Paper Citation Record · LEDGER

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning

As of 5 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 2 inbound Pith citation observations for arXiv:2510.05478.

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

pith.paper-citation-record.v1
2510.05478 v3

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:23:20.431056Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:23:16.842205Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 31a6a2d0-840a-457c-b667-49799b97ceba · outbound

This paper cites advantage collapse.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning advantage collapse

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:16.702602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88954ec1-b658-48c6-96e2-cf676a9b9362 · outbound

This paper cites AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:16.842205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ab987d7-7b65-4965-87a7-698d29b843c9 · outbound

This paper cites 𝑟#…RewardsAdvantage 𝐴! 𝐴.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning 𝑟#…RewardsAdvantage 𝐴! 𝐴

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.003452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdf2ce7f-821e-4f41-bc9f-89f130a6d0ab · outbound

This paper cites {question}Please choose the answer from the follow- ing options:{choice string}. Output the final answer in<answer> </answer>.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning {question}Please choose the answer from the follow- ing options:{choice string}. Output the final answer in<answer> </answer>

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.135795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316b11d5-8a9e-40db-aa51-15869eabe27d · outbound

This paper cites Our framework establishes a closed-loop learning process by generating confidence-weighted pseudo-labels from majority voting to guide policy optimization with GRPO.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Our framework establishes a closed-loop learning process by generating confidence-weighted pseudo-labels from majority voting to guide policy optimization with GRPO

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.263471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 589131f7-a8e1-4d51-9804-9259c77714ec · outbound

This paper cites Listen, Think, and Understand.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Listen, Think, and Understand

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.396777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c589b2-21f9-4b24-8e9c-b95b9da91b0f · outbound

This paper cites Salmonn: Towards generic hearing abilities for large language models,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Salmonn: Towards generic hearing abilities for large language models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.559550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b69095e2-c45c-4a89-b52e-57faec7ab2ac · outbound

This paper cites Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.704277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fec4e2b-0834-4458-92cd-27227a7beb4b · outbound

This paper cites Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.776171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a6f0d2-4a32-4b43-8924-e64f340f3f43 · outbound

This paper cites Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.876357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89840c29-ad96-42f3-868b-da8d84e3413b · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:17.996500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cfa4e8-ca69-49d3-8e57-caa48c531417 · outbound

This paper cites Qwen2-Audio Technical Report.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Qwen2-Audio Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:18.145873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513d9acc-d37d-431a-9187-d31604016403 · outbound

This paper cites Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:18.440292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a186adcf-1b91-40f4-8702-c0d913298660 · outbound

This paper cites Omni-r1: Do you really need audio to fine-tune your audio llm?,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Omni-r1: Do you really need audio to fine-tune your audio llm?,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:18.597964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcb41631-a86a-47b7-a51d-857cad3553ce · outbound

This paper cites TTRL: Test-Time Reinforcement Learning.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning TTRL: Test-Time Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:18.772322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d3bb884-ac91-4cdb-8693-dbc4baaa8db6 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:18.925637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0110b7e2-d07c-4589-b4cf-4ab7830a3201 · outbound

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

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.056503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8424f054-81a8-4cd0-8309-8e0bf1930b9c · outbound

This paper cites MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.218335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f721397d-e7b9-4569-98c5-5247d43af320 · outbound

This paper cites MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.304868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2cef981-2ec9-4d57-ad06-77b058848d37 · outbound

This paper cites MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.414877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef63f2d9-aef0-4e24-8243-9876e2f2ab91 · outbound

This paper cites Desta: Enhancing speech language models through descrip- tive speech-text alignment,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Desta: Enhancing speech language models through descrip- tive speech-text alignment,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.542550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 704371f3-759e-4cf2-8beb-2747351e0162 · outbound

This paper cites Developing instruction-following speech language model without speech instruction-tuning data,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Developing instruction-following speech language model without speech instruction-tuning data,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.717992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513f4a43-d9e6-47ef-96c5-66ec8faf365b · outbound

This paper cites Desta2.5- audio: Toward general-purpose large audio language model with self-generated cross-modal alignment,.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Desta2.5- audio: Toward general-purpose large audio language model with self-generated cross-modal alignment,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:19.880966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe99f8e-e2ae-4851-85b9-d275d025b811 · outbound

This paper cites SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:20.055373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28a2971-a4d6-4140-b04f-4f1f68ed129d · outbound

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

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Spurious Rewards: Rethinking Training Signals in RLVR

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:20.230179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b33e03-d5e7-46f3-a8d3-77a9e3b3abb4 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:20.346056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ada16e7-107a-49cb-adf2-49ca8fd00ad0 · outbound

This paper cites Qwen2.5-Omni Technical Report.

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning Qwen2.5-Omni Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:20.431056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 88954ec1-b658-48c6-96e2-cf676a9b9362 · inbound