Paper Citation Record · LEDGER

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

As of 16 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 7 inbound Pith citation observations for arXiv:2505.07961.

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

pith.paper-citation-record.v1
2505.07961 v3

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:11:34.020610Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:16:03.077573Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T19:43:44.121220Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy10
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8d396b3e-ca1c-42b2-80c0-76af3d123a3b · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.877772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c87e41e7-106a-4d93-954e-18bc23e143de · outbound

This paper cites The Surprising Effectiveness of Test-Time Training for Few-Shot Learning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.883525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50380b6f-a70b-4f9a-94cc-0d5ef0ec6303 · outbound

This paper cites Precise Length Control in Large Language Models.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Precise Length Control in Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.887907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 734d0927-4c52-4467-a238-670416fd82ec · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.892890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b6c686-0811-4902-80a7-94087760d863 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.897078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a60b0daa-05dc-4f83-95f0-d20e549d7e22 · outbound

This paper cites Gemini 2.0 flash thinking mode (gemini-2.0f lash-thinking-exp-1219), 2024.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Gemini 2.0 flash thinking mode (gemini-2.0f lash-thinking-exp-1219), 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.641536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 58b1928c-096f-4a7d-aa3d-e4ce852ead83 · outbound

This paper cites Test-time training provably improves transformers as in-context learners.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Test-time training provably improves transformers as in-context learners

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.905805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df98ec15-9c2c-45de-8b48-d13c6d332cd3 · outbound

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

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.910188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae9df6fc-5089-4b4e-af9e-b27fbdbcda68 · outbound

This paper cites Language Model Cascades: Token-level uncertainty and beyond.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Language Model Cascades: Token-level uncertainty and beyond

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.914295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e46da3-438e-4daa-978b-9dfe39d5fd7a · outbound

This paper cites ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.918046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77aac5a-79c2-46f2-ac1c-d4b8ee6c0d13 · outbound

This paper cites OpenAI o1 System Card.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.921887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc70092-78b9-4b5b-afde-f8834b657351 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Fast inference from transformers via speculative decoding

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.629933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2e33c4ad-7933-458f-a900-2c504879f806 · outbound

This paper cites Autobalance: Optimized loss functions for imbalanced data.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Autobalance: Optimized loss functions for imbalanced data

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.618115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 20a9a835-c90b-4c5e-806a-38350e17314d · outbound

This paper cites Small models struggle to learn from strong reasoners.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Small models struggle to learn from strong reasoners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.931708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 622e7f77-58bb-4f78-bce7-d89a22e1bf4f · outbound

This paper cites Let’s verify step by step.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Let’s verify step by step

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.935195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1cd46e9-9114-4316-91df-8934f2b3eb7c · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.938798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5093dcf-123c-4933-8cfa-b9efb290d97e · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.594816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 289ba2ba-3319-49a3-bb7a-f9d0643dcc30 · outbound

This paper cites Long-tail learning via logit adjustment.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Long-tail learning via logit adjustment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.946059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283a70c5-b00c-4a19-bb2a-62ee448c36a9 · outbound

This paper cites s1: Simple test-time scaling.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement s1: Simple test-time scaling

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.949614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2e8ccc2-6e5a-41c1-ab96-fd265de3eab9 · outbound

This paper cites Gpt-4o mini: advancing cost-efficient intelligence, 2024.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Gpt-4o mini: advancing cost-efficient intelligence, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.577740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e972ac4f-18f0-4cdd-8a9d-7a15da8a7927 · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Gpqa: A graduate-level google-proof q&a benchmark

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.957798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e45beb1-1e63-4b61-af85-f924f23096fc · outbound

This paper cites Scaling Test-Time Compute Without Verification or RL is Suboptimal.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Scaling Test-Time Compute Without Verification or RL is Suboptimal

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.962269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b883b6d-825e-40e2-8a28-c751a8bc144a · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.967068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf1e8d8b-aeff-4d37-80c8-d49962fd5640 · outbound

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

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.971434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 515e1ab3-531f-4550-b5f1-783b83f88ef4 · outbound

This paper cites Scalable Chain of Thoughts via Elastic Reasoning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Scalable Chain of Thoughts via Elastic Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.975998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0a603d5-c187-43de-afcc-3bcf18c85c01 · outbound

This paper cites Qwen2.5 Technical Report.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Qwen2.5 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.979744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 974af263-8d69-4ade-92f7-82521c49154f · outbound

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

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.983505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c09474c1-4f25-499c-831b-50a3951f0c2a · outbound

This paper cites Towards thinking-optimal scaling of test-time compute for llm reasoning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Towards thinking-optimal scaling of test-time compute for llm reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.987395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a7ccb58-5918-45cb-b07c-a8493b5f62cb · outbound

This paper cites Following Length Constraints in Instructions.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Following Length Constraints in Instructions

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T22:11:33.991234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 723c00b6-029d-4125-817b-5881c65d56c4 · outbound

This paper cites Selective attention: Enhancing transformer through principled context control.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Selective attention: Enhancing transformer through principled context control

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.560114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 341dd39d-09de-457a-9e35-50c36a47f104 · outbound

This paper cites Efficient contextual LLM cascades through budget-constrained policy learning.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Efficient contextual LLM cascades through budget-constrained policy learning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.547918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 95e6457c-71a2-4a0b-ab20-f7906668edc1 · outbound

This paper cites Class-attribute priors: adapting optimization to heterogeneity and fairness objective.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Class-attribute priors: adapting optimization to heterogeneity and fairness objective

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.535486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e4933300-2e03-433c-a78c-bcb55c7094e3 · outbound

This paper cites Pleaseanalyze the following text and determine if there are any meaningless repetitions of identical sentences.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Pleaseanalyze the following text and determine if there are any meaningless repetitions of identical sentences

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.524261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cf0b46b3-7ea4-4360-939d-7f887e96ca61 · outbound

This paper cites If the model prematurely generates the end-of-thinking token before reaching the desired length, the token is removed, and generation continues until the target length is reached.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement If the model prematurely generates the end-of-thinking token before reaching the desired length, the token is removed, and generation continues until the target length is reached

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:11:34.512528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9d808209-4fd3-4a47-bac1-8d66ce1414bc · outbound

This paper cites an unresolved cited work.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:11:34.499056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7f619b3d-b0d2-4d11-b6b4-f3d34b2dbe8a · outbound

This paper cites 2k” and “4k.

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement 2k” and “4k

Reference 36

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T22:11:34.111991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation a90e90b1-f664-4c52-a947-aabcf031f41f · inbound

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models cites this paper.

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 240

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:29:57.422076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6820098a-2d10-4b21-ae17-00996f34dbae · inbound

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning cites this paper.

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T19:16:03.077573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caafa4cf-1572-4ec2-90a7-2cb382e35772 · inbound

Bayesian Social Deduction with Graph-Informed Language Models cites this paper.

Bayesian Social Deduction with Graph-Informed Language Models Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-19T07:32:09.410714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8c401132-526a-4f28-975e-e06499a9d6a7 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 233

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.979128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6788d978-46b9-445a-9287-e00caccf6347 · inbound

VSPO: Vector-Steered Policy Optimization for Behavioral Control cites this paper.

VSPO: Vector-Steered Policy Optimization for Behavioral Control Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:43:44.123476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8f3b2d51-b066-417b-b03b-9934dd5d82f7 · inbound

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping cites this paper.

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T07:09:11.486851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2788d7-a87f-4422-ad06-7d008e98f891 · inbound

From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation cites this paper.

From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:56:34.604372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.