paper_id	claim	claim_status	evidence_status	source_depth	source_quote	page_or_section	taxonomy_fit	audit_status
2602.07488v2	We provide the first such theory in the case of data-limited scaling laws.	supported	has evidence row	full-text	Overall, this work unravels, for the first time, adi- rectlink between the shape of neural scaling laws and the statistical structure of language itself. 1.1.	16	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2509.24882v2	We provide a sharp characterization of the excess risk achieved by empirical risk minimization for both diagonal linear networks and quadratic networks in the regime n, d≫ 1 with p≥d, under a power-law design for the target function and varying regularization strength λ.	supported	has evidence row	full-text	Together, these results provide a comprehensive theoretical and empirical understanding of scaling laws for feature learning in simple network models. 1.2 Further Relevant work Scaling laws —A large body of work has studied scaling laws in the lazy regime, where the features remain fixed.	1.1 Main Results	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2605.26248v1	A functional form that accurately models and extrapolates the scaling behaviors of deep neural networks as multiple dimensions all vary simultaneously.	supported	has evidence row	full-text	When compared to other functional forms for neural scaling, this functional form yields extrapolationsof scaling behavior that are considerably more accurate on this set. 1 INTRODUCTION Training today’s state-of-the-art neural networks requires significant amounts of computational resources and training data.	1	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2411.17691v2	We reveal that low-bit quantization favors undertrained LLMs but suffers from significant quantization-induced degradation (QiD) when applied to fully trained LLMs.	supported	has evidence row	full-text	The contributions of this work are threefold: •We reveal that low-bit quantization favors undertrained LLMs but suffers from significant quantization-induced degradation (QiD) when applied to fully trained LLMs.	Abstract	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2602.02593v1	We propose a unified framework that conceptualizes learning as the progressive advancement of an Effective Frontier k⋆ in the rank space.	preliminary-linked	has evidence row	full-text	Theorem 3.3(Universal Scaling Principle). Under Assumption 2.1 ∼2.2, if a resource R induces a effective frontier k⋆(R)(Definition 3.2), the reducible loss scales as: ∆L(R)≍k ⋆(R)−(α−1).	Section 3	in-scope: LLM extractor confirmed direction match	needs work; filled but source-depth unclear; report=audit_report.md