Paper Citation Record · LEDGER

On the reliability of feature attribution methods for speech classification

As of 13 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2505.16406.

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

pith.paper-citation-record.v1
2505.16406 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:04:08.457256Z

measured 40 of 40 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:04:05.568025Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T15:04:08.598379Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy31
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 88be1ac9-9131-4893-a386-514425896815 · outbound

This paper cites On the reliability of feature attribution methods for speech classification.

On the reliability of feature attribution methods for speech classification On the reliability of feature attribution methods for speech classification

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T15:04:08.753701Z

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 586b0b26-cf6a-4841-be84-04f4ddcca0c0 · outbound

This paper cites an unresolved cited work.

On the reliability of feature attribution methods for speech classification Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:04:13.004487Z

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 75d60bfc-0116-4c72-ad0f-2c5dc6a56582 · outbound

This paper cites an unresolved cited work.

On the reliability of feature attribution methods for speech classification Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:04:12.937056Z

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 02f6af16-8424-4733-9d21-70eb2e132c2b · outbound

This paper cites Within each group, we present the effects of the varied conditions in applying feature attribution methods.

On the reliability of feature attribution methods for speech classification Within each group, we present the effects of the varied conditions in applying feature attribution methods

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.784363Z

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 6f0f37b2-701d-4ad0-834e-970e6846c9a2 · outbound

This paper cites an unresolved cited work.

On the reliability of feature attribution methods for speech classification Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:04:12.717758Z

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 12c96809-705f-473c-ae5c-ce15abf3e056 · outbound

This paper cites an unresolved cited work.

On the reliability of feature attribution methods for speech classification Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:04:12.697345Z

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 94d7f0df-e118-4478-b9e8-a992be39ae60 · outbound

This paper cites Can We Trust Explainable AI Methods on ASR? An Eval- uation on Phoneme Recognition,.

On the reliability of feature attribution methods for speech classification Can We Trust Explainable AI Methods on ASR? An Eval- uation on Phoneme Recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.341564Z

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 7a793276-0543-419a-9c4c-3c76437fb8bf · outbound

This paper cites Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Represen- tations,.

On the reliability of feature attribution methods for speech classification Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Represen- tations,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.650682Z

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 31653e5d-2b39-43e0-b1d9-acf8e7ff872f · outbound

This paper cites HuBERT: Self-Supervised Speech Rep- resentation Learning by Masked Prediction of Hidden Units,.

On the reliability of feature attribution methods for speech classification HuBERT: Self-Supervised Speech Rep- resentation Learning by Masked Prediction of Hidden Units,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:04:06.304747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b402b109-6f2e-44c8-b39f-691b30acda20 · outbound

This paper cites We use a hop length of 320 for the STFT and ISTFT transformations to keep the time resolution at 20ms to be consistent with the wav2vec2 model feature extrac- tor.

On the reliability of feature attribution methods for speech classification We use a hop length of 320 for the STFT and ISTFT transformations to keep the time resolution at 20ms to be consistent with the wav2vec2 model feature extrac- tor

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.870273Z

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 299c900e-37a8-4c6a-8ad9-699bbc4d7caf · outbound

This paper cites Attention Is All You Need,.

On the reliability of feature attribution methods for speech classification Attention Is All You Need,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:04:06.389914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c7054b-af2f-40f0-b08d-8d5fba480d2d · outbound

This paper cites How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems,.

On the reliability of feature attribution methods for speech classification How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.563396Z

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 5d5ddab9-19d9-4389-9321-fecbd25c8409 · outbound

This paper cites AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark,.

On the reliability of feature attribution methods for speech classification AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.492303Z

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 4039b78e-b56d-4e7f-a4d4-c9cbc06d7641 · outbound

This paper cites Explanations for Automatic Speech Recognition,.

On the reliability of feature attribution methods for speech classification Explanations for Automatic Speech Recognition,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.415892Z

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 31391165-37d8-4db4-ba5b-94987f76a770 · outbound

This paper cites Phoneme Discretized Saliency Maps for Explainable Detection of AI- Generated V oice,.

On the reliability of feature attribution methods for speech classification Phoneme Discretized Saliency Maps for Explainable Detection of AI- Generated V oice,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.207976Z

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 a9324419-35c9-429d-a1c1-f119d3f07204 · outbound

This paper cites SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation,.

On the reliability of feature attribution methods for speech classification SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.150634Z

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 7fa48df9-070f-460c-8b8b-6a6a1f2d0ad1 · outbound

This paper cites Investigating the Effectiveness of Explainability Methods in Parkinson’s Detection from Speech,.

On the reliability of feature attribution methods for speech classification Investigating the Effectiveness of Explainability Methods in Parkinson’s Detection from Speech,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:12.105554Z

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 b2c9f949-22e4-46e9-8504-f44761495f41 · outbound

This paper cites Explaining speech classification models via word-level au- dio segments and paralinguistic features,.

On the reliability of feature attribution methods for speech classification Explaining speech classification models via word-level au- dio segments and paralinguistic features,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.916015Z

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 1ff28901-1bbb-499b-90ad-7ad9c750ff3a · outbound

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

On the reliability of feature attribution methods for speech classification Robust speech recognition via large-scale weak supervision,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.793891Z

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 49a59723-96e1-43e0-8c84-128949c9b47a · outbound

This paper cites A song of (dis)agreement: Evaluating the evaluation of explainable artificial intelligence in natural language processing,.

On the reliability of feature attribution methods for speech classification A song of (dis)agreement: Evaluating the evaluation of explainable artificial intelligence in natural language processing,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.224269Z

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 d49f0a89-4b2e-4001-af8f-1a135b8b91a1 · outbound

This paper cites Visualizing and Understanding Con- volutional Networks,.

On the reliability of feature attribution methods for speech classification Visualizing and Understanding Con- volutional Networks,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.762082Z

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 29bdcfa1-ad5d-4998-8988-88868b1f6852 · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

On the reliability of feature attribution methods for speech classification Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:04:07.377575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf5f51e-48d3-4dfc-a14f-ba9a952ac5db · outbound

This paper cites Explaining by remov- ing: A unified framework for model explanation,.

On the reliability of feature attribution methods for speech classification Explaining by remov- ing: A unified framework for model explanation,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.627393Z

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 ef45670b-11ca-4ebd-9ae6-cdb0d0d4a885 · outbound

This paper cites The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?.

On the reliability of feature attribution methods for speech classification The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.492278Z

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 021a1fc1-15db-4586-857a-9bbfb7604fd1 · outbound

This paper cites Exploring the role of BERT token representations to explain sentence probing results,.

On the reliability of feature attribution methods for speech classification Exploring the role of BERT token representations to explain sentence probing results,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.318341Z

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 cd27a4e2-d6f0-4f68-b330-9c669d056dde · outbound

This paper cites Evaluating explana- tions: How much do explanations from the teacher aid students?.

On the reliability of feature attribution methods for speech classification Evaluating explana- tions: How much do explanations from the teacher aid students?

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.275150Z

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 545dedaa-c0aa-405b-9fff-80f30c0ccc36 · outbound

This paper cites The disagreement problem in explainable machine learning: A practitioner’s perspective,.

On the reliability of feature attribution methods for speech classification The disagreement problem in explainable machine learning: A practitioner’s perspective,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.255518Z

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 a15d7218-c123-44c2-bf98-3107fc1fbd7c · outbound

This paper cites Common voice: A massively-multilingual speech corpus,.

On the reliability of feature attribution methods for speech classification Common voice: A massively-multilingual speech corpus,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:09.777653Z

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 9d6d613e-6f22-47d2-a8a1-2f69569b9da9 · outbound

This paper cites When explanations lie: Why many modified bp attributions fail,.

On the reliability of feature attribution methods for speech classification When explanations lie: Why many modified bp attributions fail,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.072589Z

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 a221eb97-a155-4761-9ba2-bbc16f3c440c · outbound

This paper cites Impossibil- ity theorems for feature attribution,.

On the reliability of feature attribution methods for speech classification Impossibil- ity theorems for feature attribution,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:10.936050Z

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 7e491be3-b85e-431d-8eee-2e45351004b8 · outbound

This paper cites “Will you find these shortcuts?.

On the reliability of feature attribution methods for speech classification “Will you find these shortcuts?

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:10.773205Z

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 2977baec-71c1-42e0-befd-c86d7cd9cf5e · outbound

This paper cites Dy- namic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis,.

On the reliability of feature attribution methods for speech classification Dy- namic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:10.757333Z

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 2d74c39e-564e-4928-afab-98b06f503150 · outbound

This paper cites Un- derstanding and Visualizing Raw Waveform-Based CNNs,.

On the reliability of feature attribution methods for speech classification Un- derstanding and Visualizing Raw Waveform-Based CNNs,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:10.521452Z

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 42feae4c-975f-4930-96b6-35c22142c4f6 · outbound

This paper cites “Why Should I Trust You?.

On the reliability of feature attribution methods for speech classification “Why Should I Trust You?

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:10.262781Z

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 d41c5ce2-cdb5-42e8-b787-9204d953adc5 · outbound

This paper cites TIMIT Acoustic-Phonetic Continuous Speech Cor- pus,.

On the reliability of feature attribution methods for speech classification TIMIT Acoustic-Phonetic Continuous Speech Cor- pus,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:09.977019Z

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 cb0aff2e-78eb-498b-bd06-bd2ae6bac232 · outbound

This paper cites Speech Model Pre-training for End-to-End Spoken Language Understanding,.

On the reliability of feature attribution methods for speech classification Speech Model Pre-training for End-to-End Spoken Language Understanding,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:09.526954Z

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 33e00b68-96fc-4d29-9ba9-cceda5f5a329 · outbound

This paper cites Captum: A unified and generic model interpretability library for PyTorch,.

On the reliability of feature attribution methods for speech classification Captum: A unified and generic model interpretability library for PyTorch,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:09.263039Z

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 941bc786-fb5f-4303-b49c-9b8c6330f2f8 · outbound

This paper cites Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi,.

On the reliability of feature attribution methods for speech classification Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:09.004299Z

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 5282aa18-2a00-49df-93e8-ffa10a63692c · outbound

This paper cites Available: https://proceedings.mlr.press/v202/ radford23a.html.

On the reliability of feature attribution methods for speech classification Available: https://proceedings.mlr.press/v202/ radford23a.html

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:04:11.769428Z

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.

Pith citing papers

Observation 88be1ac9-9131-4893-a386-514425896815 · inbound