datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
clinical-quad-ddi-renal-clearance-inhibition-exposure-accumulation-toxicity-v0.1What this repo does
This dataset models acute toxicity risk driven by drug–drug interaction and renal clearance inhibition. It predicts when the interaction between impaired renal clearance, CYP inhibition, dose density, and exposure accumulation produces a toxicity event.
Core quad
renal_clearance_index
cyp_inhibition_index
dose_density_index
exposure_accumulation_index
Prediction target
label_toxicity_event
Row structure
Each row represents a patient pharmacokinetic state snapshot during… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-ddi-renal-clearance-inhibition-exposure-accumulation-toxicity-v0.1.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.4
What this repo does
This repository introduces a Clarus v0.4 dataset for acute kidney injury transition boundary discovery.
The dataset models renal deterioration as a coupled system where stress, physiological reserve, delayed intervention, and organ coupling interact.
Version v0.4 focuses on identifying when the system lies on the instability boundary rather than simply forecasting collapse.
The task is to detect when the renal system is sufficiently close to collapse that small… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.4.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.6
What this repo does
This repository contains a Clarus v0.6 intervention pathway dataset focused on acute kidney injury transition dynamics.
The dataset evaluates whether a model can determine if a proposed intervention meaningfully stabilizes a deteriorating renal system.
The task requires reasoning from:
system state
trajectory toward instability
boundary geometry
recovery geometry
intervention vector
projected trajectory consequence
The model cannot read the answer directly.
It… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.6.ABX-HT-002_renal_clearance_decoupling-v0.1ABX-HT-002 Renal Clearance Decoupling
Purpose
Detect early kidney function marker drift that no longer tracks drug levels.
Core pattern
stress_index high
exposure_index high
renal_coherence_index drops
egfr_drop_vs_expected or creatinine_rise_vs_expected stays high
later_severe_aki_flag appears
Files
data/train.csv
data/test.csv
scorer.py
Schema
Each row is one timepoint in a within series time course.
Required columns
row_id
series_id
timepoint_h
host_model
drug
drug_conc_mg_L… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ABX-HT-002_renal_clearance_decoupling-v0.1.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.1
What this repo does
This dataset models the transition from strained but recoverable renal physiology to acute kidney injury using a four-variable coupling structure.
The goal is to detect when a patient is drifting toward renal deterioration before overt kidney failure is established.
Acute kidney injury often unfolds as a cascade. Renal stress rises, physiological reserve narrows, intervention delays reduce reversibility, and organ interactions amplify decline.
The quad structure… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.1.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.3
What this repo does
This dataset models acute kidney injury transition using the Clarus quad coupling framework combined with trajectory and system dynamics.
The goal is to predict whether a patient is approaching an AKI deterioration cascade.
The dataset introduces a dynamic forecasting layer that allows models to reason about motion through the stability manifold rather than relying only on static physiological snapshots.
Core quad… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.3.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.5
What this repo does
This repository provides a Clarus v0.5 cascade recovery geometry dataset modeling acute kidney injury (AKI) transition.
The task evaluates whether a physiological system undergoing renal stress remains recoverable or has crossed an irreversible deterioration boundary.
The dataset combines:
• a renal instability quad• trajectory dynamics• cascade boundary discovery• recovery geometry signals
Models must determine whether deterioration remains reversible.… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.5.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.7What this repo does
This repository contains a Clarus v0.7 dataset modeling trauma deterioration using a quad-coupling system representation.
The dataset extends the v0.6 intervention layer by introducing uncertainty geometry.
The question addressed by earlier versions was:
Can the system be stabilized?
v0.7 adds a second critical question:
How confident are we in that conclusion?
This allows Clarus to distinguish three operational states:
• confident deterioration
• confident stabilization
•… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.7.clinical-quad-dose-renal-conmed-time-safety-drift-v0.1Clinical Quad Dose–Renal–ConMed–Time Safety Drift v0.1
What this dataset is
You test whether a model can detect when a patient is about to experience a safety event in a drug trial.
Each row represents a patient state during treatment.
Core quad coupling
Dose levelRenal functionConcomitant medication loadTime on treatment
The label asks
Will an adverse event occur in the next 7 days
Why this matters
Most safety models track single variables.
This dataset tests interaction drift between dose… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-dose-renal-conmed-time-safety-drift-v0.1.clinical-renal-buffer-exhaustion-v0.1
clinical-renal-buffer-exhaustion-v0.1
What this dataset does
This dataset evaluates whether models can detect instability caused by renal buffering failure.
Each row represents a simplified renal regulation scenario observed across three time points.
The task is to determine whether renal buffering remains stable or is moving toward renal instability.
Core stability idea
The kidney stabilizes metabolic and electrolyte balance through filtration, excretion, and… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-renal-buffer-exhaustion-v0.1.clinical-renal-filtration-instability-v0.1
clinical-renal-filtration-instability-v0.1
What this dataset does
This dataset evaluates whether models can detect instability in renal filtration and waste clearance.
Each row represents a simplified kidney function monitoring scenario observed across three time points.
The task is to determine whether renal filtration remains stable or is moving toward renal instability.
Core stability idea
Kidney stability depends on interaction between filtration capacity… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-renal-filtration-instability-v0.1.clinical-quad-anticoag-antiplatelet-renal-fall-bleed-v0.1What this repo does
This dataset models major bleeding risk under anticoagulation. It predicts when the interaction between anticoagulant intensity, antiplatelet coadministration, reduced renal function, and elevated fall risk creates a high probability of a bleeding event.
Core quad
anticoag_intensity_index
antiplatelet_coadmin_index
renal_function_index
fall_risk_index
Prediction target
label_bleed_event
Row structure
Each row represents a patient bleeding risk snapshot during active… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-anticoag-antiplatelet-renal-fall-bleed-v0.1.clinical-quad-renal-stress-buffer-lag-coupling-aki-transition-v0.2