Paper Citation Record · LEDGER

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

As of 21 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 3 inbound Pith citation observations for arXiv:2412.08347.

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

pith.paper-citation-record.v1
2412.08347 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:57:44.387680Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:33:18.190708Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T19:32:01.424841Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c9b2c164-dcfe-49c6-ae1a-fea2ce4bf6b1 · outbound

This paper cites URL: " 'urlintro :=.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs URL: " 'urlintro :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.242057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 836ddc78-a911-4a51-b87f-b673f039a2b1 · outbound

This paper cites write newline.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.248598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33bd1f06-1f92-4a8d-a8de-27b6cae9f073 · outbound

This paper cites an unresolved cited work.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:57:44.810700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 44e973d8-59ae-40c7-b833-938102480d86 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Gonzalez, Ion Stoica, and Eric P

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.261511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 341f2dc6-fcea-430a-ac0c-28a2cecc16c1 · outbound

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

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.266759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0f80816-4827-4ebf-a2f5-bccd20e0a251 · outbound

This paper cites Textbooks Are All You Need.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Textbooks Are All You Need

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.273825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ff712e-19ab-40d3-9aa2-a453dc1921e4 · outbound

This paper cites Training Compute-Optimal Large Language Models.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Training Compute-Optimal Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.279182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f82948-5752-4378-8c12-de8e3a6dc13a · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.284589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 325054ca-5e20-4258-9949-37ed2400ea04 · outbound

This paper cites Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.291300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc1b79e-4e72-4d1c-92c0-3fdf32b21078 · outbound

This paper cites Scaling Laws for Neural Language Models.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Scaling Laws for Neural Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.296081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24be95d8-0663-42f6-9192-92e5cd642d3e · outbound

This paper cites VinePPO: Refining Credit Assignment in RL Training of LLMs.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs VinePPO: Refining Credit Assignment in RL Training of LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.301141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fd5a98-3f28-40ee-b188-788b71f778a9 · outbound

This paper cites On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.306462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64703b08-c1d0-448d-ba36-a9cd4455dda0 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.311969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a32a60c-a3d2-4ab1-97a0-93455f2937c6 · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs RewardBench: Evaluating Reward Models for Language Modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.318396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d4d8a6d-030d-421f-a6e3-ad71fbea6a6a · outbound

This paper cites Revisiting Small Batch Training for Deep Neural Networks.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Revisiting Small Batch Training for Deep Neural Networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.323731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a1085e-952f-4628-8557-69bce0564a96 · outbound

This paper cites An Empirical Model of Large-Batch Training.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs An Empirical Model of Large-Batch Training

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.328334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2957e9e3-6bda-4516-84a8-b92b2b7b4c62 · outbound

This paper cites an unresolved cited work.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.332959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6a804d4-0a37-428d-89d5-31c66acfd6d4 · outbound

This paper cites Training language models to follow instructions with human feedback.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Training language models to follow instructions with human feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.337530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77ac710-09ba-49a2-bf35-993535cc4845 · outbound

This paper cites Training Chain-of-Thought via Latent-Variable Inference.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Training Chain-of-Thought via Latent-Variable Inference

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.342506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 075a3958-1f4f-4617-9a99-95113e0ab3ee · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.347384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c372a5-0e59-4f40-bf15-e3664eb879a6 · outbound

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

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Measuring the Effects of Data Parallelism on Neural Network Training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.352311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5d3cec-1467-49bc-8729-6e5fde666501 · outbound

This paper cites Don't Decay the Learning Rate, Increase the Batch Size.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Don't Decay the Learning Rate, Increase the Batch Size

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.358133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa46db5d-5494-466c-af10-7c120c77cc1c · outbound

This paper cites Hashimoto.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Hashimoto

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.363204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3cd64c9-7443-4360-9431-c5c14d69f934 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.367810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30f9778e-25aa-456b-95cb-97ff6f95ddd8 · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Zephyr: Direct Distillation of LM Alignment

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.372586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0b8700c-5a31-4222-a3ff-9c5034dab00d · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs STaR: Bootstrapping Reasoning With Reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.377903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786feb1b-885c-49f0-87f7-f295eff974a5 · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs TinyLlama: An Open-Source Small Language Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.382636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1aeeee2-82f4-4f4d-a930-29231ddb085f · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T17:57:44.387680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0a7af1d5-dc7c-43e1-805f-3303e0fb090f · inbound

Reinforcement Learning from Human Feedback cites this paper.

Reinforcement Learning from Human Feedback SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-22T19:32:01.428010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 75fd06a3-fb14-4161-aa42-8b0d72c3b773 · inbound

Reinforcement Learning from Human Feedback cites this paper.

Reinforcement Learning from Human Feedback SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T12:33:18.190708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d377918b-737e-48d9-8599-931c22b54de2 · inbound

EasyMath: A 0-shot Math Benchmark for SLMs cites this paper.

EasyMath: A 0-shot Math Benchmark for SLMs SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:34.734735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.