Paper Citation Record · LEDGER

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

As of 13 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 6 inbound Pith citation observations for arXiv:2601.11061.

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

pith.paper-citation-record.v1
2601.11061 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T10:13:15.647182Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T03:13:07.963343Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T03:14:31.665483Z

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8f5a0e18-e609-4c03-8bcd-d7415847e76a · outbound

This paper cites an unresolved cited work.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.280726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77764c6-16dc-4013-baae-24893b47c2f9 · outbound

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

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.452071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b09f264-9685-4506-981d-1900be54018f · outbound

This paper cites The reasoning-memorization interplay in language models is mediated by a single direction.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs The reasoning-memorization interplay in language models is mediated by a single direction

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.523326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed9ed0df-d29b-4f28-be89-c8d8198ed734 · outbound

This paper cites Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.630860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf2b441-794e-4350-bc82-1d0146fe3a2f · outbound

This paper cites HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.814920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffc9584-3a50-421c-9018-91003611e43e · outbound

This paper cites Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.951041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ae321a-ec46-4c73-a723-a87ea545fefd · outbound

This paper cites 2 OLMo 2 Furious.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs 2 OLMo 2 Furious

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.145479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03b36f4-d86f-4452-be41-ff46f16d8cf7 · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Spurious Rewards: Rethinking Training Signals in RLVR

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.212310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7db093bf-05df-4210-883f-92377ccec7e2 · outbound

This paper cites Detecting Memorization in Large Language Models.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Detecting Memorization in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.310993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa8a444-62f3-40aa-86a1-443620487913 · outbound

This paper cites Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.414661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6a6d943-7412-49b1-8e8d-079f10e2ebf3 · outbound

This paper cites Qwen3 Technical Report.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Qwen3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.553819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dde6f1f-5748-492b-baf2-b2d3e2dd3021 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.647182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838803a9-c6a6-48c2-9e49-9783e1b17d8c · outbound

This paper cites Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:15.021174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 133578b5-d394-491b-b751-3cfc492c3836 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Transformer feed-forward layers are key-value memories

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.386551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a88acd3-be15-493f-a424-bfa82670cc09 · outbound

This paper cites Solving Quantitative Reasoning Problems with Language Models.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Solving Quantitative Reasoning Problems with Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.751527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746873b4-bf13-44b4-8e96-bf83f4bce58d · outbound

This paper cites Are Your LLMs Capable of Stable Reasoning?.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Are Your LLMs Capable of Stable Reasoning?

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.881237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81bd8425-f569-4e5f-af51-1dac109baa92 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.699803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fea7e4e0-acbc-4464-9978-08e8b41d89d6 · outbound

This paper cites Exploration vs exploitation: Rethinking rlvr through clipping, entropy, and spurious reward.arXiv preprint arXiv:2512.16912,.

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs Exploration vs exploitation: Rethinking rlvr through clipping, entropy, and spurious reward.arXiv preprint arXiv:2512.16912,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T10:13:14.325731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e0d494e5-58fd-4ed6-9b78-1b857687d61a · inbound

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training cites this paper.

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-26T01:15:16.925411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ae66e80a-5c2d-4298-9785-9922735cc5a2 · inbound

VeriGate: Verifier-Gated Step-Level Supervision for GRPO cites this paper.

VeriGate: Verifier-Gated Step-Level Supervision for GRPO Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T08:53:16.058852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a07b929c-f40f-4b06-971a-0eb8ac7915e9 · inbound

When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR cites this paper.

When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T08:29:41.280184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 69d96bbf-4951-4da1-bd98-967b9b092f60 · inbound

Predictable GRPO: A Closed-Form Model of Training Dynamics cites this paper.

Predictable GRPO: A Closed-Form Model of Training Dynamics Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T06:45:29.599112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c26c71ef-6c1b-40f6-9249-eeac1be6c1fb · inbound

Predictable GRPO: A Closed-Form Model of Training Dynamics cites this paper.

Predictable GRPO: A Closed-Form Model of Training Dynamics Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T20:27:21.698716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 88b68295-3d5f-44fa-a4ac-f7208502a78d · inbound

Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment cites this paper.

Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-07-08T03:14:31.666850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.