests whether a model can detect an ICU deterioration cascade forming over time by reading a short ordered window of signals and predicting whether shock lock-in occurs by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) for an ICU patient under deterioration pressure. It includes time-series values for… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-temporal-5node-pressure-buf-lag-cpl-icu-deterioration-shock-v0.1.Temporal_Spatial_Tracking_Dataset
Dataset Overview
This dataset contains time-stamped spatial tracking records collected from tagged entities (e.g., wearable tags, assets, or devices) operating within a monitored environment.Each row represents a single localization event captured at a precise moment in time, including 3D position coordinates and device status information.
The dataset is inherently temporal and spatial, making it suitable for trajectory reconstruction, movement analysis, and time-based behavioral… See the full description on the dataset page: https://huggingface.co/datasets/VillanovaAI/Temporal_Spatial_Tracking_Dataset.temporaltemporal-nlisports-temporalai-temporal-5node-pressure-buf-lag-cpl-priv-esc-v0.1
What this repo does
This dataset tests whether a model can detect a privilege escalation cascade forming over time by reading a short ordered window of signals and predicting whether the system crosses into cascade lock-in by the final step.
Core quad
pressurebufferlagcoupling
Prediction target
label_cascade_state
Row structure
One row represents one short time window (t0 to t3) for an AI system under security pressure. It includes time-series… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-temporal-5node-pressure-buf-lag-cpl-priv-esc-v0.1.qwen3.5-temporal-blindspot
Temporal Misalignment Under Persona Conditioning
A Blind Spot Dataset for Qwen3.5-4B
Model Tested: Qwen/Qwen3.5-4BAuthor: Areeba Fatima — LUMS BS Computer ScienceTask: Probing temporal grounding failure modes in instruction-tuned LLMs
Motivation
Large language models are trained on static snapshots of the world but deployed
in dynamic contexts where temporal grounding matters. This dataset systematically
probes whether Qwen3.5-4B — a 4B parameter multimodal… See the full description on the dataset page: https://huggingface.co/datasets/areeba-sloth/qwen3.5-temporal-blindspot.