New on SSRN: Ariadne's Thread, a measurement-theoretic method for legal openness. Read the paper
Adversarial Reasoning

Negative space

The body of things courts have declined to do, such as arguments advanced and rejected, extensions refused and inferences not drawn, treated as a distinct category of legal information to be searched and indexed.

First used in The Promise Fulfilled

A rejected argument is a party's contention, described by a court in order to refuse it. It is rarely a headnote. It produces a citator signal only when the refusal takes the form of negative treatment of some authority, and it is usually a few paragraphs inside an opinion about something else. Yet it is the best available prediction of what happens if the argument is made again.

Institute papers call the failure to represent it negative-space ignorance, one of five structural failure categories of document-level legal AI: retrieval tuned to find support will keep forgetting the "no." The representational remedy is a rejected-argument index: rejections stored as searchable objects in their own right, classified by argument type, rejecting court, stated reason and scope, and built at ingestion, because no such index exists anywhere to be retrieved later.

The Pre-Filing Completeness Protocol makes a negative-space sweep mandatory. Restate each argument as a single proposition, search for it joined with rejection language in the forum, and either distinguish each rejection or drop the argument.

Related terms

Related frameworks

Used in