Hugging Face's logo
Activity Feed

AI & ML interests

We build tools to understand how models change during training, identify where regressions and unwanted behaviors emerge, localize meaningful changes within the model, and correct or remove learned behavior without full retraining.Our work spans training dynamics, model interpretability, machine unlearning, training-free model optimization, and AI governance.

Recent Activity
brandon-authentrics  published an article about 2 hours ago
Accelerating model refinement: automating Fine-Tuning through checkpoint interpolation with Authentrics Zero Training Optimization & Maintenance (Z-TOM)
bimarsh-auth  updated a Space about 23 hours ago
authentrics/README
bimarsh-auth  updated a collection about 24 hours ago
Recover a Capability Lost During Fine-Tuning
View all activity

Articles

Organization Card
Community About org cards

Docs Python Runs locally

Authentrics.ai

Find what changed. Find when it changed. Fix it without retraining.

Training is one of the most expensive and consequential parts of building a model. Once a run is complete, regressions, memorization, interference, or unwanted behavior can leave teams with a familiar answer: re-curate the dataset, change the training setup, and run it again.

Authentrics provides another path — analyze how the model changed, trace where problems emerged, and correct the resulting model without a full retrain.

What You Can Do With Authentrics

  • Understand your model. Establish a baseline across model behavior and internal structure, detect meaningful changes, and localize which layers are most associated with them.
  • Remove a known cause (machine unlearning). When unwanted behavior traces back to specific training session(s), remove that effect directly from the checkpoint.
  • Model optimization. Recover accuracy, correct a regression, or suppress unwanted behavior by optimizing the checkpoint directly against an objective — without backprop or retraining.

Everything runs locally on your own hardware; only project metadata leaves your machine, never your weights.

Operation What it's for
static_analysis audit parameter drift between pairs of sequential checkpoints
activation_analysis catch behavioral drift in intermediate activations
correlation_analysis see how strongly each layer influences a reference (usually output) layer
exclude_training compliance / unlearning: remove the effect of specific training session(s) (e.g. a sensitive/bad data slice) from the latest checkpoint without retraining from scratch
ztom_analysis optimize a model against a Callable[[output], float] loss without backprop/retraining

Demos

Each demo starts with a familiar machine-learning problem and shows how Authentrics approaches it through direct analysis and modification of the model itself.

Find Which Training Step Introduced a Backdoor — Then Remove It

Data poisoning / backdoor detection / machine unlearning

A LeNet-5 MNIST classifier is trained with one poisoned epoch that introduces a BadNets trigger. Clean accuracy remains healthy, while triggered inputs are silently misclassified.

Authentrics analyzes how the model changed through training, identifies where the unwanted behavior emerged, and removes that learned influence without retraining from scratch.

Demonstrates: training dynamics, backdoor detection, machine unlearning

Recover a Capability Lost During Fine-Tuning

Catastrophic forgetting / task interference / model optimization

Fine-tuning Gemma 3 1B on a new task quietly degrades a capability the model already had.

Instead of retraining or repeating fine-tuning, Authentrics works directly with the resulting model to recover the lost behavior.

Demonstrates: catastrophic forgetting, regression recovery, model optimization

Remove Memorized PII Without Retraining the Model

Memorization / privacy / machine unlearning

A medical chatbot fine-tuned on data containing personal information memorizes that information.

Authentrics identifies where the unwanted learning was introduced and removes its influence directly from the model without a full retrain.

Demonstrates: memorization analysis, training attribution, machine unlearning

Understand What Changed Inside Your Model

See Which Experts a Mixture-of-Experts Model Actually Uses

Interpretability / Mixture-of-Experts routing

Which experts does Mixtral-8x7B actually use, and how does that internal routing behavior vary across the model?

Authentrics analyzes the model's internal structure and behavior to expose routing patterns and layer-level influence.

Demonstrates: model interpretability, MoE routing, internal model analysis

Find Where a Model Changed Across Its Training Run

Training dynamics / model drift

Across the NVIDIA Nemotron Cascade 8B training lineage, what changed inside the model — where, when, and how much?

Authentrics analyzes the evolution of the model across training to surface where meaningful structural and behavioral changes occurred.

Demonstrates: training dynamics, model drift, model evolution

Try It on Your Model

pip install authentrics            # Linux x86_64, Python 3.11–3.13
authrx init                        # paste API key (stored at ~/.local/state/authentrics/api_key)
# or, for CI / non-interactive:
export AUTHRX_API_KEY=<your_api_key>

Generate an API key and read the full docs at https://app.authentrics.ai/.

Links

Collections 6

View 6 collections