Paper Citation Record · LEDGER

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

As of 21 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 2 inbound Pith citation observations for arXiv:2602.08222.

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

pith.paper-citation-record.v1
2602.08222 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:27:50.454980Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:28:01.622883Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T22:48:22.886654Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 59fa4573-ea50-4015-ac82-d0c550a352f8 · outbound

This paper cites Pre” denotes before joint training, and “Stronger (Post).

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Pre” denotes before joint training, and “Stronger (Post)

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:27:50.401394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d97815c-8e84-490e-901e-ad17479804e2 · outbound

This paper cites UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.463612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6084749-5a4c-4117-8136-fda46866aa78 · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger MiniLLM: On-Policy Distillation of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.534063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b682dd4-53a1-47d8-b5fe-33ba85abf028 · outbound

This paper cites The False Promise of Imitating Proprietary LLMs.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger The False Promise of Imitating Proprietary LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.597536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3526dbb3-d001-47dc-9941-6a34fbb45d75 · outbound

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

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Reinforced Self-Training (ReST) for Language Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.664337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724c113c-9907-46df-8fb4-9ce810d66487 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Distilling the Knowledge in a Neural Network

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.724872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e0a2ae-74d4-4925-a499-82e9d139bc74 · outbound

This paper cites NEFTune: Noisy Embeddings Improve Instruction Finetuning.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger NEFTune: Noisy Embeddings Improve Instruction Finetuning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.024742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67026650-d548-407c-b6e3-251e952190cf · outbound

This paper cites On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.384386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce582407-695a-48b4-a401-ca4e7122c79e · outbound

This paper cites WizardLM: Empowering large pre-trained language models to follow complex instructions.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger WizardLM: Empowering large pre-trained language models to follow complex instructions

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.509414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d6066e-9e7d-4323-a480-4914ae995cd8 · outbound

This paper cites Qwen3 Technical Report.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Qwen3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.668034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847763be-7e44-4c1e-9a08-4e48fa62f5fd · outbound

This paper cites Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., and Ma, K.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., and Ma, K

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.855213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ec002e-4c1d-4fad-ac9f-2e3ae9a599dc · outbound

This paper cites 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:50.171399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efaa566f-0fc5-4a8d-9bf9-4fe0d3b1d0e0 · outbound

This paper cites Transformer copilot: Learning from the mistake log in llm fine-tuning.arXiv preprint arXiv:2505.16270,.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Transformer copilot: Learning from the mistake log in llm fine-tuning.arXiv preprint arXiv:2505.16270,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:50.268899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 241cde0f-c00f-40d5-9061-76f59cdd8b0c · outbound

This paper cites an unresolved cited work.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Unresolved cited work

Reference 22

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:27:50.311246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d6226e-7335-4ca8-9378-126e17829fbc · outbound

This paper cites To answer the user’s question, you first think about the reasoning process and then provide the user with the answer.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger To answer the user’s question, you first think about the reasoning process and then provide the user with the answer

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:50.454980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cb47913-d6bd-4bdc-8d4a-23c21298a438 · outbound

This paper cites Configuration C (α= 0.1, β= 0.9, γ= 0), which disables the regression-repair signal, achieves the highest accuracy on MATH 500 (70.2%).

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Configuration C (α= 0.1, β= 0.9, γ= 0), which disables the regression-repair signal, achieves the highest accuracy on MATH 500 (70.2%)

Reference 500

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:27:50.342387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f44f265f-9029-492d-95e7-20521ee0881d · outbound

This paper cites Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.234476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ecea6dc-8ded-41bd-ba4f-6cf9a04ca6f2 · outbound

This paper cites Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.162370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b091852e-94c3-471b-8806-70e2c8284acf · outbound

This paper cites Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:50.058066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d4c6e4-18aa-4afd-a077-c26593e135f9 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Evaluating Large Language Models Trained on Code

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.347683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2721a2-edda-4515-ba47-6c8667c336fd · outbound

This paper cites Are NLP Models really able to Solve Simple Math Word Problems?.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Are NLP Models really able to Solve Simple Math Word Problems?

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:49.270292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54607f76-e570-42cd-a449-77b3b492c499 · outbound

This paper cites Program Synthesis with Large Language Models.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Program Synthesis with Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.189325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52eeadc-95b1-4472-a424-8987e24dc7cf · outbound

This paper cites Large Language Models Cannot Self-Correct Reasoning Yet.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Large Language Models Cannot Self-Correct Reasoning Yet

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.790097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1582f3b3-c8ad-4a09-a7d4-46aa0a24c73f · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Training Verifiers to Solve Math Word Problems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.418725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243bab27-3301-439b-92cf-da892926afa5 · outbound

This paper cites Real-Time Aligned Reward Model beyond Semantics.

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Real-Time Aligned Reward Model beyond Semantics

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-03T03:27:48.890632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5075ea1c-cdf2-4e45-8eb5-1cf11b959a1d · inbound

Policy Improvement Reinforcement Learning cites this paper.

Policy Improvement Reinforcement Learning Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-09T03:07:11.059756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 88863e25-b0d0-4b71-ad14-d5c05ee34262 · inbound

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training cites this paper.

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T14:28:01.622883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.