Paper Citation Record · LEDGER

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training

As of 17 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2508.20577.

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

pith.paper-citation-record.v1
2508.20577 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:47:40.978144Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact1
verified fuzzy4
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 00536eda-e873-4e3c-8b51-e1bf92886003 · outbound

This paper cites PaLM 2 Technical Report.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training PaLM 2 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.821282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48cc2c03-4762-4358-a072-c741a91422d2 · outbound

This paper cites Layer Normalization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Layer Normalization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.826199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868a89ea-3a3c-447f-bf09-c74aca95be43 · outbound

This paper cites signSGD: Compressed Optimisation for Non-Convex Problems.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training signSGD: Compressed Optimisation for Non-Convex Problems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.830803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d258652-2810-44e7-9183-08469a9a469f · outbound

This paper cites Language Models are Few-Shot Learners.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Language Models are Few-Shot Learners

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.835099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d29b5c88-3938-489b-94ff-034d6f5dc85c · outbound

This paper cites Symbolic Discovery of Optimization Algorithms.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Symbolic Discovery of Optimization Algorithms

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.839244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cc3a860-ff08-41c3-addd-cbe10f223769 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training PaLM: Scaling Language Modeling with Pathways

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.843641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2fa216-177b-43ee-834e-28c723dc2faf · outbound

This paper cites an unresolved cited work.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:47:41.399334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9f732d36-d317-4f1d-a4f7-a79b481b3d39 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training An image is worth 16x16 words: Transformers for image recognition at scale

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.852042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb0457d-1485-439f-b709-6c19696956d8 · outbound

This paper cites The Llama 3 Herd of Models.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.855965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e7437a-44e6-420d-9b14-135720a38361 · outbound

This paper cites Sharpness-aware minimization for efficiently improving generalization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Sharpness-aware minimization for efficiently improving generalization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.860528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6f2685-e159-4453-b010-d93bc834efcd · outbound

This paper cites and Cohen, V.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training and Cohen, V

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.865458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1295bc0e-e343-4323-a6a3-02a49e75edfd · outbound

This paper cites Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.869589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b884f949-757c-48c7-a1d9-5e709626fd48 · outbound

This paper cites A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Vinyals, O., Rae, J.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Vinyals, O., Rae, J

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:47:41.369848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 86f03f8f-1343-40cf-80de-eb6c9172dc4a · outbound

This paper cites Scaling Laws for Neural Language Models.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Scaling Laws for Neural Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.877523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb8f79de-a0f2-4949-a894-29dea75f3f7e · outbound

This paper cites S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.881521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510cb7d9-b7d9-41f1-894a-5010e5426634 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Adam: A Method for Stochastic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.885254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b89311ea-5430-4b71-bbd0-3fbc8be8f149 · outbound

This paper cites BERT busters: Outlier dimensions that disrupt transformers.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training BERT busters: Outlier dimensions that disrupt transformers

Reference 17

Resolution: verified exact; doi, observed 2026-08-15T16:47:41.034630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9f59a17c-bb5c-4b79-9ca9-a0323af91dab · outbound

This paper cites an unresolved cited work.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:47:41.353406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b07209ad-15d7-437a-bcd2-8032acda675b · outbound

This paper cites Towards Efficient and Scalable Sharpness-Aware Minimization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Towards Efficient and Scalable Sharpness-Aware Minimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.896713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392d5957-3675-40b9-a941-3360fe2c57b3 · outbound

This paper cites Decoupled Weight Decay Regularization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Decoupled Weight Decay Regularization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.904282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f22d135-dcb0-4361-9708-7cd5305d35f1 · outbound

This paper cites Came: Confidence-guided adaptive memory efficient optimization.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Came: Confidence-guided adaptive memory efficient optimization

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:47:41.343360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b5bcf96-9658-45a1-a857-6b667e081f93 · outbound

This paper cites Pointer sentinel mixture models.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Pointer sentinel mixture models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.911793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7af4b4a-369b-4d7a-b103-41d95dd46cf6 · outbound

This paper cites an unresolved cited work.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:47:41.323248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cac7ff3a-7045-4055-bf1c-5aebecbb9036 · outbound

This paper cites GPT-4 Technical Report.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training GPT-4 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.919052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff089083-a098-4ad3-a2ed-0f507802c65e · outbound

This paper cites Q., Bernardi, R., Pezzelle, S., Baroni, M., Boleda, G., and Fern \'a ndez, R.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Q., Bernardi, R., Pezzelle, S., Baroni, M., Boleda, G., and Fern \'a ndez, R

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.922862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 418f4709-e72f-4744-96ea-cff99a3a1801 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.926684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb0d58c-e7bc-47b9-ae69-4492e72cc47e · outbound

This paper cites Outlier dimensions that disrupt transformers are driven by frequency.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Outlier dimensions that disrupt transformers are driven by frequency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.931126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825c7a33-3ccb-4460-9340-6766baaca385 · outbound

This paper cites Language models are unsupervised multitask learners.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Language models are unsupervised multitask learners

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.935213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c836b4-97bb-4af0-8c20-ff25fd571f9d · outbound

This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.938783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ba05fa-53cd-4014-b12f-1dbfb01ac801 · outbound

This paper cites Measuring the Effects of Data Parallelism on Neural Network Training.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Measuring the Effects of Data Parallelism on Neural Network Training

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.942556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1638893-6607-4b7d-8f13-afcb2424a852 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Dropout: a simple way to prevent neural networks from overfitting

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:47:41.301411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9799ce51-2588-4627-bfbe-83d5d0bfa779 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training LLaMA: Open and Efficient Foundation Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.950369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b13b801-1507-4023-9d38-259f4142874d · outbound

This paper cites N., Kaiser, L.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training N., Kaiser, L

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.954213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a11328-e3bd-4340-a10e-fcf52a4e3de8 · outbound

This paper cites Superglue: A stickier benchmark for general-purpose language understanding systems.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Superglue: A stickier benchmark for general-purpose language understanding systems

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:47:41.282488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0dbfa62a-575f-433d-b5ba-6ea175404b13 · outbound

This paper cites J., Xiao, L., Everett, K.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training J., Xiao, L., Everett, K

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.961712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 581456ae-21a9-451b-a5d7-a9e9e8f77c15 · outbound

This paper cites Large Batch Training of Convolutional Networks.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Large Batch Training of Convolutional Networks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.965792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 321a57a9-80d2-4797-a589-418251fd927e · outbound

This paper cites Large Batch Optimization for Deep Learning: Training BERT in 76 minutes.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.969614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe49a30-ba22-4397-9c40-aa41c4b10581 · outbound

This paper cites an unresolved cited work.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:47:41.263710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9b8adbba-b92f-43b4-8efd-97975f0c37be · outbound

This paper cites write newline.

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training write newline

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:40.978144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.