“Probably Approximately Correct” (book)
E345815
“Probably Approximately Correct” is a 2013 book by computer scientist Leslie Valiant that explores how ideas from computational learning theory can explain intelligence, evolution, and the way we understand the world.
All labels observed (1)
| Label | Occurrences |
|---|---|
| “Probably Approximately Correct” (book) canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3308916 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Probably Approximately Correct” (book) Context triple: [Leslie Valiant, notableWork, “Probably Approximately Correct” (book)]
-
A.
The Advancement of Learning
The Advancement of Learning is a 1605 philosophical treatise by Francis Bacon that argues for the systematic reform and expansion of human knowledge through empirical inquiry and the scientific method.
-
B.
In a World of Pseudorandomness
"In a World of Pseudorandomness" is a theoretical computer science work exploring the foundations, constructions, and implications of pseudorandomness in computation and cryptography.
-
C.
Outside in the Teaching Machine
Outside in the Teaching Machine is a collection of essays by postcolonial theorist Gayatri Chakravorty Spivak that critiques global capitalism, education, and representation from the perspective of marginalized voices.
-
D.
How to Create a Mind
"How to Create a Mind" is a nonfiction book by futurist Ray Kurzweil that explores the workings of human intelligence and proposes designs for advanced artificial intelligence based on the brain’s principles.
-
E.
The Universal Computer
The Universal Computer is a book by mathematician and logician Martin Davis that traces the history and development of the concept of computation and the universal Turing machine.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: “Probably Approximately Correct” (book) Target entity description: “Probably Approximately Correct” is a 2013 book by computer scientist Leslie Valiant that explores how ideas from computational learning theory can explain intelligence, evolution, and the way we understand the world.
-
A.
The Advancement of Learning
The Advancement of Learning is a 1605 philosophical treatise by Francis Bacon that argues for the systematic reform and expansion of human knowledge through empirical inquiry and the scientific method.
-
B.
In a World of Pseudorandomness
"In a World of Pseudorandomness" is a theoretical computer science work exploring the foundations, constructions, and implications of pseudorandomness in computation and cryptography.
-
C.
Outside in the Teaching Machine
Outside in the Teaching Machine is a collection of essays by postcolonial theorist Gayatri Chakravorty Spivak that critiques global capitalism, education, and representation from the perspective of marginalized voices.
-
D.
How to Create a Mind
"How to Create a Mind" is a nonfiction book by futurist Ray Kurzweil that explores the workings of human intelligence and proposes designs for advanced artificial intelligence based on the brain’s principles.
-
E.
The Universal Computer
The Universal Computer is a book by mathematician and logician Martin Davis that traces the history and development of the concept of computation and the universal Turing machine.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf | book ⓘ |
| aimsTo |
connect evolution with learning theory
ⓘ
make learning theory accessible to non-specialists ⓘ provide a computational explanation of intelligence ⓘ |
| author |
Leslie Valiant
ⓘ
surface form:
Leslie G. Valiant
Leslie Valiant ⓘ |
| authorAffiliation | Harvard University ⓘ |
| authorNationality |
American
ⓘ
British ⓘ |
| countryOfOrigin |
United States of America
ⓘ
surface form:
United States
|
| discusses |
algorithmic view of the natural world
ⓘ
limits of computation in learning ⓘ relationship between learning and evolution ⓘ |
| explainsConcept |
computational view of evolution
ⓘ
ecorithms ⓘ probably approximately correct learning ⓘ |
| explores |
how learning theory explains evolution
ⓘ
how learning theory explains intelligence ⓘ how learning theory explains scientific understanding ⓘ |
| field |
computer science
ⓘ
learning theory ⓘ theoretical computer science ⓘ |
| genre |
non-fiction
ⓘ
popular science ⓘ science book ⓘ |
| hasAuthorProfession | computer scientist ⓘ |
| hasForm |
ebook
ⓘ
hardcover ⓘ paperback ⓘ |
| hasNotableConcept |
Probably Approximately Correct learning (PAC learning)
ⓘ
surface form:
PAC learning framework
computational theory of evolution ⓘ ecorithm ⓘ |
| language | English ⓘ |
| mainSubject |
Probably Approximately Correct learning (PAC learning)
ⓘ
surface form:
PAC learning
artificial intelligence ⓘ complexity theory ⓘ computational learning theory ⓘ evolution ⓘ machine learning ⓘ scientific explanation ⓘ theory of intelligence ⓘ |
| proposes | ecorithms as models of natural learning processes ⓘ |
| publicationYear | 2013 ⓘ |
| subtitle | Nature’s Algorithms for Learning and Prospering in a Complex World ⓘ |
| targetAudience |
general audience
ⓘ
readers interested in AI ⓘ readers interested in evolution ⓘ |
| title |
Probably Approximately Correct learning (PAC learning)
ⓘ
surface form:
Probably Approximately Correct
|
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: “Probably Approximately Correct” (book) Description of subject: “Probably Approximately Correct” is a 2013 book by computer scientist Leslie Valiant that explores how ideas from computational learning theory can explain intelligence, evolution, and the way we understand the world.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.