Cover image

Forty-Eight Features Gone, Fifty-Nine Too Far

TL;DR for operators Removing features from a production recommendation model is a release decision, not simply a feature-ranking exercise. Pinterest’s FORTE framework1 makes feature retirement repeatable through daily importance monitoring, joint feature testing, retraining, online validation, and dependency tracking. The evidence explains why these stages matter. In Search Relevance, removing 59 features passed offline evaluation but failed a secondary online guardrail; removing 48 succeeded. In a separate interaction experiment, individually favorable feature changes summed to a +6.554% Closeup AUC effect, but their jointly measured effect was only +3.084%. ...

November 17, 2026 · 8 min · Zelina
Cover image

A New Vision Backbone Can Break an Old Confidence Filter

TL;DR for operators A vision classifier can retain the same application interface after a model upgrade while its unfamiliar-image detector becomes substantially less reliable. The problem may lie in how the detector processes internal features, not in the classifier’s output labels. Anti-coherence Regularized Absolute Scaling (Anti-coh) addresses two issues: cancellation between positive and negative activations, and excessive amplification of features that oppose the predicted class. Across ten ImageNet backbones, it raises average out-of-distribution (OOD) detection AUROC from 71.28% to 85.81% relative to its predecessor, SCALE. ...

November 16, 2026 · 8 min · Zelina
Cover image

Federated Learning Needs a Control Plane, Not Just Local Data

TL;DR for operators A distributed model-training system can keep every organization’s raw records on local infrastructure and still leave several operational problems unresolved. Model updates can expose information, privacy spending can accumulate across training rounds, encrypted updates still have to be aggregated efficiently, and clients working from older model versions can send updates that no longer deserve equal influence. ...

October 10, 2026 · 7 min · Zelina
Cover image

Same State, Different Stream: Why Reproducible AI Needs More Than a Seed

TL;DR for operators A fixed seed is not a complete reproducibility guarantee. More surprisingly, neither is restoring the complete state of the random-number generator. In Reproducible AI Requires Reproducible Randomness, Anthony Bertrand, Tom Schmitt, Engelbert Mephu Nguifo, and David Hill compare library implementations of Mersenne Twister and Philox against canonical reference generators.1 Their deterministic tests show that the same nominal generator, initialized from the corresponding full state, can still emit a different sequence because libraries change what happens between stored state and returned output. ...

October 8, 2026 · 7 min · Zelina
Cover image

The Detector Can’t See What Its Features Don’t Describe

TL;DR for operators When an anomaly detector misses events that matter, teams often look first at the model, the feature selector, or the score-combination rule. The results in LLM-Generated Feature Pools for Time Series Anomaly Detection1 point to an earlier constraint: what the detector is allowed to measure. In matched experiments on the univariate TSB-AD-U benchmark, changing the candidate feature pool spans 0.226 VUS-PR, compared with 0.031 across feature-selection strategies even after adding a hindsight oracle, and 0.096 across the full score-aggregation grid. A 10-feature hand-crafted pool reaches 0.529, while a stronger LLM-generated pool reaches 0.569 on average. Combining generated and hand-crafted features raises the corresponding result to 0.588. ...

October 8, 2026 · 7 min · Zelina
Cover image

Route Cause Analysis: Stop Sending Every AI Failure to Training

TL;DR for operators An AI failure is an observation, not a diagnosis. A low benchmark score, an incorrect answer, or a broken agent run does not tell you whether the underlying problem belongs in the training data, model objective, retrieval policy, procedural instructions, tool interface, or execution environment. Treating all of these as “model quality” produces expensive interventions with weak causal logic. ...

July 22, 2026 · 19 min · Zelina
Cover image

Don’t Retrain the Whole Map When One Neighborhood Moves

TL;DR for operators Most production model-maintenance policies sit between two unattractive extremes: never retrain and watch performance decay, or retrain constantly and turn the MLOps budget into a recurring tribute payment. This paper tests a third option.1 It divides the feature space into clusters, maintains a separate ADWIN error detector for each cluster, and triggers model adaptation when one of those regional error streams changes significantly. The goal is not to beat continuous retraining at any cost. It is to approach its predictive performance while avoiding its habit of rebuilding the model whenever another batch enters the building. ...

July 15, 2026 · 20 min · Zelina
Cover image

The Drift Alarm Is Not the Strategy

TL;DR for operators A production model rarely collapses with theatrical dignity. It usually degrades in increments: a fraud pattern shifts, an electricity market regime changes, a sensor starts reporting under a new operating condition, or network traffic stops looking like yesterday’s traffic. The dashboard still has a reassuring green check. Naturally. The paper “Learner-based Concept Drift Detection: Analysis and Evaluation” by Md Moman Ul Haque Khan and Samira Sadaoui is useful because it refuses to treat concept drift detection as one magic alarm bolted onto a model after deployment.1 It surveys learner-based detectors and compares three families: Statistical Process Control methods, window-based methods, and ensemble-based methods. The experiment tests them across synthetic abrupt and gradual drift streams and two real-world streams: electricity price movement and network intrusion data. ...

July 3, 2026 · 16 min · Zelina
Cover image

Trex Marks the Spot: When AI Starts Training AI

Fine-tuning is supposed to be the practical part of AI work. You have a model. You have a task. You collect some data, choose a training recipe, run the job, look at the benchmark, and repeat until the result stops embarrassing everyone in the meeting. That tidy version is useful for slide decks. It is less useful for actual model development. ...

April 16, 2026 · 16 min · Zelina
Cover image

Targeted Forgetting: Why AI Can’t Just ‘Unlearn’ — And What TRU Fixes

Delete is a comforting word. A user deletes an account. A marketplace removes a product. A shopper corrects a preference history because the recommendation engine has decided, with touching confidence, that one accidental click reveals a permanent love of baby strollers, golf gloves, or suspiciously ugly jackets. In a normal database, deletion sounds like a row-level operation. Remove the row, update the index, move on with life. In a trained recommender model, deletion is less tidy. The deleted data may already have shaped user embeddings, item popularity, image-text fusion layers, and ranking behavior. The row is gone, but its ghost may still be politely recommending itself. ...

April 4, 2026 · 16 min · Zelina