Paper Citation Record · LEDGER

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

As of 18 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 3 inbound Pith citation observations for arXiv:2602.02472.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.02472 v2

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:27:12.839838Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-14T20:00:47.126736Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-14T20:02:53.043428Z

Reference resolution

50 of 50 outbound references displayed

verified exact1
verified fuzzy0
unresolved47
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bfe019ea-afb8-4994-b552-739c1ba0cf61 · outbound

This paper cites Cottrell, and Julian McAuley.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Cottrell, and Julian McAuley

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:08.698711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72749b4e-9227-47bc-97e2-7dfc9adbfb82 · outbound

This paper cites The affine divergence: Aligning activation updates beyond normalisation, 2025.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning The affine divergence: Aligning activation updates beyond normalisation, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:08.755807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 668eae09-1ed7-4d06-be8c-1e051075be63 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7432–7439, Apr.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Piqa: Reasoning about physical commonsense in natural language.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7432–7439, Apr

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:08.909805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a41c74f-bec8-482b-b3ef-4dc16c31c9c4 · outbound

This paper cites Language models are few-shot learners.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Language models are few-shot learners

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.050001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be4ee24-ffa7-41ac-b263-ccb66b0feab8 · outbound

This paper cites bert2BERT: Towards reusable pretrained language models.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning bert2BERT: Towards reusable pretrained language models

Reference 5

Resolution: verified exact; doi, observed 2026-08-03T05:28:21.207214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 81d9c704-8602-456c-abc2-a92a67d28ab6 · outbound

This paper cites Net2Net: Accelerating Learning via Knowledge Transfer.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Net2Net: Accelerating Learning via Knowledge Transfer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.289771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636d656a-0c89-402f-92a4-25e9393a0567 · outbound

This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.465067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed5029ad-df7d-480a-927d-8ab30d78ca35 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.553477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a46d99-048e-4214-a9a6-6dad709e81a7 · outbound

This paper cites DeepSeek-V3 Technical Report.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning DeepSeek-V3 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.643024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1655b79-3021-48d8-8666-2e753809b7fc · outbound

This paper cites Stacking your transformers: A closer look at model growth for efficient llm pre-training.Advances in Neural Information Processing Systems, 37:10491–10540, 2024.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Stacking your transformers: A closer look at model growth for efficient llm pre-training.Advances in Neural Information Processing Systems, 37:10491–10540, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.718969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28fc6e0-50ac-4c69-a32e-2076e3f9913b · outbound

This paper cites GradMax: Growing Neural Networks using Gradient Information.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning GradMax: Growing Neural Networks using Gradient Information

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.807211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7e5cf1-a23e-4f32-89c5-753162d87f1f · outbound

This paper cites Efficient training of bert by progressively stacking.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Efficient training of bert by progressively stacking

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.891745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d734d9-aabd-4a83-8df9-6c65733cf886 · outbound

This paper cites Loire: Lifelong learning on incremental data via pre-trained language model growth efficiently.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Loire: Lifelong learning on incremental data via pre-trained language model growth efficiently

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:09.969514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40da7219-5321-418f-8124-4684abadae20 · outbound

This paper cites Measuring massive multitask language understanding.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Measuring massive multitask language understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.023536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7ec4c3b-c1d7-415f-928d-3e4eae9c2d6b · outbound

This paper cites Muon: An optimizer for hidden layers in neural networks, 2024.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Muon: An optimizer for hidden layers in neural networks, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.184166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa715f27-5814-41aa-bf1c-c89e63e7194d · outbound

This paper cites Scaling Laws for Neural Language Models.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Scaling Laws for Neural Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.243526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2abbd0-1b01-4898-b68b-1f0d940184aa · outbound

This paper cites Solar 10.7 b: Scaling large language models with simple yet effective depth up-scaling.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Solar 10.7 b: Scaling large language models with simple yet effective depth up-scaling

Reference 17

Resolution: malformed identifier; no resolver link, observed 2026-08-03T05:27:10.302920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f628a8-daea-4fbf-8d14-e5bcf9243c97 · outbound

This paper cites Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.359838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd02246-9016-4e27-94dc-59067dfd3c17 · outbound

This paper cites Muon is Scalable for LLM Training.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Muon is Scalable for LLM Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.427125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1e7fcdf-a861-4ecf-b2dd-889393b7dfff · outbound

This paper cites Decoupled weight decay regularization.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Decoupled weight decay regularization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.522648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d895c92-ad9c-48cd-913b-bacc4c43de67 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.574792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8c3870-7a4d-4587-a946-17c19b7339e0 · outbound

This paper cites Smith, Pang Wei Koh, Amanpreet Singh, and Hannaneh Hajishirzi.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Smith, Pang Wei Koh, Amanpreet Singh, and Hannaneh Hajishirzi

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.666925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bfd96a4-fb79-4314-a2c0-515b863095f7 · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning OLMoE: Open Mixture-of-Experts Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.760150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35ceaa88-2379-4fcc-b792-ba64f5c2a455 · outbound

This paper cites Reusing pretrained models by multi-linear operators for efficient training.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Reusing pretrained models by multi-linear operators for efficient training

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.875800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce0e09d-da25-4f78-9175-da2294b9c609 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8732–8740, Apr.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Winogrande: An adversarial winograd schema challenge at scale.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8732–8740, Apr

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.914863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb6aaa6-c2ee-4586-8aea-dd4862d9a071 · outbound

This paper cites Social IQa: Commonsense reasoning about social interactions.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Social IQa: Commonsense reasoning about social interactions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.118893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94fe646d-36db-4d3f-8e10-e2fc9168bec0 · outbound

This paper cites Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.288777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04edbce-6c36-493c-b6c0-4460c4149aa2 · outbound

This paper cites Staged Training for Transformer Language Models.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Staged Training for Transformer Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.339717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916522cf-57c9-4257-8041-9fd6b4c8aecd · outbound

This paper cites CommonsenseQA: A question answering challenge targeting commonsense knowledge.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning CommonsenseQA: A question answering challenge targeting commonsense knowledge

Reference 29

Resolution: malformed identifier; no resolver link, observed 2026-08-03T05:27:11.428920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e30a5e-43eb-4edf-8f72-a0b350944e60 · outbound

This paper cites Learning to grow pretrained models for efficient transformer training.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Learning to grow pretrained models for efficient transformer training

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.499849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b7a6ed-4603-4086-b39f-5560c34982af · outbound

This paper cites LEMON: Lossless model expansion.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning LEMON: Lossless model expansion

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.589782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bfe53c5-4511-4940-9e97-e34a7d9e13ab · outbound

This paper cites Liu, and Matt Gardner.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Liu, and Matt Gardner

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.735079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5777e0f-7155-4334-87a6-6068c55c0a19 · outbound

This paper cites LLaMA pro: Progressive LLaMA with block expansion.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning LLaMA pro: Progressive LLaMA with block expansion

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.827614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a80e592b-b5fd-4b8d-b073-224a7dae5ff9 · outbound

This paper cites Splitting steepest descent for growing neural architectures.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Splitting steepest descent for growing neural architectures

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.896296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2fa2d2-17cc-4b36-89a9-0404091186ba · outbound

This paper cites Firefly neural architecture descent: a general approach for growing neural networks.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Firefly neural architecture descent: a general approach for growing neural networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.986365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0e1600-cd52-48e4-874c-96c666a93b84 · outbound

This paper cites Qwen3 Technical Report.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Qwen3 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.045565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578dc4ff-6366-41e4-a264-07fa25860ce0 · outbound

This paper cites Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.128943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b000a58-37e8-4306-b5c5-7c2ae9ac8dca · outbound

This paper cites Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.183400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a49ca44f-11b2-42cb-a527-73bce849d492 · outbound

This paper cites Lesa: Learnable llm layer scaling-up.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Lesa: Learnable llm layer scaling-up

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.265681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17334999-d331-4022-94d6-1d404401a96c · outbound

This paper cites Efficient construction of model family through progressive training using model expansion.CoRR, abs/2504.00623, April 2025.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Efficient construction of model family through progressive training using model expansion.CoRR, abs/2504.00623, April 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.346769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06c16bb1-3e0d-4a81-ade1-f355ef23037d · outbound

This paper cites Masked structural growth for 2x faster language model pre- training.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Masked structural growth for 2x faster language model pre- training

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.448978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f995f5-c0ae-45a9-9fb8-23c04273e03e · outbound

This paper cites Accelerated training via incrementally growing neural networks using variance transfer and learning rate adaptation.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Accelerated training via incrementally growing neural networks using variance transfer and learning rate adaptation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.528076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0056c01a-ba76-4ce5-82cb-d7d9018d7505 · outbound

This paper cites an unresolved cited work.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.611710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92e6da55-0b66-401c-a1f8-b26ff1b6bb31 · outbound

This paper cites Root mean square layer normalization.Advances in neural information processing systems, 32, 2019.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Root mean square layer normalization.Advances in neural information processing systems, 32, 2019

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.677568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d54210d-c173-4cda-878e-957d15cd8593 · outbound

This paper cites AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.779137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434b1a2c-dbe2-440f-a3b2-949dae129fbb · outbound

This paper cites an unresolved cited work.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:12.839838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 655c76ba-82f7-45a4-9bf7-ad76367d395f · outbound

This paper cites doi: 10.18653/v1/D19-1454.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning doi: 10.18653/v1/D19-1454

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.211610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df65068e-a0c6-4c10-8a73-062a65fe24dc · outbound

This paper cites URLhttps://ojs.aaai.org/index.php/AAAI/article/view/6399.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning URLhttps://ojs.aaai.org/index.php/AAAI/article/view/6399

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.003973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6891302-9cf2-4f07-994b-7b81c9e82fe5 · outbound

This paper cites an unresolved cited work.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Unresolved cited work

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:10.081047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132f7e99-390a-4b15-bcca-cd289dd65bbb · outbound

This paper cites an unresolved cited work.

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T05:27:11.658837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 07a51333-4fa4-4b00-b560-897cd477fb50 · inbound

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts cites this paper.

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:18:06.134504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 30cb0f66-efd6-4f61-a052-6e254deb1f49 · inbound

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts cites this paper.

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:18:06.134504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9d8fb988-dd5a-4056-b221-c6d9a04fc9e8 · inbound

When is Warmstarting Effective for Scaling Language Models? cites this paper.

When is Warmstarting Effective for Scaling Language Models? SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:18:06.134504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.