The Vapnik-Chervonenkis dimension is the fundamental combinatorial parameter of distribution-free binary classification. Introduced by Vapnik and Chervonenkis in their work on uniform convergence [VC71], and closely connected to the Sauer-Shelah lemma [Sau72, She72], it characterizes classical PAC learnability [Val84, BEHW89, EHKV89]. In particular, finite VC dimension is equivalent to distribution-free learnability. This paper asks whether that finite-versus-infinite VC dichotomy is still visible after replacing a concept class by its contradiction graphs. For a binary class H {0,1}X, the order-m contradiction graph Gm(H) has as vertices the H-realizable labeled samples of length m, with an edge between two samples if they assign opposite labels to some common domain point. Throughout, samples are ordered sequences, and repetitions of domain points are allowed, subject to consistent labeling. We use the contradiction-graph framework introduced by Alon et al. in their graph-theoretic characterization of private learnability [AMSY24]. They ask whether two binary classes can have isomorphic contradiction graphs at every level while one has finite VC dimension and the other has infinite VC dimension.

We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step solutions to math problems written by different thinkers, or step-by-step execution traces of different programs solving the same problem. We consider classes that are computationally easy to learn using CoT supervision from a single thinker, but hard to learn with only end-result supervision, i.e., without CoT (Joshi et al. 2025). We establish that, under cryptographic assumptions, learning can be hard from CoT supervision provided by two or a few different thinkers, in passive data-collection settings. On the other hand, we provide a generic computationally efficient active learning algorithm that learns with a small amount of CoT data per thinker that is completely independent of the target accuracy $\varepsilon$, a moderate number of thinkers that scales as $\log \frac{1}{\varepsilon}\log \log \frac{1}{\varepsilon}$, and sufficient passive end-result data that scales as $\frac{1}{\varepsilon}\cdot poly\log\frac{1}{\varepsilon}$.

This is the appendix for "A general approximation lower bound inLp norm, with applications to feed-forwardneuralnetworks". Layer L consists of a single node: the output neuron. Note that skip connections are allowed, i.e., there can be connections between non-consecutivelayers. We now explain how to derive Proposition 1 (with an arbitrary range[a,b]) as a straightforward consequenceofProposition7. Proof(ofProposition1). In order to apply Proposition 7, we reduce the problem from[a,b] to [0,1] by translating and rescaling every function inG.

A.1 Singleclasscase The properties of Lebesgue measure over euclidean spaceRn are recalled in [78].

Third, weintroduce acomplexitymeasure (seeDefinition 5)thatcharacterizes theoptimal sample complexity of learning in settings (ii) and (iii) above, and we give optimal algorithms for these settings. Finally,wealso provide adaptivelearning algorithms that interpolate between settings (i) and (ii), i.e., whenh is partiallyinvariant.

We study computable probably approximately correct (CPAC) learning, where learners are required to be computable functions. It had been previously observed that the Fundamental Theorem of Statistical Learning, which characterizes PAC learnability by finiteness of the Vapnik-Chervonenkis (VC-)dimension, no longer holds in this framework. Recent works recovered analogs of the Fundamental Theorem in the computable setting, for instance by introducing an effective VC-dimension. Guided by this, we investigate the connection between CPAC learning and recursively enumerable representable (RER) classes, whose members can be algorithmically listed. Our results show that the effective VC-dimensions can take arbitrary values above the traditional one, even for RER classes, which creates a whole family of (non-)examples for various notions of CPAC learning. Yet the two dimensions coincide for classes satisfying sufficiently strong notions of CPAC learning. We then observe that CPAC learnability can also be characterized via containment of RER classes that realize the same samples. Furthermore, it is shown that CPAC learnable classes satisfying a unique identification property are necessarily RER. Finally, we establish that agnostic learnability can be guaranteed for RER classes, by considering the relaxed notion of nonuniform CPAC learning.