Past decisions guide new cases
The system's norms reside in a body of past decided cases rather than in a written rulebook. Each new case is settled by analogy to the earlier ones. Its single outcome is added to the record as one more holding.
Scroll the diagram sideways to see all of it.
aiag/cases/precedential_adjudication.pyimport aiag
# The 3 approaches of Precedential adjudication, with the classes that carry them out
for approach in aiag.approaches(locus="case", conflict="collapse"):
print(approach)pip install aiagaiag/cases/precedential_adjudication.py Every method in aiag Library on GitHub
Limitation
The earliest cases generally carry outsized weight, since every later case is decided by reference to them. An early mistake may therefore become settled law instead of being corrected. In addition, retrieving a textually similar case is not the same as analogy in the legal sense. In legal analogy, what matters is whether the reasons behind the earlier holding apply to the new facts.
This approach builds the case record itself. Rather than writing rules, a group gives verdicts on particular situations, and these accumulated verdicts become the standard the system is answerable to. The two papers differ in who decides and how they cover the range of cases. One runs a deliberative process in which a panel argues cases through to binding precedents (with a variant in which a model is prompted to play that role). The other builds a repository by seeding cases, having experts name the dimensions along which the cases can vary, generating variations along those dimensions, and putting each variation to public judgment. Neither paper decides anything new by itself. Both leave behind a collection of cases that can be looked up, which the other two approaches in this regime then consult.
When a new situation arises, the system retrieves the already-decided cases most similar to it. It reaches an answer by working out which features of those cases carry over to the new one and which do not. The oldest version builds the retrieval and matching procedure by hand over 500 professional-engineering ethics decisions, and returns both the past cases and the principles they turned on. The two recent versions instead train the comparison skill. One uses reinforcement learning on its own case-augmented reasoning chains, with the written safety rules kept in view beside the precedents. The other bootstraps analogy chains through retrieval and then optimizes them, using the cases alone, so that the model stops relying on surface similarity. These two differ in where authority lies (shared between statute and precedent, or in the cases only), and there is one paper on each side. In all three, the standing record is consulted case by case at decision time and is never replaced by a compiled version.
This approach distills the case record once and then stops consulting it. Past judgments are generalized into a standing artifact that decides new situations without retrieving anything. The artifact takes two forms, which differ in whether a person can read and dispute it. One is a neural judge trained on a large collection of crowd verdicts about everyday situations, where the judgments end up in opaque weights. The other is a written constitution recovered from the record and then applied like any written constitution. Among the papers that recover a constitution, the record being read also differs. In one line of work it is raters' preferences between two answers, and in the other a model's own red-teamed failures, logged as verdicts.
This procedure decides a new case by comparison with already decided ones. The judge states which features of the earlier case are relevant and which are not, and that selection is generally where the reasoning happens.
This distinction separates the part of a past decision that binds later cases (the holding) from the remarks made along the way (the dicta), which do not. Without a way to tell the two apart, a body of precedent cannot indicate which of its own decisions are actually binding.
These two techniques let a later court revise the record. Distinguishing confines an earlier precedent to its own facts, and overruling sets it aside altogether. Both are done openly and with reasons stated, which keeps a body of case law open to revision.
This way of reasoning bases judgment on paradigm cases (i.e., clear cases on which agreement is easy) and on the short maxims drawn from them. A hard case is then settled by asking how far it is from the paradigms, rather than by deduction from a general principle.
This doctrine holds that a court is bound by the decisions of earlier courts on materially similar facts, whether or not it agrees with them. The binding force comes from the earlier decision itself, not from any rule stated in advance.
Under this practice, a court decides each case on the narrowest ground available and leaves the wider question open. The record then grows by small increments, and later cases remain free to settle what earlier ones deliberately did not.
This claim holds that rights are established by the accumulated decisions of ordinary courts rather than declared in a founding document. The general rule is a summary of what has been decided, not the source the decisions follow from.
This is the casuist's account of which circumstances of a case carry moral weight (e.g., who was involved, what was at stake, and what was known at the time). Cases are sorted by these features, and this sorting is what makes it possible to compare them.
This doctrine permits an agent to act on a defensible opinion even when a more certain one is available, provided the opinion is genuinely supported. It treats moral authority as admitting degrees rather than as either settled or absent.
An Introduction to Legal Reasoning
1949
Legal Reasoning and Political Conflict
1996
One Case at a Time (judicial minimalism)
1999
Introduction to the Study of the Law of the Constitution
1885
Determining the Ratio Decidendi of a Case
1930
The Abuse of Casuistry
1988
Probabilism (Jesuit casuist tradition)
16th-17th c.