Paper Citation Record · LEDGER

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models

As of 11 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2608.06409.

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

pith.paper-citation-record.v1
2608.06409 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T04:32:31.857707Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact1
verified fuzzy16
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 12fc2f26-e210-4872-8367-3d12a1a249b8 · outbound

This paper cites Qwen2.5-Omni Technical Report.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Qwen2.5-Omni Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.744530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1d5867-a5d2-4b12-907a-4be96bf25341 · outbound

This paper cites Qwen2-Audio Technical Report.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Qwen2-Audio Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.748709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7df22cbd-5337-4217-b9fd-2d77c200377e · outbound

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

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.751914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7169cc16-c308-4225-8642-e29ac828e1da · outbound

This paper cites Kimi-audio technical report,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Kimi-audio technical report,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.351418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1f549bc2-f8db-46eb-9657-e954e9be14af · outbound

This paper cites Phi-4 Technical Report.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Phi-4 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.758858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e3798a-e601-4e98-b73d-f23e6beae2bc · outbound

This paper cites Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning bench- mark for speech,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning bench- mark for speech,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.342391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5a74baf5-dfff-4e1d-ba59-47745e2b5ba9 · outbound

This paper cites Air-bench: Benchmarking large audio-language models via generative comprehension,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Air-bench: Benchmarking large audio-language models via generative comprehension,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.764890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 514276ec-cd9f-4def-8c4f-e1cc9e407b2b · outbound

This paper cites Sd-eval: A benchmark dataset for spoken dialogue under- standing beyond words,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Sd-eval: A benchmark dataset for spoken dialogue under- standing beyond words,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.327593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 73518e17-ad29-4a05-a8ed-85e3b0495df2 · outbound

This paper cites V ocal communication of emotion: A review of research paradigms,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models V ocal communication of emotion: A review of research paradigms,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.318384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 84c1c3fa-3f22-4829-9065-125e7e961368 · outbound

This paper cites Communication of emotions in vocal expression and music performance: Different channels, same code?.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Communication of emotions in vocal expression and music performance: Different channels, same code?

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.308892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0b853dc7-4226-41e7-9c07-496e62ae3e72 · outbound

This paper cites Crema-d: Crowd-sourced emotional multimodal actors dataset,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Crema-d: Crowd-sourced emotional multimodal actors dataset,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.775354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21baf8da-79c4-415f-bf8f-335cb0217c49 · outbound

This paper cites Calibrate before use: Improving few-shot performance of language models,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Calibrate before use: Improving few-shot performance of language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.284663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ea5c18ea-ad1b-4da2-b542-f9db439a562e · outbound

This paper cites Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.781328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c06e0b6-47a1-4b6d-907c-8f2e6f0f9fcd · outbound

This paper cites Speechgpt: Empowering large language models with intrinsic cross- modal conversational abilities,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Speechgpt: Empowering large language models with intrinsic cross- modal conversational abilities,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.784638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4495293-cf5d-4097-b97a-12ffc1a69720 · outbound

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

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Salmonn: Towards generic hearing abilities for large language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.268581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 975be820-add6-4905-8c1e-0de9bccd650b · outbound

This paper cites Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.790153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb2572c-a031-49a5-9ce0-ca827b501a8e · outbound

This paper cites Do audio LLMs really LISTEN, or just transcribe? measuring lexical vs. acoustic emotion cues reliance,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Do audio LLMs really LISTEN, or just transcribe? measuring lexical vs. acoustic emotion cues reliance,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.260228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a342f4ec-b2ba-4a16-9a7a-2ec0c823efe3 · outbound

This paper cites Large Language Models Are Not Robust Multiple Choice Selectors.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Large Language Models Are Not Robust Multiple Choice Selectors

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.796280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f238438-bd9e-441c-a9de-d0807bd603b7 · outbound

This paper cites Answer-level calibration for free-form multiple choice ques- tion answering,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Answer-level calibration for free-form multiple choice ques- tion answering,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.250869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 55b95ac9-c208-44b8-980f-53e4562a4e8e · outbound

This paper cites Hubert: Self-supervised speech representation learning by masked prediction of hidden units,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Hubert: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.803074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d5956e8-bd0a-40fe-9de2-4cace1eb436b · outbound

This paper cites Wavlm: Large-scale self-supervised pre- training for full stack speech processing,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Wavlm: Large-scale self-supervised pre- training for full stack speech processing,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.806129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa98c24-0039-4434-ac89-9f289bd86581 · outbound

This paper cites Robust speech recognition via large-scale weak supervi- sion,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Robust speech recognition via large-scale weak supervi- sion,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.809159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15dd4bdf-9119-43c7-bcef-508061614cdd · outbound

This paper cites Layer-wise analysis of a self-supervised speech representation model,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Layer-wise analysis of a self-supervised speech representation model,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.812197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d95b1587-b325-4ae9-8fe7-80e61dfb5db2 · outbound

This paper cites Probing phoneme, language and speaker information in unsupervised speech representations,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Probing phoneme, language and speaker information in unsupervised speech representations,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.219835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8a24cd67-ef46-40c3-91c3-e4cf0f41e746 · outbound

This paper cites Dawn of the transformer era in speech emotion recognition: Closing the valence gap,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Dawn of the transformer era in speech emotion recognition: Closing the valence gap,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.210353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d941a1d7-0c41-496d-95a6-c3be79a69a4f · outbound

This paper cites emotion2vec: Self-supervised pre-training for speech emotion repre- sentation,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models emotion2vec: Self-supervised pre-training for speech emotion repre- sentation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.821264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b8cb20c-c684-4561-851e-9dbd9768238f · outbound

This paper cites AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.824223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdcc73b5-582e-4ab3-84d1-176c007af2dc · outbound

This paper cites Probing classifiers: Promises, shortcomings, and ad- vances,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Probing classifiers: Promises, shortcomings, and ad- vances,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.827506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e1e1750-5569-426a-9efc-2dff05f7ae46 · outbound

This paper cites Interpreting GPT: The logit lens,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Interpreting GPT: The logit lens,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.189362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0ddd82d8-1421-4acf-a6f1-958a9fc9eb74 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.832716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cd0d5de-6a37-4cb8-b987-f20dd1ccde1b · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Investigating gender bias in language models using causal mediation analysis,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.180872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a572b513-5b0e-49d3-a1ab-73c952795bee · outbound

This paper cites Causal abstractions of neural networks,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Causal abstractions of neural networks,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.171051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cf029d59-5115-49fa-9785-ff579905f8aa · outbound

This paper cites Locating and editing factual associations in gpt,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Locating and editing factual associations in gpt,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.841090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b8722f-1044-4f42-97ec-c41e226f8953 · outbound

This paper cites Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.843709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a16442fd-35b7-4eb5-b923-cc08be8f495a · outbound

This paper cites Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.846587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47eb4545-247f-4fa5-8bda-220483bfde1a · outbound

This paper cites AR&D: A framework for retrieving and describing concepts for interpreting AudioLLMs,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models AR&D: A framework for retrieving and describing concepts for interpreting AudioLLMs,

Reference 36

Resolution: verified exact; raw_fallback, observed 2026-08-10T04:32:32.031362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 02154628-7b4f-461a-b37b-39cd7ad01534 · outbound

This paper cites Who wins the conflict? mechanistic interpretability of text bias in audio LLMs,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Who wins the conflict? mechanistic interpretability of text bias in audio LLMs,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.154974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 66530ff9-482e-4856-a6a1-cd81a27d2b6a · outbound

This paper cites VESUS: A crowd-annotated database to study emotion production and perception in spoken English,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models VESUS: A crowd-annotated database to study emotion production and perception in spoken English,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:32:32.144647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f28e80ba-7aed-4275-b341-81ebfbb19afb · outbound

This paper cites A theory of usable information under computational constraints,.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models A theory of usable information under computational constraints,

Reference 39

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T04:32:31.964757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.