Paper Citation Record · LEDGER

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR

As of 6 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2604.18105.

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

pith.paper-citation-record.v1
2604.18105 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-05T13:15:50.794969Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:07:18.543379Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T16:07:18.649756Z

Reference resolution

34 of 34 outbound references displayed

verified exact27
verified fuzzy4
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5cc50c4a-651b-4806-9932-c676f56abf70 · outbound

This paper cites Fun-ASR technical report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Fun-ASR technical report

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.302515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7da1bb08-7c34-4060-b9c9-caab82427ab1 · outbound

This paper cites Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.346052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8df13715-f3a4-42fc-a9c7-c0f56cf3ff50 · outbound

This paper cites Wenetspeech-chuan: A large- scale sichuanese corpus with rich annotation for dialectal speech processing.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Wenetspeech-chuan: A large- scale sichuanese corpus with rich annotation for dialectal speech processing

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.339334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8f05a89f-ce2f-408a-830a-8e26f9109f09 · outbound

This paper cites AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.313166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ed05c17d-f466-4d42-b037-ec72edea00d7 · outbound

This paper cites Downscaling intelligence: Exploring perception and reasoning bottlenecks in small multimodal models.arXiv preprint arXiv:2511.17487.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Downscaling intelligence: Exploring perception and reasoning bottlenecks in small multimodal models.arXiv preprint arXiv:2511.17487

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.259064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6fb3f93a-cf53-4557-b67d-2b032e36f61f · outbound

This paper cites Prompting large language models with speech recognition abilities.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Prompting large language models with speech recognition abilities

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T13:21:06.540157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af0c3e40-4eba-4fc8-9bfe-e431ca73aeb5 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Sequence Transduction with Recurrent Neural Networks

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.291509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 39e80b68-f2a1-4a0b-a324-29a11dafecc3 · outbound

This paper cites Conformer: Convolution-augmented Transformer for Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Conformer: Convolution-augmented Transformer for Speech Recognition

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-05T13:21:06.270505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 44e6ba43-4058-4bd9-a488-3d3fd096143d · outbound

This paper cites Integrating pre-trained speech and language models for end-to-end speech recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Integrating pre-trained speech and language models for end-to-end speech recognition

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T13:21:06.531031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 75c73fcb-a533-4e20-9cd3-93b23f955f05 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Adam: A Method for Stochastic Optimization

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.296633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 02bb07cd-cedc-4e20-862b-5c6b982055e9 · outbound

This paper cites Contextualization of asr with llm using phonetic retrieval-based augmentation.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Contextualization of asr with llm using phonetic retrieval-based augmentation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T13:21:06.535175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4f8c7203-3f75-4e3c-b49e-f023ca52de37 · outbound

This paper cites WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.294936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eb5755be-f0df-4074-9c12-38e2410bcec6 · outbound

This paper cites Voxtral.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Voxtral

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-05T13:21:06.288305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d329b114-03c1-412d-bd57-b680f7132aa0 · outbound

This paper cites Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.276178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7c4f7696-4372-49c6-a8a7-90442edb1a00 · outbound

This paper cites Stateful conformer with cache-based inference for streaming automatic speech recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Stateful conformer with cache-based inference for streaming automatic speech recognition

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T13:21:06.527499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 47b3835b-a2f2-481c-9359-8a2863bdaeba · outbound

This paper cites SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.249364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 392b84a9-cc43-4c5a-b705-9ae7b1feea81 · outbound

This paper cites Evaluating hallucina- tions in multimodal llms with spoken queries under diverse acoustic conditions.arXiv preprint arXiv:2510.08581.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Evaluating hallucina- tions in multimodal llms with spoken queries under diverse acoustic conditions.arXiv preprint arXiv:2510.08581

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.327743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation edbe9a1d-bf6a-4146-b2a0-7f615fd00ee7 · outbound

This paper cites MLS: A Large-Scale Multilingual Dataset for Speech Research.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR MLS: A Large-Scale Multilingual Dataset for Speech Research

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.332766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61a908cf-03f2-4c2e-bb51-d6d6cd5bf5ca · outbound

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

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.320052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e288f875-d3de-4ea7-8483-9ddf66a51ecd · outbound

This paper cites Qwen3-ASR Technical Report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Qwen3-ASR Technical Report

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.241887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f66e0147-75fe-47ff-9268-692b3d487eda · outbound

This paper cites L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.365764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bca5e256-de41-4314-897b-adde2d50f769 · outbound

This paper cites Index-asr technical report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Index-asr technical report

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.371739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da266c15-6598-425c-b86c-fac0e22796a6 · outbound

This paper cites Back to basics: Revisiting asr in the age of voice agents.arXiv preprint arXiv:2603.25727.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Back to basics: Revisiting asr in the age of voice agents.arXiv preprint arXiv:2603.25727

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.360459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 264e8d1d-0dc4-4e03-bc76-23b2dd7fc850 · outbound

This paper cites ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.353109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f633ed74-cb31-419c-b18a-f930150d1af8 · outbound

This paper cites Step-Audio 2 Technical Report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Step-Audio 2 Technical Report

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.196498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 180a3df5-2c74-4b5a-b85b-2a06864d1cdc · outbound

This paper cites Uni-asr: Unified llm-based architecture for non-streaming and streaming automatic speech recognition.arXiv preprint arXiv:2603.11123.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Uni-asr: Unified llm-based architecture for non-streaming and streaming automatic speech recognition.arXiv preprint arXiv:2603.11123

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-05T13:21:06.234987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6686575a-a8a1-4e9d-9cd2-782cf231a2a6 · outbound

This paper cites Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.204122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5c6041a2-e9cd-452d-b68d-20c6174366d5 · outbound

This paper cites Qwen3-Omni Technical Report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Qwen3-Omni Technical Report

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.226586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4fc42d8e-3f4d-4ed8-9670-d9e59d9f9bcc · outbound

This paper cites Qwen3 Technical Report.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Qwen3 Technical Report

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.182334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c3cae221-1615-4e38-9688-0cf6661b90fd · outbound

This paper cites CR-CTC: Consistency regularization on CTC for improved speech recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR CR-CTC: Consistency regularization on CTC for improved speech recognition

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.172636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d5abe31f-6cd1-4942-b71c-8d865372d548 · outbound

This paper cites Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.222299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 210230e5-33fe-4c5a-b5b1-3653557e7037 · outbound

This paper cites Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-07-05T13:21:06.189264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5a678cfb-b67b-406b-9a82-6671bb536cb2 · outbound

This paper cites Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.217010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 51df2314-ec22-4027-b203-079da9370906 · outbound

This paper cites CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition.

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-05T13:21:06.211696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 68bbc463-626d-44e6-9079-2dfe733d9d65 · inbound

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR cites this paper.

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-05T16:07:18.654073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.