Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T14:22:34.997009Z
Paper Citation Record · LEDGER
AHELM: A Holistic Evaluation of Audio-Language Models
As of 6 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 10 inbound Pith citation observations for arXiv:2508.21376.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-03T11:52:45.801592Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T13:59:52.874154Z
Reference resolution
75 of 75 outbound references displayed
- verified exact2
- verified fuzzy47
- unresolved26
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation c9781f1e-d579-44da-aab7-1f362649c634 · outbound
This paper cites GPT-4 Technical Report.
AHELM: A Holistic Evaluation of Audio-Language Models GPT-4 Technical Report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:33.697071Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 51e0b0aa-3846-40c3-8ef3-af0dd4b33398 · outbound
This paper cites The Claude 3 model family: Opus, Sonnet, Haiku, 2024.
AHELM: A Holistic Evaluation of Audio-Language Models The Claude 3 model family: Opus, Sonnet, Haiku, 2024
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.739040Z
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 a2426604-3b6c-4168-a590-8cb736b79234 · outbound
This paper cites Common Voice: A Massively-Multilingual Speech Corpus.
AHELM: A Holistic Evaluation of Audio-Language Models Common Voice: A Massively-Multilingual Speech Corpus
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:33.923565Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2602b30f-96dd-4597-8e93-c1a7b37ea665 · outbound
This paper cites Qwen Technical Report.
AHELM: A Holistic Evaluation of Audio-Language Models Qwen Technical Report
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.102234Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b69d948-705f-4460-9ef4-0a4967a3ff44 · outbound
This paper cites Towards multimodal sarcasm detection (an _obviously_ perfect paper).
AHELM: A Holistic Evaluation of Audio-Language Models Towards multimodal sarcasm detection (an _obviously_ perfect paper)
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.731229Z
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 2b74c9ce-de68-4f7c-b1c5-70410f7cdd73 · outbound
This paper cites Qwen2-Audio Technical Report.
AHELM: A Holistic Evaluation of Audio-Language Models Qwen2-Audio Technical Report
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.352067Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41cacf6c-12bb-4b8c-a526-e4abebb8b96f · outbound
This paper cites VoxCeleb2: Deep Speaker Recognition.
AHELM: A Holistic Evaluation of Audio-Language Models VoxCeleb2: Deep Speaker Recognition
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.385152Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4269de4-646a-4529-86dc-f4865d5969a2 · outbound
This paper cites Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.
AHELM: A Holistic Evaluation of Audio-Language Models Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.722887Z
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 38f7207c-cba3-4f5a-9765-493bc4c10f6b · outbound
This paper cites FLEURS: Few-shot learning evaluation of universal representations of speech.
AHELM: A Holistic Evaluation of Audio-Language Models FLEURS: Few-shot learning evaluation of universal representations of speech
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.714660Z
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 c7aecf5c-9e8e-491b-8fa9-a0115a3c3be6 · outbound
This paper cites MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector.
AHELM: A Holistic Evaluation of Audio-Language Models MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-08-05T14:22:35.199235Z
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 d728dde4-d52a-4a2f-b473-9ccde920fbd1 · outbound
This paper cites Speech-transformer: a no-recurrence sequence-to- sequence model for speech recognition.
AHELM: A Holistic Evaluation of Audio-Language Models Speech-transformer: a no-recurrence sequence-to- sequence model for speech recognition
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.706024Z
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 fe123ce9-b696-4805-9234-726bc74cbbe1 · outbound
This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.
AHELM: A Holistic Evaluation of Audio-Language Models Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.779733Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9a8d9c12-d1d7-4781-8e23-3bd439c1ee47 · outbound
This paper cites Alpacafarm: A simulation framework for methods that learn from human feedback.
AHELM: A Holistic Evaluation of Audio-Language Models Alpacafarm: A simulation framework for methods that learn from human feedback
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.697626Z
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 02a1fa96-c5ad-42d8-b7c0-252adacb5815 · outbound
This paper cites Clap learning audio concepts from natural language supervision.
AHELM: A Holistic Evaluation of Audio-Language Models Clap learning audio concepts from natural language supervision
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.689202Z
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 6b2cf18e-ff38-4505-a3d2-fc3396052351 · outbound
This paper cites Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images.
AHELM: A Holistic Evaluation of Audio-Language Models Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-08-05T14:22:35.170240Z
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 dd5a1352-ec15-4aed-98d6-51d73912d090 · outbound
This paper cites CSR-I (WSJ0) Complete.
AHELM: A Holistic Evaluation of Audio-Language Models CSR-I (WSJ0) Complete
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.680312Z
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 a2cebc79-52ca-4f7e-bb5c-7b9e40df3c96 · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
AHELM: A Holistic Evaluation of Audio-Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.797552Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 80c80121-1169-4858-a503-2b0fc6c46247 · outbound
This paper cites Gama: A large audio-language model with advanced audio understanding and complex reasoning abilities.
AHELM: A Holistic Evaluation of Audio-Language Models Gama: A large audio-language model with advanced audio understanding and complex reasoning abilities
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.669917Z
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 0afda4f7-ceff-44f8-9dc6-e6014bebf7d0 · outbound
This paper cites V ocalsound: A dataset for improving human vocal sounds recognition.
AHELM: A Holistic Evaluation of Audio-Language Models V ocalsound: A dataset for improving human vocal sounds recognition
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.661754Z
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 93ad2fea-62ad-447d-84c6-01898825071b · outbound
This paper cites Sequence Transduction with Recurrent Neural Networks.
AHELM: A Holistic Evaluation of Audio-Language Models Sequence Transduction with Recurrent Neural Networks
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.808889Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 71697c35-c355-43ba-b779-faeba1af1613 · outbound
This paper cites Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.
AHELM: A Holistic Evaluation of Audio-Language Models Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.653539Z
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 6641787a-fc0b-4f71-8245-0d829f09500b · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
AHELM: A Holistic Evaluation of Audio-Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.815275Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9668280e-98e8-4b15-88ba-4a84c824c22c · outbound
This paper cites Design of a linguistic statistical decoder for the recognition of continuous speech.
AHELM: A Holistic Evaluation of Audio-Language Models Design of a linguistic statistical decoder for the recognition of continuous speech
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.645260Z
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 366e1f1f-8735-45f1-bd81-92a809687cb2 · outbound
This paper cites Gemini 2.5: Our most intelligent AI model.
AHELM: A Holistic Evaluation of Audio-Language Models Gemini 2.5: Our most intelligent AI model
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.636480Z
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 13b680d9-4fd5-4b52-95f4-db89ba74f8ea · outbound
This paper cites AudioCaps: Generat- ing captions for audios in the wild.
AHELM: A Holistic Evaluation of Audio-Language Models AudioCaps: Generat- ing captions for audios in the wild
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.628926Z
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 106c11c1-51a3-405e-9cb2-fed3cd7d70fc · outbound
This paper cites Prometheus-vision: Vision-language model as a judge for fine-grained evaluation.
AHELM: A Holistic Evaluation of Audio-Language Models Prometheus-vision: Vision-language model as a judge for fine-grained evaluation
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.620586Z
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 7d73ef13-c850-4071-8564-9fe6da7cf9b3 · outbound
This paper cites Vhelm: A holistic evaluation of vision language models.
AHELM: A Holistic Evaluation of Audio-Language Models Vhelm: A holistic evaluation of vision language models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.611540Z
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 e85f6957-3677-45d6-8bd4-bf9d69372f0f · outbound
This paper cites Holistic evaluation of text-to-image models.
AHELM: A Holistic Evaluation of Audio-Language Models Holistic evaluation of text-to-image models
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.601221Z
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 779edca4-f6cc-4ca8-a1b6-cf978c979b3e · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.591876Z
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 e0df2478-580a-4889-a915-2f06b3634273 · outbound
This paper cites The next chapter of the Gemini era for developers.
AHELM: A Holistic Evaluation of Audio-Language Models The next chapter of the Gemini era for developers
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.582196Z
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 280baaad-fbf2-4893-88cf-f56237ef9faa · outbound
This paper cites Hello GPT-4o, 2024.
AHELM: A Holistic Evaluation of Audio-Language Models Hello GPT-4o, 2024
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.572830Z
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 0ed65fc5-1a08-49c4-95dc-657b8e8cfabb · outbound
This paper cites Introducing our next-generation audio models, Mar 2025.
AHELM: A Holistic Evaluation of Audio-Language Models Introducing our next-generation audio models, Mar 2025
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.563178Z
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 1d37ba2b-6924-4f40-bb80-fbaad1e10bbf · outbound
This paper cites LibriSpeech: an ASR corpus based on public domain audio books.
AHELM: A Holistic Evaluation of Audio-Language Models LibriSpeech: an ASR corpus based on public domain audio books
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.553483Z
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 0a627daf-dfb1-40e9-82a3-149fe1217b18 · outbound
This paper cites MELD: A multimodal multi-party dataset for emotion recognition in conversa- tions.
AHELM: A Holistic Evaluation of Audio-Language Models MELD: A multimodal multi-party dataset for emotion recognition in conversa- tions
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.545031Z
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 4a345e82-50e5-47fb-8f4e-f8f82df64bad · outbound
This paper cites MLS: A Large-Scale Multilingual Dataset for Speech Research.
AHELM: A Holistic Evaluation of Audio-Language Models MLS: A Large-Scale Multilingual Dataset for Speech Research
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.858777Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0c9017b8-63ac-46df-81f9-2c5038f0525e · outbound
This paper cites Robust speech recognition via large-scale weak supervision.
AHELM: A Holistic Evaluation of Audio-Language Models Robust speech recognition via large-scale weak supervision
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.862427Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 20219ee9-5565-425d-80c8-3895efb66f6e · outbound
This paper cites Speech Robust Bench: A Robustness Benchmark For Speech Recognition.
AHELM: A Holistic Evaluation of Audio-Language Models Speech Robust Bench: A Robustness Benchmark For Speech Recognition
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.865850Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90cb00ee-5387-4568-af70-1a4c4781ecf3 · outbound
This paper cites V oice jailbreak attacks against GPT-4o, 2024.
AHELM: A Holistic Evaluation of Audio-Language Models V oice jailbreak attacks against GPT-4o, 2024
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.530681Z
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 09d16adf-5107-46f1-bb0e-e5f9d8bf2d42 · outbound
This paper cites Salmonn: Towards generic hearing abilities for large language models.
AHELM: A Holistic Evaluation of Audio-Language Models Salmonn: Towards generic hearing abilities for large language models
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.521493Z
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 4e4f081b-e1f0-4e0c-887e-5c4cd491836a · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
AHELM: A Holistic Evaluation of Audio-Language Models Gemini: A Family of Highly Capable Multimodal Models
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.875777Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3abc1829-0a24-4cb6-bc49-48c29cb16690 · outbound
This paper cites CoVoST 2 and Massively Multilingual Speech-to-Text Translation.
AHELM: A Holistic Evaluation of Audio-Language Models CoVoST 2 and Massively Multilingual Speech-to-Text Translation
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.879225Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b57f1fcb-69fa-49dc-8cfe-fa202f93dd4e · outbound
This paper cites Qwen2.5-Omni Technical Report.
AHELM: A Holistic Evaluation of Audio-Language Models Qwen2.5-Omni Technical Report
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.882641Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81ee07bf-d9ee-44bb-b7c7-8ea7ded00799 · outbound
This paper cites Qwen3 Technical Report.
AHELM: A Holistic Evaluation of Audio-Language Models Qwen3 Technical Report
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.886194Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1b45dbc-f6be-4405-871f-4538421e4457 · outbound
This paper cites AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension.
AHELM: A Holistic Evaluation of Audio-Language Models AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.889693Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4d5afb4d-7645-48d4-86bc-306b24464242 · outbound
This paper cites Speechlm: Enhanced speech pre-training with unpaired textual data.
AHELM: A Holistic Evaluation of Audio-Language Models Speechlm: Enhanced speech pre-training with unpaired textual data
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.512709Z
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 e4df7286-3747-4109-a699-fcaec0306b8a · outbound
This paper cites Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese.
AHELM: A Holistic Evaluation of Audio-Language Models Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:22:34.896569Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f46aaaf8-49d0-4b7f-9471-8852c1804a6d · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 47
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.503933Z
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 6b02af22-b3d2-4244-a430-85bf59d46073 · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 48
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.495380Z
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 94f55932-df50-4f9f-ae84-315f1317d399 · outbound
This paper cites humorous and imaginative.
AHELM: A Holistic Evaluation of Audio-Language Models humorous and imaginative
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.487336Z
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 9122540e-17ca-44f8-9f7d-e72828c7eedb · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 50
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.478978Z
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 36bc4d4e-83e2-4d0e-bf9d-0e3c89ed6915 · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 51
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.470623Z
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 746c16fa-8b67-4ab6-8ddd-f90736f57628 · outbound
This paper cites E.1.1 Obtaining a list of contrasting roles We use the list of roles from PAIRS (replicated in Table A4) to seed the generation of speech content.
AHELM: A Holistic Evaluation of Audio-Language Models E.1.1 Obtaining a list of contrasting roles We use the list of roles from PAIRS (replicated in Table A4) to seed the generation of speech content
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.461880Z
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 1953059c-e1a3-4b3a-9680-cad11029ab8e · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 53
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.452859Z
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 7100bcb0-534f-44b1-853f-e0a1fb4429cb · outbound
This paper cites You should refer to the score rubric.
AHELM: A Holistic Evaluation of Audio-Language Models You should refer to the score rubric
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.445050Z
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 91bc551c-76b9-45aa-bc4f-37b5f5d10b12 · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.437420Z
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 fd9eec2a-1908-42c0-81cc-67730c0c68d4 · outbound
This paper cites haha”) or throat clearing (e.g., “ahem.
AHELM: A Holistic Evaluation of Audio-Language Models haha”) or throat clearing (e.g., “ahem
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.429327Z
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 cafd4911-0adb-4276-8e8d-1cd50d4a9aeb · outbound
This paper cites an unresolved cited work.
AHELM: A Holistic Evaluation of Audio-Language Models Unresolved cited work
Reference 57
- Resolution
- unresolved
- raw_fallback, observed 2026-08-05T14:22:35.421481Z
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 d000f3ec-6c48-4317-99a0-4a1f55975eaf · outbound
This paper cites From Table A9, we see that Qwen2-Audio Instruct takes the lead in audio knowledge, followed by Gemini 2.5 Pro (05-06 Preview) and then Gemini 2.0 Flash.
AHELM: A Holistic Evaluation of Audio-Language Models From Table A9, we see that Qwen2-Audio Instruct takes the lead in audio knowledge, followed by Gemini 2.5 Pro (05-06 Preview) and then Gemini 2.0 Flash
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.413407Z
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 0ad1c622-00ad-4d0f-be3a-b2dc963f88b7 · outbound
This paper cites When looking at the safety aspect, we see that OpenAI models are robust to the voice jailbreak attack.
AHELM: A Holistic Evaluation of Audio-Language Models When looking at the safety aspect, we see that OpenAI models are robust to the voice jailbreak attack
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.404930Z
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 ce0143f0-edec-44b0-a2c5-f3104c8eec86 · outbound
This paper cites We explain our benchmark in Section 3 and describe the experiments in Section 4 and report results in Section 5.
AHELM: A Holistic Evaluation of Audio-Language Models We explain our benchmark in Section 3 and describe the experiments in Section 4 and report results in Section 5
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.396940Z
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 fe1d0241-7fb1-4404-878f-8d5d953d958a · outbound
This paper cites Limitations.
AHELM: A Holistic Evaluation of Audio-Language Models Limitations
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.388203Z
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 94467b2d-8bef-4025-b527-944ac890cf07 · outbound
This paper cites Guidelines: • The answer NA means that the paper does not include theoretical results.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not include theoretical results
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.379320Z
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 865d1775-6ed3-449e-a803-01997f63b213 · outbound
This paper cites Guidelines: • The answer NA means that the paper does not include experiments.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not include experiments
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.371248Z
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 bed55278-f3a2-4c5b-942a-36e402193d8b · outbound
This paper cites com/stanford-crfm/helm and the new datasets at https://huggingface.co/ datasets/UCSC-VLAA/PARADE_audio and https://huggingface.co/datasets/ stanford-crfm/CoReBench_v1.
AHELM: A Holistic Evaluation of Audio-Language Models com/stanford-crfm/helm and the new datasets at https://huggingface.co/ datasets/UCSC-VLAA/PARADE_audio and https://huggingface.co/datasets/ stanford-crfm/CoReBench_v1
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.362856Z
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 31b3c5a6-d911-4336-a6d4-ab1b7ac171cd · outbound
This paper cites Guidelines: • The answer NA means that the paper does not include experiments.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not include experiments
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.354147Z
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 c9c61ba0-91ae-45a4-bcfd-6cd5a60f4db5 · outbound
This paper cites But we do not compute error bars for other scenarios.
AHELM: A Holistic Evaluation of Audio-Language Models But we do not compute error bars for other scenarios
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.344723Z
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 2b1cd651-9153-45be-a311-d04b174b3f1d · outbound
This paper cites Guidelines: • The answer NA means that the paper does not include experiments.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not include experiments
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.335836Z
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 0ba18208-7e04-4b5c-8bd6-64e4f23efcec · outbound
This paper cites Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.327529Z
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 1aacc2fa-b354-4c1b-82a3-e84f0db5faf4 · outbound
This paper cites Guidelines: • The answer NA means that there is no societal impact of the work performed.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that there is no societal impact of the work performed
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.318849Z
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 462c6a8a-0ff0-46e1-ae74-e02ca8c24b93 · outbound
This paper cites Before transforming tran- scripts to audio, we performed human scrutiny of the audio transcripts to make sure that there is no improper or toxic content in the metadata.
AHELM: A Holistic Evaluation of Audio-Language Models Before transforming tran- scripts to audio, we performed human scrutiny of the audio transcripts to make sure that there is no improper or toxic content in the metadata
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.309287Z
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 979de6e4-0d9a-433a-8dfa-f1b0852bb2da · outbound
This paper cites We cite all the datasets and models used in our work.
AHELM: A Holistic Evaluation of Audio-Language Models We cite all the datasets and models used in our work
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.300092Z
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 e119bfdd-abc9-4fae-92af-603f17650782 · outbound
This paper cites PARADE is available at https://huggingface.co/datasets/UCSC-VLAA/PARADE_ audio.
AHELM: A Holistic Evaluation of Audio-Language Models PARADE is available at https://huggingface.co/datasets/UCSC-VLAA/PARADE_ audio
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.289975Z
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 85324c3b-c3d3-4ad6-904e-fa33b94ec416 · outbound
This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.279914Z
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 48de1972-aa06-47ee-883c-a22d9a349457 · outbound
This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.
AHELM: A Holistic Evaluation of Audio-Language Models Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.269972Z
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 913828ab-683a-4f62-91d4-fe2b0213da28 · outbound
This paper cites Answer: [Yes] Justification: As detailed in the Appendix B, we leverage OpenAI’s GPT-4o to create audio transcripts for the curation of PARADE benchmark.
AHELM: A Holistic Evaluation of Audio-Language Models Answer: [Yes] Justification: As detailed in the Appendix B, we leverage OpenAI’s GPT-4o to create audio transcripts for the curation of PARADE benchmark
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T14:22:35.259930Z
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 438bb6eb-afa4-4118-9e01-f38ceee8c266 · inbound
AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs cites this paper.
AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs AHELM: A Holistic Evaluation of Audio-Language Models
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T18:11:43.185900Z
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 420de55c-2f6c-49e9-9414-845e6f2c69af · inbound
Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics cites this paper.
Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics AHELM: A Holistic Evaluation of Audio-Language Models
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T11:52:45.801592Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b118258d-1bab-4c12-ba6a-d91a2b208abd · inbound
PRiSM: Benchmarking Phone Realization in Speech Models cites this paper.
PRiSM: Benchmarking Phone Realization in Speech Models AHELM: A Holistic Evaluation of Audio-Language Models
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:21:31.131370Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3af163d3-1a39-4b7a-8f15-d33576402f1d · inbound
VoxSafeBench: Not Just What Is Said, but Who, How, and Where cites this paper.
VoxSafeBench: Not Just What Is Said, but Who, How, and Where AHELM: A Holistic Evaluation of Audio-Language Models
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T10:24:22.088783Z
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 a2e3a273-2a73-4c70-9492-e80937080f18 · inbound
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech cites this paper.
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech AHELM: A Holistic Evaluation of Audio-Language Models
Reference 25
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:51:10.226416Z
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 c7a02f6c-211f-4b94-ba6b-cd699f7bcfc5 · inbound
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI cites this paper.
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI AHELM: A Holistic Evaluation of Audio-Language Models
Reference 227
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-09T05:55:29.197360Z
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 ec1072ce-d1cb-4a1e-97ae-f072a79f6845 · inbound
AudioMosaic: Contrastive Masked Audio Representation Learning cites this paper.
AudioMosaic: Contrastive Masked Audio Representation Learning AHELM: A Holistic Evaluation of Audio-Language Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T01:53:28.861492Z
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 6e1dc822-8c61-4464-b2ea-73165ac7f0a0 · inbound
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities cites this paper.
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities AHELM: A Holistic Evaluation of Audio-Language Models
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:17:57.430007Z
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 0a7d2131-ece3-4fec-9428-112d78267f36 · inbound
RedVox: Safety and Fairness Gaps in Speech Models Across Languages cites this paper.
RedVox: Safety and Fairness Gaps in Speech Models Across Languages AHELM: A Holistic Evaluation of Audio-Language Models
Reference 122
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T13:59:52.875641Z
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 6d5d8abb-cfc8-46d0-a5f4-cc38b5f97d4c · inbound
RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems cites this paper.
RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems AHELM: A Holistic Evaluation of Audio-Language Models
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T00:57:37.780637Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.