Paper Citation Record · LEDGER

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

As of 18 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 7 inbound Pith citation observations for arXiv:2504.18116.

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

pith.paper-citation-record.v1
2504.18116 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:29:18.775808Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

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

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:12:44.575215Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-19T14:12:24.048558Z

Reference resolution

32 of 32 outbound references displayed

verified exact2
verified fuzzy2
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation df37955b-165b-43b5-b25f-4ef4cbf9e0e5 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Training Verifiers to Solve Math Word Problems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.678331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6501e6a1-0502-48f4-8399-773f84d5a93e · outbound

This paper cites Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.681178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29975e9c-4f04-4867-8756-b3af45f025a8 · outbound

This paper cites The Llama 3 Herd of Models.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models The Llama 3 Herd of Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.684578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5182a38e-35ae-47c3-bf8f-3834c8c3bbfa · outbound

This paper cites Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.691380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de16bbfe-712e-4a3f-9caa-6a411173fee2 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Distilling the Knowledge in a Neural Network

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.694087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a45e69-b45a-45a8-98ac-eb70033b135c · outbound

This paper cites Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.697529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be58e89-cc4a-4a25-8134-1741564a8b89 · outbound

This paper cites Unfamiliar Finetuning Examples Control How Language Models Hallucinate.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Unfamiliar Finetuning Examples Control How Language Models Hallucinate

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.700736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e197f5-ddb5-4529-ba95-330b3e026e68 · outbound

This paper cites Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.703807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0896e7a-3417-4472-9fe2-eb6958b413c6 · outbound

This paper cites Modecollapse in generative adversarial networks: An overview.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Modecollapse in generative adversarial networks: An overview

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:19.193290Z

Source-reported events for the cited work

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

Observation a782e00d-e4d6-4a23-bb08-1c62c9eeeb19 · outbound

This paper cites Solving Quantitative Reasoning Problems with Language Models.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Solving Quantitative Reasoning Problems with Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.710012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b18922-4c2e-446e-bf76-50657867d9f4 · outbound

This paper cites Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.713202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f99597a-737d-4f4d-b6ee-8d3f50ba0663 · outbound

This paper cites Small Language Model Can Self-correct.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Small Language Model Can Self-correct

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-16T10:29:19.057681Z

Source-reported events for the cited work

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

Observation d9d91eea-71ff-4a7c-a84c-60dd60d3029f · outbound

This paper cites Decoupled Weight Decay Regularization.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Decoupled Weight Decay Regularization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.719488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d528b8f-051f-479a-8fd7-0d4dfa2e5ca7 · outbound

This paper cites s1: Simple test-time scaling.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models s1: Simple test-time scaling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.722453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081eaf4b-e20b-4895-95ad-5469d2390b93 · outbound

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

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Training language models to follow instructions with human feedback

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.725495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdbd755b-0bbd-48af-b871-e2a4c3417be6 · outbound

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

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.728358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8aacbcb-5940-45bb-aea5-318db137dd21 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Proximal Policy Optimization Algorithms

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.731564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be6fbbd6-16f3-422e-9655-d73eca963c94 · outbound

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

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.734408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ed649a-eebb-4480-b3a0-a349b4c50cfe · outbound

This paper cites Shumailov, Z.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Shumailov, Z

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.737211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe95064a-ddb3-4203-b404-ce569541ce96 · outbound

This paper cites Taori, I.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Taori, I

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:19.175854Z

Source-reported events for the cited work

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

Observation b9931bc2-bb6b-4988-ae01-aa3773a14e6b · outbound

This paper cites CodeGemma: Open Code Models Based on Gemma.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models CodeGemma: Open Code Models Based on Gemma

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.742586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f134f3-9b6a-407e-aefe-d12bd6e3f4aa · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.745214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d76e3437-6bc1-4576-abf4-cc03a26ab7df · outbound

This paper cites Manifestation of edge-bulk incompatibility in fractional quantum Hall platform.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Manifestation of edge-bulk incompatibility in fractional quantum Hall platform

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T10:29:18.948846Z

Source-reported events for the cited work

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

Observation a9f4ea08-cf17-4cd7-8bd4-ba8974e4a136 · outbound

This paper cites ELM-free Enhanced D{\alpha} H-mode with Near Zero NBI Torque Injection in DIII-D Tokamak.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models ELM-free Enhanced D{\alpha} H-mode with Near Zero NBI Torque Injection in DIII-D Tokamak

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.750834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef5b236-8576-4739-91e3-bf93308f28d7 · outbound

This paper cites Almost sure and moment convergence for triangular P\'olya urns.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Almost sure and moment convergence for triangular P\'olya urns

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.753595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9fe5e4-6787-4d08-8521-f84d1f19b17f · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.756661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb92f36-840e-457d-a07e-928dd7079e27 · outbound

This paper cites An experimental sorting method for improving metagenomic data encoding.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models An experimental sorting method for improving metagenomic data encoding

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-16T10:29:18.903624Z

Source-reported events for the cited work

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

Observation e8796403-773c-46c3-9b08-f21577d8ddc3 · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models STaR: Bootstrapping Reasoning With Reasoning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.763056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6785450e-fe14-4fee-bf61-8f66673491bc · outbound

This paper cites write newline.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models write newline

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.766197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5075d6e8-c6b8-4bbf-bffb-7583df3750d6 · outbound

This paper cites @esa (Ref.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models @esa (Ref

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.769485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab4f4dd-ce3f-42fd-a3b7-afaa34bda0dc · outbound

This paper cites an unresolved cited work.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.772749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5e19c7-cbd3-4c50-bec7-08e3991c8ebf · outbound

This paper cites an unresolved cited work.

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:18.775808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e5bcea23-fdf5-4b43-9c85-2862e200f7d2 · inbound

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review cites this paper.

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 232

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:57:38.184767Z

Source-reported events for the cited work

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

Observation 6e1e882d-b04a-44d1-9999-6a823bb9ab66 · inbound

Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models cites this paper.

Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-19T14:12:24.068042Z

Source-reported events for the cited work

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

Observation b71a2602-5e4e-42db-bc26-2cf26d7a6d0f · inbound

Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks cites this paper.

Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-19T09:52:14.119976Z

Source-reported events for the cited work

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

Observation ef8ed2bf-a7c3-4489-99eb-6f312d11a0c4 · inbound

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing cites this paper.

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:12:44.575215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 581a9e5e-96de-45d7-bb67-4afca74fe4b8 · inbound

A Survey of Context Engineering for Large Language Models cites this paper.

A Survey of Context Engineering for Large Language Models Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 191

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:58:45.155651Z

Source-reported events for the cited work

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

Observation 62bdf170-c2bf-4f6e-86a1-e1b11953eb15 · inbound

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning cites this paper.

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T15:12:01.777554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcdd1b14-b89a-4391-8bf8-d0ac79661f03 · inbound

Chained Recursive Language Models for Multi-Iteration Reasoning cites this paper.

Chained Recursive Language Models for Multi-Iteration Reasoning Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:21.021997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.