Paper Citation Record · LEDGER

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

As of 19 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 2 inbound Pith citation observations for arXiv:2507.18973.

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

pith.paper-citation-record.v1
2507.18973 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:08:57.965208Z

measured 27 of 27 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:43:31.887361Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T20:50:36.689069Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy6
unresolved18
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8c853a83-6fa9-42dc-98b9-dff1a25da275 · outbound

This paper cites This solution trace is extracted from the GPT-4o MATH500 main results.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation This solution trace is extracted from the GPT-4o MATH500 main results

Reference 1

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T18:08:58.170484Z

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 f107c717-5086-41b3-949a-6f54f455a251 · outbound

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

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.876003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afb2aaf-404e-4261-9f2c-9b9885f14d3d · outbound

This paper cites Mistral 7B.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Mistral 7B

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.880501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a76e3716-3002-4148-9297-c766f0e6bdc5 · outbound

This paper cites com/blog/chatgpt.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation com/blog/chatgpt

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.234448Z

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 1e259782-87c3-4490-8e5b-55b8399e893b · outbound

This paper cites Ac- cessed: 2025-05-20.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Ac- cessed: 2025-05-20

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.222115Z

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 f34d1317-1354-48a0-9424-7e57e88c8a2e · outbound

This paper cites ART: Automatic multi-step reasoning and tool-use for large language models.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation ART: Automatic multi-step reasoning and tool-use for large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.894032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78783b95-248c-46a5-9c48-074cfa6253ba · outbound

This paper cites an unresolved cited work.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:08:58.207808Z

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 164e3357-181f-4f53-b678-3781123a5f2d · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.907498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2f1add-e06c-42fe-b807-764efe3e1614 · outbound

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

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.911718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c778130-0eb6-410f-9bbd-287802446e09 · outbound

This paper cites The Llama 3 Herd of Models.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.915801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 611cb0cb-ca8b-4b94-87fc-afb52114e604 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.921130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec36337-04c9-4847-901b-e153b186db01 · outbound

This paper cites OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.926060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cd0b35b-c2b9-4a0a-93b7-fbe01a8150f2 · outbound

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

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.929662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb97c5bd-d93b-4f96-8635-5562c2986457 · outbound

This paper cites Mumath-code: Combin- ing tool-use large language models with multi-perspective data augmentation for mathematical reasoning.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Mumath-code: Combin- ing tool-use large language models with multi-perspective data augmentation for mathematical reasoning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.195122Z

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 52c70981-a4dd-4608-a89c-38d52fa2ad45 · outbound

This paper cites Benchmarking Reasoning Robustness in Large Language Models.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Benchmarking Reasoning Robustness in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.937996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c55c07fc-b309-4abb-bf70-1c96b15f55f1 · outbound

This paper cites MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.942041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a173a57-1d26-4cca-9a22-9bb20f89f145 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.946814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80396b0e-a5e7-40e0-bd60-6c99919da825 · outbound

This paper cites Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.950951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f07a55ad-7f18-4314-a06e-8ccf6032ecc0 · outbound

This paper cites The problem and the current progress will be given below.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation The problem and the current progress will be given below

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.183430Z

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 9cbbe699-fc9d-40c0-b73f-22876cdd8c42 · outbound

This paper cites First, we will compute the gradients off andg.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation First, we will compute the gradients off andg

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.158403Z

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 d757e84a-ba67-4de2-9f2d-2287a1261d41 · outbound

This paper cites Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.903082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82182151-1961-422d-8330-615edc5eef43 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Training Verifiers to Solve Math Word Problems

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.862156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37c59522-c55b-444e-8731-b97df7de957a · outbound

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

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Tora: A tool-integrated reasoning agent for mathematical problem solving

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:08:58.246182Z

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 53371c67-c32d-42c5-bb6c-705770b9bb4e · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.855526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe99bdc5-c45a-4443-88a9-b061da0f59a6 · outbound

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

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:57.867148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 83c9eea7-fb04-4532-957e-94030896d882 · inbound

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems cites this paper.

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:50:36.691399Z

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 656bd126-cf33-4f5a-968f-a9d99d15cf4a · inbound

AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving cites this paper.

AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T18:43:31.887361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.