Paper Citation Record · LEDGER

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs

As of 9 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 0 inbound Pith citation observations for arXiv:2507.11371.

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

pith.paper-citation-record.v1
2507.11371 v1

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:16:54.724511Z

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

11 of 11 outbound references displayed

verified exact0
verified fuzzy2
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cf99c4e5-03f3-4284-9d33-bb448d99d66f · outbound

This paper cites Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.103748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e776e815-70d3-4daf-b3d0-c24dbcbab051 · outbound

This paper cites https://blog.google/technology/google-deepmind/ gemini-model-thinking-updates-march-2025/.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs https://blog.google/technology/google-deepmind/ gemini-model-thinking-updates-march-2025/

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:16:55.296994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f24182c9-8ee5-44c8-966c-b95f9f94199b · outbound

This paper cites https://huggingface.co/ datasets/openai/gsm8k.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs https://huggingface.co/ datasets/openai/gsm8k

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:16:55.130338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 952aac95-37b0-4b0c-95d4-ebdef36b2c5d · outbound

This paper cites GPT-4 Technical Report.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs GPT-4 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.490994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6989800-c228-4a3f-b99c-6821732c4721 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.629011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7587c99-1d5d-47c4-9e83-219e3ae2d350 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs Proximal Policy Optimization Algorithms

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.545256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18dd0e8e-ab3a-4dba-bb3a-4293995890b6 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.724511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea1729d6-1ea2-4783-b31b-a345da004d31 · outbound

This paper cites Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Reference 2020

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T17:16:54.917862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 89ce7c00-fcbd-4ec7-b525-fa7822e75dd7 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.311385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29ebef4f-ecef-4e45-b5a4-aa5c07f5675b · outbound

This paper cites The Llama 3 Herd of Models.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.251389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710a76c4-7641-4292-b7a5-a0056b1c0155 · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T17:16:54.028227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.