Paper Citation Record · LEDGER

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

As of 14 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 7 inbound Pith citation observations for arXiv:2507.17634.

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

pith.paper-citation-record.v1
2507.17634 v2

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:49:40.374840Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T08:04:06.432613Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:48:39.719025Z

Reference resolution

70 of 70 outbound references displayed

verified exact1
verified fuzzy24
unresolved43
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b40b8c51-98bd-4592-9a8a-ea78cbd8178f · outbound

This paper cites write newline.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.161054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5c0682f-0a66-4e98-9e9f-94ecc31f50b9 · outbound

This paper cites Command A: An Enterprise-Ready Large Language Model.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Command A: An Enterprise-Ready Large Language Model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.164771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7cc77a-cbd0-4bf7-8520-8567d0c59a48 · outbound

This paper cites GQA: training generalized multi-query transformer models from multi-head checkpoints.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training GQA: training generalized multi-query transformer models from multi-head checkpoints

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.168634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7653a452-a6eb-4708-9b21-6b8f59e459ad · outbound

This paper cites Singular value decomposition for genome-wide expression data processing and modeling.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Singular value decomposition for genome-wide expression data processing and modeling

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.951863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bf4ac10f-53f1-4cd0-96a7-47579c692fe4 · outbound

This paper cites Efficient Training of Language Models to Fill in the Middle.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Efficient Training of Language Models to Fill in the Middle

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.174037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d0af229-8979-4c47-833e-111f69af968c · outbound

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

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.177307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c452095-68dd-4574-9f1b-931eb1cd1d41 · outbound

This paper cites PIQA: reasoning about physical commonsense in natural language.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training PIQA: reasoning about physical commonsense in natural language

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.180214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ed7f98-a06d-4b5e-bf2e-b71b4ef485e4 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Evaluating Large Language Models Trained on Code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.183110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ff99f4-5945-4f0f-93bd-03462c4a5d28 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.186163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ddb38eb-9df7-4a41-b576-9e4050683a22 · outbound

This paper cites DeepSeek-V3 Technical Report.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training DeepSeek-V3 Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.189875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f23933e-377f-4d5a-812e-ac93845b4613 · outbound

This paper cites Optimal Linear Decay Learning Rate Schedules and Further Refinements.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Optimal Linear Decay Learning Rate Schedules and Further Refinements

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.192955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203545ba-b5b0-4689-8d7b-921ea7f367f0 · outbound

This paper cites The road less scheduled.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training The road less scheduled

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.944051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 86616692-7305-4c4c-a24b-b033ff50d23a · outbound

This paper cites Ernie 4.5 technical report, 2025.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Ernie 4.5 technical report, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.936385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eb8d68e8-e2b1-440e-8eb8-c05cad23f7a8 · outbound

This paper cites A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.929541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a9488bd-2143-49cf-83f2-7c3034dbff2c · outbound

This paper cites The Llama 3 Herd of Models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.203886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e031a19-d770-4c7a-bbdc-97905fb8be40 · outbound

This paper cites Cruxeval: A benchmark for code reasoning, understanding and execution.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Cruxeval: A benchmark for code reasoning, understanding and execution

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.921888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 767a9476-fe71-4897-b757-2b355ffabbef · outbound

This paper cites Measuring massive multitask language understanding.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Measuring massive multitask language understanding

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.914354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 600bdd67-00bd-445c-8465-8d0366ce6c02 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Measuring mathematical problem solving with the MATH dataset

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.906979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd226e5d-e9d6-4aec-9d45-36a5b290fe05 · outbound

This paper cites Training Compute-Optimal Large Language Models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Training Compute-Optimal Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.215478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316f645f-0a47-4f65-80f9-6fdbbba51394 · outbound

This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.219276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e736d96-9b1f-406d-b8ca-ef0cc1f07da7 · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.223058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8ee7ec0-676a-472c-852a-bd82e31f2d90 · outbound

This paper cites C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.899199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e78238f1-43f9-48f5-929f-c3c107944b12 · outbound

This paper cites Richter, Quentin Gregory Anthony, Eugene Belilovsky, Timoth \' e e Lesort, and Irina Rish.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Richter, Quentin Gregory Anthony, Eugene Belilovsky, Timoth \' e e Lesort, and Irina Rish

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.891363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26fc44d2-0d2a-4f90-96d8-e09ce6d05f58 · outbound

This paper cites Vetrov, and Andrew Gordon Wilson.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Vetrov, and Andrew Gordon Wilson

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.883249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 97bc146a-f747-4825-ad5a-187d111e6a86 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.235282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c8a01b1-70b3-4eab-9769-b3b40af967c0 · outbound

This paper cites Rethinking learning rate tuning in the era of large language models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Rethinking learning rate tuning in the era of large language models

Reference 26

Resolution: verified exact; raw_fallback, observed 2026-08-06T14:49:40.718320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fe181627-fec2-42d5-a385-46f2f81ed036 · outbound

This paper cites Weld, and Luke Zettlemoyer.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Weld, and Luke Zettlemoyer

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.241618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c208857-404e-4fda-86fe-b1e9232e2a17 · outbound

This paper cites Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.244546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f4d678-8373-4e81-9269-194552a071d2 · outbound

This paper cites Scaling Laws for Neural Language Models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Scaling Laws for Neural Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.247566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0986341d-8cb4-4960-a89a-78a9fe9f17a7 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Adam: A Method for Stochastic Optimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.250757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b156b9-734c-46c3-bc7d-79d25f64b4f4 · outbound

This paper cites Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming - Wei Chang, Andrew M.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming - Wei Chang, Andrew M

Reference 31

Resolution: malformed identifier; no resolver link, observed 2026-08-06T14:49:40.255037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d43276-78d1-4e4d-80d5-111c6b495cec · outbound

This paper cites an unresolved cited work.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.258558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92810c51-2ae3-4353-a885-12bdda675a2d · outbound

This paper cites CMMLU: measuring massive multitask language understanding in chinese.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training CMMLU: measuring massive multitask language understanding in chinese

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.261471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80457c3f-2016-4f98-a019-eb28e5a8d60f · outbound

This paper cites Gsm-plus: A comprehensive benchmark for evaluating the robustness of llms as mathematical problem solvers.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Gsm-plus: A comprehensive benchmark for evaluating the robustness of llms as mathematical problem solvers

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.264278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff6b0366-0353-4801-b059-198f28d01ab6 · outbound

This paper cites Trainable weight averaging: Efficient training by optimizing historical solutions.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Trainable weight averaging: Efficient training by optimizing historical solutions

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.871354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b01d7e69-effd-4359-869c-aaa6507bee03 · outbound

This paper cites Model Merging in Pre-training of Large Language Models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Model Merging in Pre-training of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.270904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7393a6f6-d761-4dd3-a0c7-e5030d5fad5a · outbound

This paper cites Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.275301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04763bb9-e42d-4b7d-98ae-5d4af2c4573e · outbound

This paper cites Checkpoint Merging via Bayesian Optimization in LLM Pretraining.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Checkpoint Merging via Bayesian Optimization in LLM Pretraining

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.278771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd15129-6fde-4231-b630-e247e463f365 · outbound

This paper cites Mathbench: Evaluating the theory and application proficiency of llms with a hierarchical mathematics benchmark.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Mathbench: Evaluating the theory and application proficiency of llms with a hierarchical mathematics benchmark

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.282544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aaa4fbe-0b1f-4f4d-bdd9-5eb9434c5cd2 · outbound

This paper cites Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.859947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 00bf9dac-1894-4206-ae92-115eddcfa730 · outbound

This paper cites Muon is Scalable for LLM Training.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Muon is Scalable for LLM Training

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.287585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a61f1f-3ff0-4842-8d7e-6258c9900bd3 · outbound

This paper cites Decoupled weight decay regularization.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Decoupled weight decay regularization

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.852087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ad685db0-d7e0-46b9-8969-896301d0f5ea · outbound

This paper cites Kor-bench: Benchmarking language models on knowledge-orthogonal reasoning tasks.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Kor-bench: Benchmarking language models on knowledge-orthogonal reasoning tasks

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.844328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 80ef4eb8-0795-49b4-9394-ebe5812f7620 · outbound

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

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Can a suit of armor conduct electricity? A new dataset for open book question answering

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.296436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8ca48f-a9e5-4982-bb70-25a8150f586e · outbound

This paper cites Humaneval-xl: A multilingual code generation benchmark for cross-lingual natural language generalization.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Humaneval-xl: A multilingual code generation benchmark for cross-lingual natural language generalization

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.836404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d441faa6-5beb-4307-b58b-e070c24e151c · outbound

This paper cites Acceleration of stochastic approximation by averaging.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Acceleration of stochastic approximation by averaging

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.302393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b2617c9-22da-4f45-a52e-e38e97ebe2cf · outbound

This paper cites Know what you don't know: Unanswerable questions for squad.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Know what you don't know: Unanswerable questions for squad

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.305913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f45b4229-3401-43fd-821a-02d59d43cf5c · outbound

This paper cites WARP: On the Benefits of Weight Averaged Rewarded Policies.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training WARP: On the Benefits of Weight Averaged Rewarded Policies

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.309508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88fe0e4-73e4-4e04-aed1-ba08bb7f98bd · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.313269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4937d0-9314-4a55-84ac-e2315a2e4758 · outbound

This paper cites The effective rank: A measure of effective dimensionality.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training The effective rank: A measure of effective dimensionality

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.823812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 55aeede7-6672-4f15-a676-ca48906940a7 · outbound

This paper cites Winogrande: an adversarial winograd schema challenge at scale.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Winogrande: an adversarial winograd schema challenge at scale

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.319980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f1d570c-bd0e-43dd-801f-db8643107920 · outbound

This paper cites Training trajectories, mini-batch losses and the curious role of the learning rate.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Training trajectories, mini-batch losses and the curious role of the learning rate

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.322544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73da079d-8e71-47cf-b9bd-b020e6655d68 · outbound

This paper cites Early Weight Averaging meets High Learning Rates for LLM Pre-training.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Early Weight Averaging meets High Learning Rates for LLM Pre-training

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.325724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6ee47d-7fbd-47c8-86ba-445a33954511 · outbound

This paper cites Language models are multilingual chain-of-thought reasoners.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Language models are multilingual chain-of-thought reasoners

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.816226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1cce468c-e7dd-4ef1-9218-fe5adff6e048 · outbound

This paper cites Through the river: Understanding the benefit of schedule-free methods for language model training.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Through the river: Understanding the benefit of schedule-free methods for language model training

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.808956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4204b1e0-83ec-411d-9f30-1c2abe880c2b · outbound

This paper cites an unresolved cited work.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.335742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea764802-3135-4306-af8b-8d21c68ddba5 · outbound

This paper cites Le, Ed H.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Le, Ed H

Reference 57

Resolution: malformed identifier; no resolver link, observed 2026-08-06T14:49:40.338371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f812d33d-5413-472e-b7fc-955f835f8f3b · outbound

This paper cites Mathscale: Scaling instruction tuning for mathematical reasoning.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Mathscale: Scaling instruction tuning for mathematical reasoning

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.801334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f4ea028c-ef97-4992-9152-210cc5ee25d2 · outbound

This paper cites Enhancing program synthesis with large language models using many-objective grammar-guided genetic programming.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Enhancing program synthesis with large language models using many-objective grammar-guided genetic programming

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.344028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0027e135-283e-4e1f-9a36-87ef21193dba · outbound

This paper cites SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.346687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d294a735-8dde-4bab-99cb-21384f5ecf60 · outbound

This paper cites Visualizing data using t-SNE.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Visualizing data using t-SNE

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.793666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f28e7aef-5bda-4e5e-9835-af7e705c1959 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.786032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e3538294-b9c8-4b01-8041-8c5902f68996 · outbound

This paper cites CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.355079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 448880cd-8952-4b5d-af44-e21859de42a6 · outbound

This paper cites Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.357950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4900d096-1dbc-4dbe-a105-665d9c9757d0 · outbound

This paper cites Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.778343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99940e47-70b3-4835-96e4-0630566f407a · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In Anna Korhonen, David R.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Hellaswag: Can a machine really finish your sentence? In Anna Korhonen, David R

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.363376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae4fb1b-a952-4491-b770-84f014fa9064 · outbound

This paper cites Foster, and Sham M.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Foster, and Sham M

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.771043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3075dbd0-d7ad-43e0-bed6-b43256ac86dd · outbound

This paper cites Why gradient clipping accelerates training: A theoretical justification for adaptivity.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Why gradient clipping accelerates training: A theoretical justification for adaptivity

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:49:40.763979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9435e165-90f4-4332-b5e9-359316fbaa19 · outbound

This paper cites Evaluating the Performance of Large Language Models on GAOKAO Benchmark.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Evaluating the Performance of Large Language Models on GAOKAO Benchmark

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.371463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f730784f-86c2-46b1-9910-f09757b42636 · outbound

This paper cites Agieval: A human-centric benchmark for evaluating foundation models.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training Agieval: A human-centric benchmark for evaluating foundation models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T14:49:40.374840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e5a9069d-4f1c-40a3-96cc-fe6071bece89 · inbound

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities cites this paper.

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 222

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:16:04.630970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 28d0e392-e39a-4e9d-97eb-ce31a2ebb1e0 · inbound

LLaDA2.0: Scaling Up Diffusion Language Models to 100B cites this paper.

LLaDA2.0: Scaling Up Diffusion Language Models to 100B WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:53:21.153791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9a673bd1-0782-431b-b822-ae5f7cfa19aa · inbound

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration cites this paper.

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:16:04.606637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation da5f2e47-57cc-4cf2-96e2-cf75387d6980 · inbound

Nucleus-Image: Sparse MoE for Image Generation cites this paper.

Nucleus-Image: Sparse MoE for Image Generation WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T10:26:00.500863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 03f0c8e7-2dbf-42b5-9192-ee498d954630 · inbound

Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training cites this paper.

Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:56.726091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation faf207a2-565d-44f8-93f8-594a43b59c56 · inbound

Optimizing Visual Generative Models via Distribution-wise Rewards cites this paper.

Optimizing Visual Generative Models via Distribution-wise Rewards WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T16:48:39.720432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 946f17a8-297a-41de-843e-b5edf6e0d030 · inbound

WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training cites this paper.

WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-14T08:04:06.432613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.