Paper Citation Record · LEDGER

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

As of 23 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 58 inbound Pith citation observations for arXiv:2502.06703.

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

pith.paper-citation-record.v1
2502.06703 v1

Coverage vector

measured 77 of 77 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T14:40:36.160535Z

measured 135 of 135 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 58 of 58 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:02:43.391391Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T21:00:08.398075Z

Reference resolution

77 of 77 outbound references displayed

verified exact0
verified fuzzy30
unresolved47
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b234873-5a17-4cbc-9950-59c4831a6423 · outbound

This paper cites Aime 2024, 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Aime 2024, 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.140448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 06ce97ab-dcdd-4aa0-9a79-f9045c9869d8 · outbound

This paper cites Introducing Claude , 2023.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Introducing Claude , 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.130065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ddd5ca04-ed60-4b7d-af4b-aef9152c1f26 · outbound

This paper cites Jiang, Jia Deng, Stella Biderman, and Sean Welleck.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Jiang, Jia Deng, Stella Biderman, and Sean Welleck

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.119494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 712a3c0b-25bf-45d1-b9cb-a3beea0be966 · outbound

This paper cites Scaling test-time compute with open models, 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Scaling test-time compute with open models, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.909681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d79cbd-262d-4ba7-9547-f5012acd2b88 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.912801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e25032-ec12-4d41-9dde-cba02e654965 · outbound

This paper cites Alphamath almost zero: Process supervision without process.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Alphamath almost zero: Process supervision without process

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.101228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 30793fe3-4fea-493f-b778-cf1d4dc31f23 · outbound

This paper cites an unresolved cited work.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-08T14:40:37.089675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b3be7772-8dda-4476-b35e-0a398b107fd9 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Process Reinforcement through Implicit Rewards

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.922961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45a1a20f-3ff6-4919-a5d1-d5ea3cf29412 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.926575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3b29857-2dab-48a0-bc8f-de5c5cfb570e · outbound

This paper cites The Llama 3 Herd of Models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.930952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 566da9e1-339e-4e73-b2ab-52de7e17902c · outbound

This paper cites PAL : Program-aided language models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling PAL : Program-aided language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.078105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d82bdf7d-f831-4cb8-b1ac-5e61b2fba3d5 · outbound

This paper cites To RA : A tool-integrated reasoning agent for mathematical problem solving.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling To RA : A tool-integrated reasoning agent for mathematical problem solving

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.066886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7e1abdd1-50fb-48bf-8a14-e2f02454c213 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.941372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5840cf9b-0d50-4fa1-9a3b-262f2902e37d · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Reinforced Self-Training (ReST) for Language Modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.944896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab3ca706-af8b-4e5c-9fd9-cf4d4b816374 · outbound

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

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Measuring mathematical problem solving with the MATH dataset

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.055719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0bc30d98-3359-4a0b-a26f-831a39a02904 · outbound

This paper cites V-STaR: Training Verifiers for Self-Taught Reasoners.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling V-STaR: Training Verifiers for Self-Taught Reasoners

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.951932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 624dac24-83cc-4a27-be2e-2c9f3a305274 · outbound

This paper cites O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.955396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce7b896e-a227-4b1f-922d-b56f2204c105 · outbound

This paper cites GPT-4o System Card.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling GPT-4o System Card

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.959414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57320b16-f3c1-4e58-b6cc-4950d0f23936 · outbound

This paper cites Mistral 7B.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Mistral 7B

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.963873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1acd9cc6-35c3-4e0a-af46-d6b722437adf · outbound

This paper cites MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.967949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4a654a2-13ab-401c-8f11-08bb223f5ebf · outbound

This paper cites ARGS : Alignment as reward-guided search.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling ARGS : Alignment as reward-guided search

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.044614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0741e2ef-f8c8-4360-9f98-9db2a4ba181f · outbound

This paper cites k0-math, November 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling k0-math, November 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.033274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 064fd4a5-66a7-4b43-b591-a837bb24d4f9 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.978584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af72ee27-cc45-4415-a83f-ff4808dc3417 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Training Language Models to Self-Correct via Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.982068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c47f1cf-0b92-47ba-8bef-8f498b9b7289 · outbound

This paper cites CoMAT : Chain of mathematically annotated thought improves mathematical reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling CoMAT : Chain of mathematically annotated thought improves mathematical reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.985577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3df4bf-21af-4c82-87ea-c8af838614f8 · outbound

This paper cites Process Reward Model with Q-Value Rankings.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Process Reward Model with Q-Value Rankings

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.988761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ce9f88a-7f18-41eb-84d3-b7974d12d9fe · outbound

This paper cites Let's verify step by step.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Let's verify step by step

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.991827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a81314a-c661-4bb7-b89d-1de1b1eb2365 · outbound

This paper cites Autopsv: Automated process-supervised verifier.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Autopsv: Automated process-supervised verifier

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.014738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b70475cd-8263-46b3-bae9-cc6442650a4e · outbound

This paper cites WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:35.997449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad645c84-0867-4c71-a2c1-fb03097333fe · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.000646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a638610-5dad-438b-982e-cef6dbf8a1db · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Self-refine: Iterative refinement with self-feedback

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:37.002315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 28dbae4a-9763-4ab2-b62d-6bb555d23956 · outbound

This paper cites Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.007327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c24f4a-71ea-486c-8656-7176fd0f95f9 · outbound

This paper cites GPT-4 Technical Report.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling GPT-4 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.010978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c56bb5-23de-4d70-8814-04cc66d0faa1 · outbound

This paper cites Learning to reason with llms, 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Learning to reason with llms, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.014673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25dd2f91-ba65-4050-8ee3-fe1df5e68c3c · outbound

This paper cites O1 Replication Journey: A Strategic Progress Report -- Part 1.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling O1 Replication Journey: A Strategic Progress Report -- Part 1

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.017882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c303f902-d6a2-4476-b52b-c8661b8c323e · outbound

This paper cites Recursive introspection: Teaching language model agents how to self-improve.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Recursive introspection: Teaching language model agents how to self-improve

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.984757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 742df8c8-f473-4602-b00a-13436d3260fb · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.972908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2a82e362-277a-4120-910f-1cc2d62ec641 · outbound

This paper cites RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.027707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a86e0f-6e88-4f8c-86c4-3fd1c3c5815a · outbound

This paper cites Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.031174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1916c2ad-1322-4db7-876a-fbef78dd2aee · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.034863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dce8e4f-0f9d-4d11-a579-5c0aabe028d2 · outbound

This paper cites Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.038438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23018d0f-dec7-41ab-a100-76ea8108a30e · outbound

This paper cites Skywork-o1, November 2024.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Skywork-o1, November 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.960840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9dde4a2d-d7d3-45af-8c16-eb539b2c6a83 · outbound

This paper cites Skywork-o1 open series.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Skywork-o1 open series

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.949886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4c3df50b-c127-466c-96e4-8db1aa666aa1 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.048931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37177012-0210-4d98-88e6-f2e2220604b7 · outbound

This paper cites PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.052680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b87581-3c4a-4909-b64a-c04607f3f0c2 · outbound

This paper cites Reinforcement learning: An introduction.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Reinforcement learning: An introduction

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.056441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f11997-da93-40d2-90d1-71f742bd1619 · outbound

This paper cites M ath S cale: Scaling instruction tuning for mathematical reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling M ath S cale: Scaling instruction tuning for mathematical reasoning

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.932605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3d29d45-a60e-4d05-87e1-a8126d48b419 · outbound

This paper cites DART -math: Difficulty-aware rejection tuning for mathematical problem-solving.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling DART -math: Difficulty-aware rejection tuning for mathematical problem-solving

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.921249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0789a4ea-4b89-427d-9fbe-7739eac0e165 · outbound

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

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.066620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b26a9589-09f1-4d73-a331-db9acceeb84c · outbound

This paper cites Reft: Reasoning with reinforced fine-tuning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Reft: Reasoning with reinforced fine-tuning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.909963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation daa40684-8410-4522-937b-42520a90b9e0 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Solving math word problems with process- and outcome-based feedback

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.074931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ff50eb6-6c28-4bf0-9a17-79734fe149c4 · outbound

This paper cites A lpha Z ero-like tree-search can guide large language model decoding and training.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling A lpha Z ero-like tree-search can guide large language model decoding and training

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.898379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2fea5eae-ac56-4f25-a10a-7eb4351bbeac · outbound

This paper cites OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.081619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774282b2-a9c4-4325-8fa5-87dd9a34556d · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.885802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d5603a6b-9393-46dd-8c6e-5c5d0a5c7a09 · outbound

This paper cites Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.089127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9624cf7a-6058-47e1-9e9c-3df7d3a45a81 · outbound

This paper cites Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.873687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 055280d8-4604-453b-b2a2-8e3e5f71105f · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Chain-of-thought prompting elicits reasoning in large language models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.862420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 118fdae9-c98e-4e55-9036-0c2d304eb8ae · outbound

This paper cites Large language models are better reasoners with self-verification.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Large language models are better reasoners with self-verification

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.851289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8e022e89-257e-4389-9a15-22aac81bde78 · outbound

This paper cites Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.103088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fe2ff11-667c-4b94-8c94-fa569d2a000e · outbound

This paper cites Self-evaluation guided beam search for reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Self-evaluation guided beam search for reasoning

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.839516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e42eec14-34b8-4c59-9232-6f56194215e5 · outbound

This paper cites An implementation of generative prm.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling An implementation of generative prm

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.109732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7804413-2afd-4129-858b-7d5094ef3eeb · outbound

This paper cites Qwen2 Technical Report.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Qwen2 Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.112622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eca76b55-733a-4676-ad93-7da8f5b93698 · outbound

This paper cites Qwen2.5 Technical Report.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Qwen2.5 Technical Report

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.115695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee1a504-814b-4a98-a9c1-003f89a534a6 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.118755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af62b3a-bb44-4bfb-bd5e-d53ed81bd928 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Tree of thoughts: Deliberate problem solving with large language models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.821051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8cf6ffe1-ee6e-4e76-a1ae-24dbc07fd35f · outbound

This paper cites MetaMath : Bootstrap your own mathematical questions for large language models.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling MetaMath : Bootstrap your own mathematical questions for large language models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.809196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b22cc61a-0819-4ca9-b55b-4430dfc7bc60 · outbound

This paper cites Free Process Rewards without Process Labels.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Free Process Rewards without Process Labels

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.127934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09937fb9-fcca-4823-b78e-9e8096432330 · outbound

This paper cites STaR : Bootstrapping reasoning with reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling STaR : Bootstrapping reasoning with reasoning

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.797361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0976b0af-aa03-4cb9-92b9-b9d325a6ba1f · outbound

This paper cites Quiet- ST ar: Language models can teach themselves to think before speaking.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Quiet- ST ar: Language models can teach themselves to think before speaking

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.785727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 36d41b5b-d316-4c83-b945-3fead7233752 · outbound

This paper cites Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.136935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dfb2880-ecef-4fdd-a85e-775e78307e49 · outbound

This paper cites 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.140097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b525bb1b-7f58-491e-b1e7-c250e11dfd5b · outbound

This paper cites Re ST - MCTS *: LLM self-training via process reward guided tree search.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Re ST - MCTS *: LLM self-training via process reward guided tree search

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.767667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation df41818f-15c1-457f-8453-228ca05e8ec2 · outbound

This paper cites Entropy-regularized process reward model.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Entropy-regularized process reward model

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.146362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8985249a-65d0-45ed-9783-3e917694a695 · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.149694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b308f711-f1d7-44e4-b73a-f08d37d36706 · outbound

This paper cites Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.153233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8732e1ea-9b23-4cf6-a522-b7934a693e48 · outbound

This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling ProcessBench: Identifying Process Errors in Mathematical Reasoning

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.156886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bd7b484-084e-43ef-b060-f8173872cc84 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:40:36.755459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 12e23caf-5740-48e4-a599-552c1dc2ba0d · inbound

Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise cites this paper.

Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T14:03:18.881721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe093e0f-d652-441b-b5fa-38c9472106c5 · inbound

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles cites this paper.

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:59:03.190673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation de9a547a-9609-43e4-a615-cc6cdb1b7bca · inbound

Generative AI Act II: Test Time Scaling Drives Cognition Engineering cites this paper.

Generative AI Act II: Test Time Scaling Drives Cognition Engineering Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 198

Resolution: unresolved; no resolver link, observed 2026-08-16T12:02:43.391391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75491ede-3eb2-43fb-a5ac-1803552c43bc · inbound

Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals cites this paper.

Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T12:01:24.978443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d34214-fdf5-4c87-a187-334209e2a6f2 · inbound

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment cites this paper.

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:24:11.989033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6566f18c-c441-4f8c-95c5-1b5bb6c878d8 · inbound

Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation cites this paper.

Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T04:32:20.445343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e6488e-6282-4356-b486-808a8578c478 · inbound

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law cites this paper.

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T00:48:17.937441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ca01e10-82d6-4c5b-bc2c-171388286475 · inbound

SLOT: Sample-specific Language Model Optimization at Test-time cites this paper.

SLOT: Sample-specific Language Model Optimization at Test-time Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:16.941819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4935d78-a4ba-474c-b0b3-7ad6ed3f10c7 · inbound

Multilingual Test-Time Scaling via Initial Thought Transfer cites this paper.

Multilingual Test-Time Scaling via Initial Thought Transfer Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:20:21.815453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec42c1f-e556-47dc-b89a-fa22ea3aa623 · inbound

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning cites this paper.

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:45:17.775098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 061d8941-df23-4968-95e9-82c3a7d639e5 · inbound

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models cites this paper.

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:13.154734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 770b0951-6d1e-4e04-80c8-1b81e777a340 · inbound

Faster and Better LLMs via Latency-Aware Test-Time Scaling cites this paper.

Faster and Better LLMs via Latency-Aware Test-Time Scaling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:22.357992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9834023-d4e3-4163-b2fb-b9b35d000c63 · inbound

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision cites this paper.

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:19.428465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c218e16-140b-455b-92f5-e2e6dc5776f2 · inbound

Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence cites this paper.

Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:38:06.969200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08a3bb2-51a6-464e-bd4b-23b5a2357fc3 · inbound

Can Past Experience Accelerate LLM Reasoning? cites this paper.

Can Past Experience Accelerate LLM Reasoning? Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:53:57.290694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b51122-ee9a-4f4c-a762-8a2f07fc51e9 · inbound

PixelThink: Towards Efficient Chain-of-Pixel Reasoning cites this paper.

PixelThink: Towards Efficient Chain-of-Pixel Reasoning Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T12:45:46.144862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df98069d-c01a-4be8-a355-bf5788b300b8 · inbound

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation cites this paper.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.678833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70bd4eff-189c-4e66-ba8b-fcf6c0b35422 · inbound

CyberV: Cybernetics for Test-time Scaling in Video Understanding cites this paper.

CyberV: Cybernetics for Test-time Scaling in Video Understanding Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:26:47.172225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b527d30a-272e-4fb3-9d5c-64ecec4f111a · inbound

Scaling Test-time Compute for LLM Agents cites this paper.

Scaling Test-time Compute for LLM Agents Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.364617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1dffc48-5b3e-485f-844b-22ccc0ae2bac · inbound

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling cites this paper.

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:48:23.585240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bb8fc79-a48f-435b-ba00-1ec1647935fc · inbound

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations cites this paper.

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T22:59:14.428010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c08bd8-c10a-4603-a5cf-ceaf7891c0a7 · inbound

Reasoning in machine vision by learning fast and slow thinking cites this paper.

Reasoning in machine vision by learning fast and slow thinking Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T22:16:18.935562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47967841-d013-48fe-a5c4-a9853eeb27be · inbound

Test-Time Scaling with Reflective Generative Model cites this paper.

Test-Time Scaling with Reflective Generative Model Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T20:46:44.778485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d5599b-be23-49fd-9f3b-148432ac69ae · inbound

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs cites this paper.

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T20:43:11.344018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53431e79-949f-4e23-b2ac-162677dd400c · inbound

Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need cites this paper.

Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-06T16:17:44.141518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd9282a-53af-4db8-a978-38b29d59fe79 · inbound

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR cites this paper.

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T23:24:26.286832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f4e7dcf-2c7d-4e7e-aa2a-2a3989bf4133 · inbound

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations cites this paper.

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:59.459727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1a11d3-de30-4c11-9006-604f787b15e8 · inbound

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction cites this paper.

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T00:49:56.372971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0972242c-07d0-4677-81ae-206435b91c3f · inbound

SSRL: Self-Search Reinforcement Learning cites this paper.

SSRL: Self-Search Reinforcement Learning Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T20:17:10.690804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bff4313-4b00-48ed-aa9e-c23e1d52487a · inbound

ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism cites this paper.

ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T20:04:02.266502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6267bea-60f9-4002-9d17-e79cf6229fd4 · inbound

Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models cites this paper.

Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-18T22:41:52.929951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3eaa87b-24a6-41d4-be51-6f9b9d280004 · inbound

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness cites this paper.

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T17:31:41.548743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2a58f66e-2eb4-4c11-a9b8-328ef81b1a4e · inbound

Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction cites this paper.

Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T12:43:41.263738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a18a124-832f-43ac-b30b-6e04511b983b · inbound

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL cites this paper.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:30:35.518062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 92240cde-4213-4933-91e7-3328797739ac · inbound

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling cites this paper.

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:57:43.015774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bbda081e-6dd4-4094-a0ad-2de16fb6ff00 · inbound

Decoding the Critique Mechanism in Large Reasoning Models cites this paper.

Decoding the Critique Mechanism in Large Reasoning Models Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:50:28.456759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 54d004f6-27d7-4e08-9bce-fb0331d17a3d · inbound

DeepStack: Scalable and Accurate Design Space Exploration for Distributed 3D-Stacked AI Accelerators cites this paper.

DeepStack: Scalable and Accurate Design Space Exploration for Distributed 3D-Stacked AI Accelerators Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:30:52.070140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 126d36a2-d261-418c-8477-6cc26e49bbea · inbound

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization cites this paper.

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:00:22.130974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e27a3869-9ed8-4ef0-9efb-add1b299e1c8 · inbound

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens cites this paper.

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T11:20:11.264650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7ad84d25-93e2-4f8e-b738-589f602625db · inbound

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis cites this paper.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:56:15.853807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3b38060d-072b-466c-b341-4eeb9f518978 · inbound

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis cites this paper.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.492180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a195219e-a949-4335-852b-361d6126e051 · inbound

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding cites this paper.

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:31:09.074348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 11ce872f-0adc-4370-8d30-fe73dc63e331 · inbound

Stream-T1: Test-Time Scaling for Streaming Video Generation cites this paper.

Stream-T1: Test-Time Scaling for Streaming Video Generation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:40:39.485808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf6069d9-8c6b-41c2-b8be-3d5599c9b936 · inbound

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation cites this paper.

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:25:58.231082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation caf4bf73-971a-4969-b53a-d38ec486c73f · inbound

Unsupervised Process Reward Models cites this paper.

Unsupervised Process Reward Models Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:21:18.916734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bee8b60e-40cd-4275-a5e4-987132bfa689 · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:51:30.089678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 03950951-7438-428e-bfa6-432eab0f39d4 · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:15:03.365580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3be9bfea-ecf3-44d4-bf02-409477c54888 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 115

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T20:56:13.733864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6388b362-79f2-43ae-9054-63e432943e5d · inbound

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff cites this paper.

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 117

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:27:26.378161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7170760e-940f-4c37-902f-f3141149314a · inbound

Data Selection Through Iterative Self-Filtering for Vision-Language Settings cites this paper.

Data Selection Through Iterative Self-Filtering for Vision-Language Settings Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T09:49:44.883889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ec2d4e04-69fa-49d4-ab3d-60fa6008b35b · inbound

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity cites this paper.

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T21:00:08.400710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ff9bd608-6a8d-4d92-9f84-fce98c499edf · inbound

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling cites this paper.

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T09:44:37.092805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fb27912b-109e-4283-9f1d-4c4727f952d5 · inbound

Test-Time Scaling for Small VLMs on Multilingual Visual MCQ cites this paper.

Test-Time Scaling for Small VLMs on Multilingual Visual MCQ Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T03:00:51.318412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479f5bd3-9708-4dd4-bb78-add836d6214f · inbound

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning cites this paper.

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T14:00:54.863716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c322afa-c81b-4eb6-ae47-174fb3224b10 · inbound

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning cites this paper.

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T07:28:23.264118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71089cd9-0a78-4511-b41f-ac42a2359ce4 · inbound

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals cites this paper.

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T05:09:00.865375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0c3839-c60d-4d1e-808f-c23fbca65622 · inbound

Interpretable Adaptive Sampling for LLM Test-Time Scaling cites this paper.

Interpretable Adaptive Sampling for LLM Test-Time Scaling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T05:02:10.707287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d7ffdc-ce11-42f4-96f2-5e42db65a721 · inbound

Hidden Language Consistency Phenomena in Reasoning LLMs cites this paper.

Hidden Language Consistency Phenomena in Reasoning LLMs Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 278

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:10.392620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.