Resources for Addressing Head On the Myths and Misinformation That are Holding TAR Back


TAR for Smart People

This book is a great place to start. Learn how technology assisted review works and why it matters for legal professionals.

Ask Catalyst: A User’s Guide to TAR

Catalyst’s new book answers 20 common questions about  TAR.

Case Studies

Using TAR 2.0 to Expedite Multi-Language Review

Insight Predict’s unique capabilities cut review by two thirds In a major shareholder class... >>

Client Cuts Review Time in Half Using TAR 2.0

Catalyst helped a client negotiate a discovery stipulation to use Insight Predict... >>

Patent Case Proves It’s Never Too Late to Use TAR

Even after manually reviewing half the collection, TAR produced substantial savings >>...

Predict Proves Effective for Small Collection

Facing a tight deadline in SEC probe, this corporation reduced review by 75%... >>

Major Bank Slashes Review Costs with Innovative E-Discovery Technology

Catalyst’s Insight Predict cut production review costs by 94%. Our client was a large bank... >>


A Brief History of Technology Assisted Review

How did TAR take root among lawyers? And how did it become so widespread so quickly?... >>

Why Control Sets are Problematic in E-Discovery

Continuous Active Learning makes control sets irrelevant. Catalyst’s chief scientist explains why... >>

An Open Look at Keyword Search vs. Predictive Analytics

Can keyword search be as effective as TAR? This question is one we frequently hear from lawyers and it... >>


How Does 1 Reviewer Do the Work of 48

Reviewers typically code documents at a pace of 50 per hour. In a review of 723,537 documents... >>

Cut the Cost of Discovery in Five Easy Steps

Continuous active learning finds relevant documents faster and with less effort than TAR 1.0 or linear review... >>

Scientific Research

Most of these articles are written by Maura R. Grossman and Gordon V. Cormack. Please click links for details.

Technology-Assisted Review in e-Discovery Can Be More Effective and More Efficient Than Exhaustive Manual Review

We offer evidence that technology-assisted processes, while less expensive, can yield results superior to those of exhaustive manual review.

The Grossman-Cormack Glossary of Technology-Assisted Review

This paper includes a glossary of technology assisted review terms and a foreword by John M. Facciola, U.S. Magistrate Judge.

Comments on “The Implications of Rule 26(g) on the Use of Technology-Assisted Review”

Validation should consider all available evidence concerning the effectiveness of the end-to-end review process, including prior scientific evaluation of the TAR method.

AutoTAR Technology-Assisted Review Platform with Continuous Active Learning™ (CAL™)

Search Jeb Bush emails using this online tool.

Autonomy and Reliability of Continuous Active Learning for Technology-Assisted Review

Grossman and Cormack enhance the autonomy of the continuous active learning method.

Multi-Faceted Recall of Continuous Active Learning for Technology-Assisted Review

Grossman and Cormack results assuage the concern that continuous active learning may achieve high overall recall at the expense of excluding identifiable categories of relevant information.

Engineering Quality and Reliability in Technology-Assisted Review

The objective of TAR is to find as much relevant information as possible with reasonable effort.

Scalability of Continuous Active Learning for Reliable High-Recall Text Classification

Grossman and Cormack  present a scalable version of CAL to construct a classifier.  

Impact of Review-Set Selection on Human Assessment for Text Classification

A laboratory study by Adam Roegiest and Gordon V. Cormack on  human assessors.

TREC 2015 Total Recall Track Overview

Adam Roegiest, University of Waterloo, Gordon V. Cormack, University of Waterloo, Maura R. Grossman, Wachtell, Lipton, Rosen & Katz and Charles L.A. Clarke, University of Waterloo

TREC 2016 Total Recall Track Overview

Maura R. Grossman, Gordon V. Cormack, and Adam Roegiest University of Waterloo

Automatic and Semi-Automatic Document Selection for Technology-Assisted Review

In this work, we investigate the extent to which the observed effectiveness of the different methods may be confounded by chance.

Navigating Imprecision in Relevance Assessments on the Road to Total Recall: Roger and Me

TAR systems seek to achieve "total recall"; that is, to approach, as nearly as possible, the ideal of 100% recall and 100% precision, with minimal human effort.

A Tour of Technology-Assisted Review

The conflation of diverse tools and methods under a single label has resulted in confusion in the marketplace.

Technology-Assisted Review in Electronic Discovery

Scientific evidence suggests that certain TAR methods offer not only reduced effort and cost, but also improved accuracy, when compared to manual review.

Featured Video: Continuous Active Learning


Phone: 303.824.0900 | Toll Free: 877.557.4273
Fax: 303.293.9073
Privacy Policy | Privacy Shield


OpenText™, The Information Company, is a market leader in Enterprise Information Management software and solutions, enabling Intelligent and Connected Enterprises by managing, leveraging, securing and gaining insight into enterprise information, on-premises or in the cloud. OpenText™ Catalyst designs, hosts and supports the world’s fastest and most powerful document repositories for large-scale discovery and regulatory compliance. For more than 20 years, global corporations and their counsel have relied on Catalyst to help reduce litigation costs and take control of complex legal matters.

Copyright © 2019 Catalyst Repository Systems. All Rights Reserved.