Cataphora Release
Cataphora Awarded All Claims in Patent for its Core Technology that Revolutionizes Mission-Critical Corporate Search

Return to Main Releases Page

Breakthrough Overturns Long-Standing Fundamental Assumption about Information Retrieval

Redwood City, CA. March 22, 2007. Cataphora, Inc., an industry-leading provider of evidence analytics and review software, today disclosed that it has been granted a patent for key inventions that revolutionize information retrieval technology. The essence of the patent reverses a fundamental assumption in traditional information retrieval, which is that the individual document is the logical unit of search. Instead, Cataphora's groundbreaking invention, which lies at the core of the company's technology, offers the construct of a "discussion" - a logical sequence of dialog among a set of actors that may span many items, and even different types of items.

"Traditional information retrieval techniques are geared towards the retrieval and categorization of documents each of which has a substantial amount of content," explains Cataphora CEO Elizabeth Charnock. "However, in today's fast paced, remotely-connected business world, conversations are often had and decisions made in brief emails, instant messages and voicemails that may have very little distinguishing content - and indeed, quantitatively very little content at all." Charnock comments that such innovations as have been made in search in the past ten years have been mostly focused on Internet search, or have been limited to very narrow domains. By contrast, the commercially vital area of search of broader organizational information is very little different from the way it was fifteen or more years ago. In a world in which ten billion email messages are sent each day, such dated technology is rapidly becoming inadequate to cope with corporate communications.

Practical Applications

While the applications of Cataphora's breakthrough technology are extremely broad, obvious uses include electronic discovery and evidence analytics in the course of litigation; investigation; regulatory compliance; and military intelligence. These are areas where the technology's unique ability to unify "short format" messages with their logical antecedents or descendants is invaluable. Without this capability, key elements of an electronic conversation such as a message that simply says "let's proceed" can easily go unremarked - or may even be been entirely culled out of a data set for failing to contain the right words. In such situations, the needle would not even get into the haystack.

Organizing a collection of electronic data into discussions provides an extraordinarily rich view of the data that helps quickly detect anomalies and paints a highly accurate picture of the interactions among the principal actors. This can often be the key to rapidly understanding the facts, and offers the critical advantage to litigators and investigators of not only finding information, but also being able to identify "holes" in the data.

Information Complexity

Data in large organizations is not only increasingly vast in quantity, but also in complexity, as the number of different data types and devices continues to increase. Consequently, in addition to being more voluminous, organizations' communications are today vastly more fragmented than ever and much more difficult to reconstruct and interpret correctly. Those with superior - or indeed any - ability to perform such reconstruction and interpretation correctly over many millions of electronic data items thus can gain substantial advantage in a legal action or investigation.

One recent report estimates the amount of digital data created worldwide in 2006 at 161 billion gigabytes (about three million times the information in all the books ever written, according to the research authors.) Another study suggests that over 90% of all corporate data exists only in electronic form, and that it is growing by 30% per year. Says CEO Charnock: "It is increasingly rare for us to encounter data collections with fewer than four million or so items, while the time available to make sense of them is often only a matter of weeks. And the really important stuff often is not conveniently written in an expository form of which your sixth grade English teacher would approve. Or it might be what's not there that is really important."

In these circumstances, explains Steve Roberts, Cataphora's Chief Technology Officer, many people rely on what is known in the computer industry as "topic categorization," in preference to the much more simplistic plain keyword search. But all topic categorization mechanisms prior to Cataphora's require that the individual document contain explicit evidence of the presence of the topic - perhaps one or more specific variations of phrases - or has content that is statistically similar to known references to the topic. "A short message sent from the Blackberry or Treo that so many professionals can't live without probably has neither," Roberts points out. "Users of older information retrieval technologies can do little better than hope that short message wasn't important…"

Cataphora's Completely Self-Funded Rapid Growth

Cataphora has been able to use its fundamental breakthroughs to accomplish growth to a substantial size and profitability that are perhaps unprecedented for a Silicon Valley software company that has chosen to be 100% funded from revenue. The company was founded in 2002 and has funded its growth entirely from customer revenues since inception. Today, Cataphora has over 100 employees and works with major law firms, federal government agencies, and large corporations in such industries as pharmaceuticals, financial services, energy, chemicals, and insurance.

Charnock attributes this success to several key factors: "We were able to identify and seize the opportunity to bring real, differentiated value to an initial market with a dramatic need: litigation and investigation. Moreover, because we chose to bootstrap the company, we have had to manage our business extremely efficiently. It has paid off."

About Cataphora

Cataphora Inc. is the creator of C-Evidence, the solution of choice for investigative analytics and electronic evidence review. C-Evidence Investigative Analytics provide attorneys and investigators with unprecedented insight into electronic data, revealing fact and behavior patterns and providing answers to critical questions that were previously unanswerable. C-Evidence Electronic Evidence Review presents clients with the most important evidentiary data early in the review cycle and more effectively filters out junk and the other non-responsive data. By contrast with software that merely groups documents based on similarity of their contents, C Evidence automatically finds the relationships among all the documents and all the people who created, received, or interacted with them, using these to present data for review in the most efficient review platform available.

Cataphora's C-Evidence Platform is being widely used by corporate legal departments, private law firms, and investigators with document-intensive matters in such areas as white-collar crime, securities, antitrust and intellectual property.

Cataphora is headquartered in Redwood City, California with an East Coast office in Washington, DC. For more information, please visit www.cataphora.com or email info@cataphora.com.

Media Contact:
Rick Janowski

Cataphora Inc.
Tel: (650) 622-9840 x607
Fax: (650) 622-9844

Return to Main Releases Page

  [Click on image to close]
Click anywhere on image to close