datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
agent-intrusion-escalation-forensics
Both Sides Detected It, Neither Escalated: Concurrency and Escalation Failure in the July 2026 Autonomous Agent Intrusion
This repository contains the corpus, ingestion pipeline and report for a forensic reconstruction
of the July 2026 autonomous agent intrusion, submitted to the Apart Research & CeSIA AI
Incident Response Sprint, Track 2 (Forensics and Forecasting).
By: Fatimah Mohamed Emad Elden
Trouve Labs
Detection was not the binding… See the full description on the dataset page: https://huggingface.co/datasets/FatimahEmadEldin/agent-intrusion-escalation-forensics.clinical-vital-sign-escalation-response-coherence-risk-v0.1What this repo is for
Detect when
vital signs deteriorate
but escalation and response
fail
Common breaks
high NEWS not escalated
doctor notified late
review done but no action
action taken too late
Used for
deterioration detection
ward safety
ICU outreach
rapid response auditing
clinical-deterioration-escalation-response-coherence-risk-v0.1What this repo is for
Detect when
deterioration signals fire
but escalation and response
do not track them
Common breaks
NEWS2 high but nobody calls
team arrives late
team arrives but no intervention starts
intervention delayed after arrival
Examples you can use
sepsis screen positive but antibiotics late
hypotension triggers outreach but fluids delayed
high NEWS2 overnight with no review
You use it to flag
avoidable harm risk
ICU transfer delay risk
clinical-observation-chart-escalation-response-coherence-risk-v0.1What this repo is for
Detect when
observation charts show deterioration
but escalation and review
do not match
Common breaks
obs missed during high risk period
NEWS trigger not escalated
escalated but no review
review late
review done but no action plan recorded
Examples
NEWS 9 with no doctor call
post-op patient triggering with review hours late
night shift missed obs leading to arrest
You use it to flag
deterioration miss risk
late ICU transfer risk
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.ai-autonomy-escalation-coherence-risk-v0.1What this repo is for
Detect when an AI system escalates autonomy beyond its permitted scope.
Core failure modes:
acting without approval
executing irreversible actions
expanding task scope
ignoring permission boundaries
This dataset is central for agent governance and deployment safety.
clinical-transfer-escalation-bed-availability-coherence-risk-v0.1What this repo is for
Detect when escalation need
and bed or transfer capacity
fall out of alignment
before
ward deterioration
and preventable ICU delays.
clinical-lactate-escalation-coherence-risk-v0.1What this repo is for
Detect when lactate trend signals
and escalation decisions
fall out of alignment
before
avoidable ICU transfers
shock
or preventable deterioration.
clinical-escalation-trigger-senior-review-coherence-risk-v0.1What this repo is for
This dataset tests whether a model can detect coupling failures between deterioration triggers and timely senior clinical review.
It measures alignment between
trigger activation
and
senior review completion within target time.
It predicts
missed deterioration
avoidable ICU transfers
cardiac arrest risk windows
governance failures when plans are not documented.
You use it to flag
ward safety risk
rapid response pathway integrity
shift staffing risk
clinical-escalation-discipline-v0.1
What this dataset does
This dataset tests whether a model can decide when a patient should be escalated rather than simply monitored.
The task is not to identify the sickest patient by a single score.
The task is to decide whether the current pattern requires escalation.
Core stability idea
Escalation depends on more than visible severity.
A patient with a moderate score may need escalation if the trajectory is worsening and treatment response is poor.
A patient with a… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-escalation-discipline-v0.1.escalation-discipline-classification-v0.1
What this dataset does
This dataset tests whether a model can detect escalation discipline.
The task is simple:
Given a scenario and an escalation-discipline claim, predict whether the claim is supported.
Core stability idea
Escalation is neither inherently good nor bad.
Escalation discipline means escalating:
when thresholds are crossed
when local controls fail
when authority limits are reached
when risk exceeds containment capacity
Poor escalation occurs when systems… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/escalation-discipline-classification-v0.1.clinical-sepsis-screening-antibiotic-escalation-coherence-risk-v0.1What this repo is for
Detect when sepsis signals
and screening plus antibiotic escalation
fall out of alignment
before
delayed treatment
and avoidable deterioration.
clinical-escalation-discipline-v0.2
What this dataset does
This dataset tests whether a model can decide when a patient should be escalated rather than monitored.
The task is not to identify the sickest-looking patient.
The task is to determine whether the current pattern requires escalation.
What changed in v0.2
v0.2 adds adversarial cases where the same NEWS score can have different labels.
Some high-score patients are improving and should be monitored.
Some moderate or low-score patients are… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-escalation-discipline-v0.2.healthcare-escalation-deterioration-response-coherence-risk-v0.1What this repo is for
Detect failure-to-rescue risk before serious harm.
Tracks alignment between early warning triggers, staff recognition, escalation calls, and timely intervention.
Helps hospitals prevent unrecognised deterioration and delayed response events.
clinical-deterioration-vitals-escalation-coherence-risk-v0.1What this repo is for
Detect when
vital signs show deterioration
but escalation
does not happen
or happens too late
before
ICU transfer
cardiac arrest
or avoidable harm.
clinical-escalation-threshold-response-coherence-risk-v0.1What this repo is for
Detect when
a trigger threshold is crossed
but escalation
or response
does not happen
Examples you can use
NEWS2 high but no senior review
critical lactate but no sepsis bundle
critical hypotension but no fluids review
You use it to flag
deterioration response failure risk
clinical-quad-dose-escalation-early-ae-pk-exposure-mtd-misidentification-v0.1Clinical Quad Dose Escalation Early Safety PK MTD Misidentification v0.1
Each row is a subject snapshot during dose escalation.
Core quad
Dose escalation stepEarly safety signalPK exposureMTD decision threshold
Target
label_mtd_misid_risk_next_14d
Files
data/train.csvdata/tester.csvscorer.py
Evaluation
Run model on data/tester.csvReturn predictions row alignedScore with scorer.py
License
MIT
filesystem_playwright_with_chunk_huggingface_4048_escalations_taf545clinical-escalation-criteria-response-coherence-risk-v0.1What this repo is for
Detect when
escalation criteria are met
but the system
fails to escalate
or escalates late
or escalates to the wrong place
before
avoidable deterioration
and cardiac arrests
clinical-observation-escalation-response-coherence-risk-v0.1What this repo is for
Detect when
abnormal vital signs
do not trigger
timely escalation and response
Examples you can use
NEWS2 high score but no review
hypoxia recorded but no oxygen escalation
tachycardia trend ignored
You use it to flag
deterioration risk
before arrest or ICU transfer
customer-escalation-handling-and-resolution-quality-free
Customer Escalation Handling And Resolution Quality
Free sample for AI agent reliability dashboards, anomaly exploration, and observability-oriented analytics workflows.
What is included
conversation_traces.csv: 3256 rows, 10 columns
evaluation_sessions.csv: 1085 rows, 10 columns
judge_actions.csv: 2171 rows, 10 columns
quality_programs.csv: 27 rows, 10 columns
quality_scorecards.csv: 253 rows, 10 columns
review_outcomes.csv: 705 rows, 10 columns
Why this… See the full description on the dataset page: https://huggingface.co/datasets/Tekhnika/customer-escalation-handling-and-resolution-quality-free.clinical-quad-dose-escalation-toxicity-signal-expansion-pressure-mtd-misestimation-v0.1Clinical Quad Dose Escalation Toxicity Expansion Pressure MTD Misestimation v0.1
Each row is a cohort week snapshot in dose escalation.
Core quad
Dose escalation speedEarly toxicity signalCohort expansion pressureMTD misestimation risk
Target
label_mtd_misestimation_risk_next_30d
Files
data/train.csvdata/tester.csvscorer.py
Evaluation
Run model on data/tester.csvReturn predictions row alignedScore with scorer.py
License
MIT
ssrf-escalation-34
test
ssrf-escalation-43
test
ssrf-escalation-13
test
ssrf-escalation-31
test
ssrf-escalation-33
test
ssrf-escalation-40
test
escalation_synthetic_data
Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
Dataset Details
Dataset Description
Curated by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Dataset Sources [optional]
Repository: [More… See the full description on the dataset page: https://huggingface.co/datasets/akashkpatel1991/escalation_synthetic_data.healthcare-icu-capacity-escalation-coherence-risk-v0.1What this repo is for
Detect ICU overload before collapse.
Tracks alignment between staffed ICU beds, occupancy, ED ICU demand, step-down capacity, and staffing ratios.
Helps hospitals trigger escalation early and prevent critical care gridlock.
