Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T13:01:16.734876Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 1 inbound Pith citation observation for arXiv:2505.23013.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T13:01:16.734876Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-04T13:54:14.882976Z
A source-named dated measurement, never combined with another source.
Source: cited_works
91 of 91 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 5457f73d-7ac0-475d-bf02-d362e3618e9c · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs https://github.com/microsoft/Megatron-DeepSpeed, 2022
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2a9b256-73be-4ca9-b7fb-a2e5e5d92217 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs GPT-4 Technical Report
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6bf9b84-1ad7-4f48-b755-584fa896a6bf · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Physics of Language Models: Part 3.2, Knowledge Manipulation
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5eb13650-0a32-45e3-9c7b-46d0dc03d08a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs On exact computation with an infinitely wide neural net
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d61a9c0b-c1d3-4b02-af57-54e9e169d93b · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Stronger generalization bounds for deep nets via a compression approach
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a433bd0-383a-47c6-bf63-5580513c8bba · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Program Synthesis with Large Language Models
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 48f30585-57a1-4125-9f61-90a465821b75 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Spectrally-normalized margin bounds for neural networks
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af5f868e-1dc4-4f20-aafd-43bea8489f15 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Rademacher and gaussian complexities: Risk bounds and structural results
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 908ff992-fbb6-45d9-b40b-6b3b6d77018a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Phase dia- gram of initial condensation for two-layer neural networks
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95e387de-012b-4965-bbb6-7a0e72a48b2b · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs On the global convergence of gradient descent for over- parameterized models using optimal transport
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f6a14e24-ec22-4d8f-b3c3-1fefbf5fbb0d · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c273550-96d4-4bc5-a178-240fe84006b8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Training Verifiers to Solve Math Word Problems
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ade86d39-b6c9-409f-a08d-fa7154f9013a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Hwang, Soumya Sanyal, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, and Yejin Choi
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c7b4fe34-ce64-473d-acbf-0fac6dfb573d · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 172ebb0d-7afb-4666-a22e-f67de9f50e26 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Machine learning from a continuous viewpoint, I
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b278425-63ce-4fcf-90ee-d470f3a9d9da · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs The Barron space and the flow-induced function spaces for neural network models
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87b12a14-9648-4cf6-9e41-52d48731a592 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Representation formulas and pointwise properties for Barron functions
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b942faf0-0b3b-48ae-9c33-198240fb283b · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Towards revealing the mystery behind chain of thought: A theoretical perspective
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 121d19d2-58df-4ee7-86e2-6d89ffd18cfb · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs The language model evaluation harness, 07 2024
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be5019ee-90a2-4eb5-ac33-96b7e95b27b8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Size-independent sample complexity of neural networks
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2cd7b32b-d1f4-4670-a0c8-bcb1e543ce21 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 461499a4-7ddb-4d0a-a5cc-6e641eb739f7 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bf634ed-110b-406a-8a43-fef6869be0c9 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Measuring Massive Multitask Language Understanding
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3d437b45-dde5-465a-85fc-13a3b0ca345f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Measuring Mathematical Problem Solving With the MATH Dataset
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39f72398-a770-45c8-ab2f-1365577a5abb · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Improving transformer optimization through better initialization
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 73d6da20-4525-4d4f-837c-c42a30b20276 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c45fabec-fa96-466a-9490-652c98463f1a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Neural tangent kernel: Convergence and generalization in neural networks
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c3f81ff-b4d2-4958-b9cc-b2449e994c90 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Unresolved cited work
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 424f633e-088d-41e0-9a81-1f5bea2e60a4 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs A simple weight decay can improve generalization
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e88b0141-ae3c-4763-b62a-239c05c474df · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Training Language Models to Self-Correct via Reinforcement Learning
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90ab2c2c-e78f-4af6-9149-c42bd88546c8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Orr, and Klaus Robert Müller
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e0f86fe0-be75-4123-a2ce-dabc152a9a38 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Cmmlu: Measuring massive multitask language understanding in chinese, 2023
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a466707f-56ba-459b-9aa4-b4f8375cbe6f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Chain of thought empowers transformers to solve inherently serial problems
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1049df3d-f2de-4e82-9cda-4b16a2680ed7 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Truthfulqa: Measuring how models mimic human falsehoods, 2021
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e5abf49-4540-45ec-b04d-0cff66ce79e1 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Unresolved cited work
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 517e97b2-521b-43d8-8be7-40fda7621f3e · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs DeepSeek-V3 Technical Report
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 281783b6-e49b-4986-9cd9-02e36e31483e · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Crystal: Introspective reasoners reinforced with self-feedback
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cba16ffd-1a5f-4d76-988d-a4abbe2cb58f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Understanding the Difficulty of Training Transformers
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2bdf455f-ef31-4081-b330-7f39dd292aeb · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Phase diagram for two-layer relu neural networks at infinite-width limit
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 953116e3-88f8-4453-a09b-99798707fae1 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs A mean field view of the landscape of two-layer neural networks
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bcaf3a6a-2621-420c-932a-0ceaf9d60fcd · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Can a suit of armor conduct electricity? a new dataset for open book question answering
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44f8c287-b220-41e1-b26c-e10ca82e424b · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Norm-based capacity control in neural networks
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8f61ea8f-5c8f-45e5-b8d4-e9bdf6bb3f22 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs In-context learning and induction heads, 2022
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7db0732a-5484-4500-bbfe-0e9e45f6dc9f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4d96f11a-3ee5-42d9-b622-e98f25972de6 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Measuring and narrowing the compositionality gap in language models
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ea5228b0-35dc-4efc-97c1-a02611524227 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Li, and Noah Goodman
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2ca62aca-d0df-4c18-827a-b412e7ae34d5 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f108e1d2-904b-42ad-9d02-03f3ec6646cc · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Uniform approximation of functions with random bases
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ee3d5132-a479-4890-8994-71d7b01ebb0c · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Gpqa: A graduate-level google-proof q&a benchmark
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c60af0c1-f4ef-405e-ae16-1928492dea00 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks
Reference 50
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 57b20b7f-406e-4bf3-b466-700e0343ddd0 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Winogrande: An adversarial winograd schema challenge at scale
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 82817998-373a-48a6-a49c-1d7da5fd2630 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Mean field analysis of neural networks: A central limit theorem
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a284127-eb2c-4018-8b3e-2419982650f5 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs SlimPajama: A 627B token cleaned and deduplicated version of RedPajama
Reference 53
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a49ef92b-5ad1-4ceb-b084-ca6838b02859 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Recitation-augmented language models
Reference 54
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 32310810-35d0-46e4-9e92-890131eae86f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
Reference 55
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 693d7810-b491-4777-b924-70eec4ffef8a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs olmpics-on what language model pre-training captures
Reference 56
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2498b933-0398-43ec-9462-a2ccd3d76478 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs CommonsenseQA: A question answering challenge targeting commonsense knowledge
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ac688fde-78a6-4324-ba97-5d054b801415 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 58
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e9d3c00-c851-4d59-9b6f-298b726a0cc7 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Mimetic initialization of self-attention layers
Reference 59
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 790fd982-3074-4413-94f2-0f2ce10c7405 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Explaining grokking through circuit efficiency
Reference 60
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d14d5aed-b5c6-4070-ab2d-f07fb1bdb810 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Deepnet: Scaling transformers to 1,000 layers
Reference 61
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 69ff8425-0302-461d-bc27-ff8c59f13279 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Interpretability in the wild: a circuit for indirect object identification in GPT-2 small
Reference 62
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e5f5057-f236-4bcc-8e0b-50f92b10b9a8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
Reference 63
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9077a94c-a589-42cc-9935-5132c010d123 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Mmlu-pro: A more robust and challenging multi-task language understanding benchmark
Reference 64
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b45ce7ed-af2c-4cd7-b6bf-10cec7778aab · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Data-dependent sample complexity of deep neural networks via lipschitz augmentation
Reference 65
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 88c5ce30-60c5-4d6d-8d09-f84573b1bcdd · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus
Reference 66
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c70e5f60-ba96-43b7-bf19-2acbfab72c5c · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Chain-of-thought prompting elicits reasoning in large language models
Reference 67
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce639f83-6e4a-4c36-8b3c-90595941b8c5 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Gradient Dynamics of Shallow Univariate ReLU Networks
Reference 68
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8676d420-e160-48d1-9221-7ae600eb002b · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs An overview of condensation phenomenon in deep learning
Reference 69
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ffe451a-b0ad-4059-aa26-476030934fb2 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Qwen2.5 Technical Report
Reference 70
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c5d6f6de-09fb-47ca-884a-70a91a2dfb7d · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Memory 3: Language modeling with explicit memory
Reference 71
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 48406109-4071-4bce-a63b-9704781068d3 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Do Large Language Models Latently Perform Multi-Hop Reasoning?
Reference 72
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b8fc0767-8d84-497a-abfa-5756056ee175 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs An Analysis for Reasoning Bias of Language Models with Small Initialization
Reference 73
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1332bd4b-75a8-4d27-8c5a-4ee78f92f64f · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Reference 74
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64dcd9ba-ee72-478d-a7a1-fcc0d4adf224 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs STar: Bootstrapping reasoning with reasoning
Reference 75
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23b33b18-a34a-4001-a930-8ec0b9994de9 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Hellaswag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019
Reference 76
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 76bc0cd3-7146-40ba-8227-3fc877d7551a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs PanGu-$\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Reference 77
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 603b62c3-90be-4501-a832-17b5326ec18a · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
Reference 78
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 47513559-7eed-4827-ac62-09b03f2b1bed · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Understanding deep learning (still) requires rethinking generalization
Reference 79
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b493c1c3-2c72-440e-8a48-caffdba9fbaa · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs A type of generalization error induced by initialization in deep neural networks
Reference 80
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 987b80f7-5761-4632-af58-b13023f10df8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Linear Stability Hypothesis and Rank Stratification for Nonlinear Models
Reference 81
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 748fc06e-a645-429a-9728-05d84920d1c8 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Stochastic Modified Equations and Dynamics of Dropout Algorithm
Reference 82
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2997f494-9abe-4edd-a981-3dc1de38e6cd · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Initial- ization is critical to whether transformers fit composite functions by reasoning or memorizing
Reference 83
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cedd0c3e-339a-4303-b315-50e0c1845b91 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
Reference 84
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f4fd1f6-9a96-4f81-8ef5-72a172a9a297 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Loss Spike in Training Neural Networks
Reference 85
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eaa04008-3c79-46bc-9ec1-3459ed5cfe62 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Implicit regularization of dropout
Reference 86
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation aad62654-f98b-45a0-bf83-193d3f8d7827 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Reference 87
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2885099e-3d38-421a-adbc-5aa65931bf0d · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Empirical phase diagram for three-layer neural networks with infinite width
Reference 88
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 74d195da-2e08-4aa7-a1b5-2ed14935e9a3 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Towards understand- ing the condensation of neural networks at initial training
Reference 89
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f4ca6c82-34c1-4b20-8b10-2c3704c4a8e9 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs Instruction-following evaluation for large language models, 2023
Reference 90
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6615ec43-35b0-4841-8c9d-64592666f755 · outbound
Scalable Complexity Control Facilitates Reasoning Ability of LLMs 0.9B Large
Reference 91
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6e413ba7-37c3-42d9-a3d8-908253c3a3fa · inbound
Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge Scalable Complexity Control Facilitates Reasoning Ability of LLMs
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.