The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
A formal theory of inductive inference. Part I
Open accessAbstract
The following sections will apply the foregoing induction systems to three specific types of problems, and discuss the "reasonableness" of the results obtained. Section 4.1 deals with the Bernoulli sequence. The predictions obtained are identical to those given by "Laplace's Rule of Succession." A particularly important technique is used to code the original sequence into a set of integers which constitute its "descriptions" for the problems of Sections 4.2 and 4.3. Section 4.2 deals with the extrapolation of a sequence in which there are certain kinds of intersymbol constraints. Codes for such sequences are devised by defining special symbols for subsequenees whose frequencies are unusually high or low. Some properties of this coding method are discussed, and they are found to be intuitively reasonable. A preliminary computer program has been written for induction using this coding method. However, there are some important simplifications used in the program, and it is uncertain as to whether it can make useful predictions. Section 4.3 describes the use of phrase structure grammars for induction. A formal solution is presented and although the resultant analysis indicates tha t this model conforms to some extent to intuitive expectations, the author feels tha t it still has at least one serious shortcoming in
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The ability to generalise is closely related to compression [14,15], with more compressed representations yielding better accuracy [13] for the same reason that there is only one straight line interpolating any two points, but infinitely many polynomials of higher degree.”
From Compression, The Fermi Paradox and Artificial Super-Intelligence (2022) · cites this paper as [14]
In the citing paper
“Kolmogorov complexity is in general uncomputable, and, therefore, of limited practical interest.”
From Meta-learned models of cognition (2024) · cites this paper as Solomonoff, 1964
In the citing paper
“However, even in the absence of external influences, deep networks naturally adhere to Occam's razor, implicitly favoring simple solutions that fit the data (Solomonoff, 1964;Gunasekar et al., 2018;Arora et al., 2019a;Valle-Perez et al., 2019;Huh et al., 2023;Dingle et al., 2018;Goldblum et al., 2023).”
From The Platonic Representation Hypothesis (2024) · cites this paper as Solomonoff, 1964
In the citing paper
“In a loose sense, FunSearch attempts to find solutions that have low Kolmogorov complexity48–50 (which is the length of the shortest computer program that produces a given object as output), whereas traditional search procedures have a very different inductive bias.”
From Mathematical discoveries from program search with large language models (2024) · cites this paper as [50]
Citations
Cites
On computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283
Three models for the description of language
Chomsky, N. (1956) · IEEE Transactions on Information Theory · doi:10.1109/tit.1956.1056813 · Cited by 2,796 · cited 2×
“The method that will be used is equivalent to finding a PSL (context free phrase structure language, Chomsky (1956)) that in some sense best "fits" the set [al]. The measure of goodness of fit will be the product of the a-priori probability of the language selected and the probability that the language selected would…”
MethodLogical Foundations of Probability.
Burks, A. W., & Carnap, R. (1951) · The Journal of Philosophy · doi:10.2307/2021419 · Cited by 2,370
Computer Languages for Symbol Manipulation
Green, B. F. (1961) · IRE Transactions on Electronic Computers · doi:10.1109/tec.1961.5219281 · Cited by 11
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
The definition of random sequences
Martin-Löf, P. (1966) · Information and Control · doi:10.1016/s0019-9958(66)80018-9 · Cited by 1,220
A theory and methodology of inductive learning
Michalski, R. S. (1983) · Artificial Intelligence · doi:10.1016/0004-3702(83)90016-4 · Cited by 1,002
The minimum description length principle in coding and modeling
Barron, A., Rissanen, J., & Yu, B. (1998) · IEEE Transactions on Information Theory · doi:10.1109/18.720554 · Cited by 1,019
Managing artificial intelligence
Berente, N., Gu, B., Recker, J., & Santhanam, R. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16274 · Cited by 898
Metadata
- Authors
- Solomonoff, R. J.
- Corresponding author
- Solomonoff, R.J.
- Venue
- Information and Control
- Publisher
- Elsevier BV
- Published
- 1964-03
- Volume
- 7
- Issue
- 1
- Pages
- 1-22
- ISSN
- 0019-9958 (ISSN-L)
- OpenAlex
- W4213350211
- Cited by
- 1,192
- References
- 4
- Citations by year
- 2026: 36 · 2025: 37 · 2024: 31 · 2023: 47 · 2022: 74 · 2021: 39 · 2020: 31 · 2019: 29 · 2018: 45 · 2017: 40 · 2016: 40 · 2015: 37 · 2014: 32 · 2013: 54 · 2012: 42
- FWCI
- 0.51
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (vor, 18337 d)
- Locations
- Information and Control (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computability, Logic, AI Algorithms
- Physical Sciences › Computer Science › Computational Theory and Mathematics › semigroups and automata theory
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- inductive reasoning, universal Turing machine, phrase structure grammar
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A formal theory of inductive inference. Part I. https://app.cochat.ai/papers/10.1016/s0019-9958(64)90223-2
- The paper
- Solomonoff, R. J. (1964). A formal theory of inductive inference. Part I. Information and Control. https://doi.org/10.1016/s0019-9958(64)90223-2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.