Where Induction Runs Out: Description-Length Difficulty and the Memorisation Gap in Integer-Sequence Benchmarks
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Where Induction Runs Out: Description-Length Difficulty and the Memorisation Gap in Integer-Sequence Benchmarks
Abstract:Integer sequences from the On-Line Encyclopedia of Integer Sequences (OEIS) are increasingly used to benchmark mathematical reasoning in language models. We ask what such benchmarks actually measure, using an exactly computable reference learner: two-part minimum description length (MDL) over the class of P-recursive (holonomic) recurrences, evaluated on every prefix of a sequence as terms arrive. Three findings follow. First, MDL difficulty is a parameter count. The discovery point nd, the first prefix length at which a symbolic hypothesis beats verbatim storage, is predicted almost exactly by a combinatorial identifiability bound on the selected operator's order and degree. It is invariant to term magnitude: scaling Fibonacci over twelve orders of magnitude leaves nd unchanged, because a hypothesis must encode its own initial conditions and the magnitude cancels. Second, at scale the learner exhibits a regime our curated corpus could not produce even once: across 20,000 OEIS sequences, 89.98% of those that fit a recurrence on some prefix fit none at full length. We call this the wilderness -- induction acquires a theory, loses it, and never recovers. Third, evaluating three language models on sequences stratified by these MDL regimes refuted our pre-registered hypothesis: models do not confabulate where MDL reports no theory, but hedge appropriately. Confident errors are inverted, concentrating on the easy stratum, where apparent competence tracks recognition of the sequence rather than induction of its rule. OEIS-derived benchmarks therefore substantially measure memorisation, and MDL supplies a cheap, contamination-free difficulty signal they currently lack. Code and data are released.
| Comments: | 14 pages, 6 figures. Code and data: this https URL. Archived: doi:https://doi.org/10.5281/zenodo.21830331 |
| Subjects: | Machine Learning (cs.LG); Symbolic Computation (cs.SC) |
| Cite as: | arXiv:2608.29411 [cs.LG] |
| (or arXiv:2608.29411v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2608.29411
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Sabilashan Ganeshan [view email][v1] Sat, 29 Aug 2026 19:25:31 UTC (92 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems
Sep 14
-
Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators
Sep 14
-
Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
Sep 14
-
Efficient AI Model Deployment Using Quantization Analysis Tool
Sep 14
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.