Pith. sign in

Paper Citation Record · LEDGER

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR

As of 23 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2607.05051.

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

pith.paper-citation-record.v1
2607.05051 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T09:35:44.381743Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-11T09:35:44.381743Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

29 of 29 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved28
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b38bedaa-8812-49b1-9758-d60a44115457 · outbound

This paper cites Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:a47524ec368c96f7ac9b0e4019f8ad3dfb1e5660630e42b7422fe47c61d94e62

Observation b4bf8623-f37d-4892-bc87-43e5fc25d838 · outbound

This paper cites Coconut [4] feeds last-layer hidden states back into the model in place of discrete tokens, allowing rea- soning to proceed in a continuous embedding space.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Coconut [4] feeds last-layer hidden states back into the model in place of discrete tokens, allowing rea- soning to proceed in a continuous embedding space

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:5c41d020c8d91cbf633ac95f17b4ad517aa5a559ecf244fa9cd91fba8bb81f9a

Observation 66b247be-3f8f-4bef-b16b-e46ecab79b8e · outbound

This paper cites would extra la- tent compute help this utterance?.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR would extra la- tent compute help this utterance?

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:0e7c79caee6614ac5c6861c413b836c54a9c5f09ffee3cda1fe6bb2100ff476a

Observation 433de1ba-f74a-4969-9c74-aa4ffc64e807 · outbound

This paper cites train on more data.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR train on more data

Reference 4

Resolution
malformed identifier
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:f6bdccd41520a5a9a937b0f31de3afc7faa06223e0149e5f3923290e76b362b8

Observation 365efd85-2e3b-4d75-a1cc-cccc2ac0eacf · outbound

This paper cites This asymmetry is by design.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR This asymmetry is by design

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b4377c6504f6d29ec9c141eaa56cf3719f534411c4d6bec5755aee38b5fe0db8

Observation a67fbb9f-d091-4b3e-9276-4ca08a58f7b9 · outbound

This paper cites an unresolved cited work.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b682964840ac57261acf1922604c6e08354acd2e1118e2ef2c3bf312b6af3bcf

Observation 18780e3d-d0e2-4ab1-ba1f-a4c7b4984e09 · outbound

This paper cites Robust speech recognition via Large-Scale weak supervision,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Robust speech recognition via Large-Scale weak supervision,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:4960ae4e6955a280e00d88b2a4b70403d1a4a24cbd05f649f4d9927b215e835c

Observation 35b3126d-ebfe-4215-95b8-050fe80dba23 · outbound

This paper cites OWSM v4: Improving open whisper-style speech models via data scaling and cleaning,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR OWSM v4: Improving open whisper-style speech models via data scaling and cleaning,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:6112f214e7ad40da05af17789bd6b35c3b3363d148b3c827e7efe7306b9a57b2

Observation d8eb67ff-d1c7-47aa-ad59-ee41e7d75e08 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Chain-of-thought prompting elicits reasoning in large language models,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:2f069eb99fa21a5bc7087f813f817449ee5dd4f2d15df9a43136d3e8fed19bb1

Observation b512082f-65c3-4be5-b0e5-b1b8a73d76c5 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Training Large Language Models to Reason in a Continuous Latent Space

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:56699921794a42fe975ff88be42b074d5ef95969987ec0501fdd6c51d8778ed5

Observation 29bc3ea0-c14a-461d-a85d-393acb0a9456 · outbound

This paper cites Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:93e57100a244682c8e37cf29b9d9d40123d5ddd10fac6cfa6a94e176cbb341b4

Observation 6e54cb4d-b88f-4ea2-8a3c-e09b04f77d60 · outbound

This paper cites Think before you speak: Training language models with pause tokens,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Think before you speak: Training language models with pause tokens,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:75645e77d1a8710e54243fb39cdd435edfd0c43675d35d754ad13a355ddd0e7a

Observation 5348cb12-7a45-4608-9059-90107eccfa94 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Lora: Low-rank adaptation of large language models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:8b57dfff6484d46dacc2c23f7d4301c659f83a50a6d22f6166c0e46e196fdbdc

Observation 0aa251c0-a8fa-4afa-99c9-fa9c0b553a36 · outbound

This paper cites The power of scale for Parameter-Efficient prompt tuning,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR The power of scale for Parameter-Efficient prompt tuning,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:e981a90c144e8263350ed6ffbbeca3c9ba3b0dad325826315ad7d668f0f297cb

Observation 3fa88b42-cc00-427c-8623-8adcf0b1bac1 · outbound

This paper cites Prefix-tuning: Optimizing continuous prompts for generation,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Prefix-tuning: Optimizing continuous prompts for generation,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b560e3db5015cc2d28c71ec65689e32c35c479426e7a4b3d3d8acea524bc7476

Observation 2a7d3e37-3869-4e16-aea3-08e6a8a5c477 · outbound

This paper cites Adaptive Computation Time for Recurrent Neural Networks.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Adaptive Computation Time for Recurrent Neural Networks

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:7b2279094360e8666139b112d68a7842e847d0f92a200790f19062ac3e401b51

Observation 61dbaa89-ca62-40c4-9e8f-bea2c5954bb6 · outbound

This paper cites PonderNet: Learning to Ponder.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR PonderNet: Learning to Ponder

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:28702c741da4d5e4bbf4db10aee6683050368552618f736ab42a1cf3db77cb30

Observation 073e34c4-2e04-4b34-a69f-de3362f23b1a · outbound

This paper cites Confident adaptive language mod- eling,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Confident adaptive language mod- eling,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:e6a13b9f2192b8abbe29d2049493afec9bde2933ee75fc826605882c41dbf372

Observation 7429241d-3235-4ea5-9816-3162142103b1 · outbound

This paper cites DeeBERT: Dynamic early exiting for accelerating BERT inference,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR DeeBERT: Dynamic early exiting for accelerating BERT inference,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:454364f887bca7a376839cedce0c3deaae1f5b6879709d3e217f96ded7f73ea1

Observation 3e14638e-cfb9-489e-ac26-d5d4d209dc63 · outbound

This paper cites Qwen3-ASR Technical Report.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Qwen3-ASR Technical Report

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:e1e292957176216896ef38acb762b42c61204985a493b94754ee82233bd6215c

Observation be18eeb9-5b63-4540-bc01-527a33335966 · outbound

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

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Common voice: A massively-multilingual speech corpus,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:baf379963786473a9f8d549c8e2a5853ea11e51cf683d9f145dc1e90e7c097c4

Observation bab88ca9-b577-4721-8e2b-fbe6da7cfdfa · outbound

This paper cites FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b5040f527d8f3cf567a992b30c62db54f0aa1432cf5bcd6e4843e576b641b51e

Observation 9436f225-9398-40f2-94c4-11509cc166cf · outbound

This paper cites V oxpopuli: A large- scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR V oxpopuli: A large- scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:7a8de10d143783bf361019ee803d4cbbe19ce6463d87f59ad7792d6173d993cc

Observation 3d0a7a76-1ad0-4bb1-a5ce-62dfefebae22 · outbound

This paper cites Lib- rispeech: An asr corpus based on public domain audio books,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Lib- rispeech: An asr corpus based on public domain audio books,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:87c552f86aa732d490190e283af1383559208df7188340b3bd57729209551040

Observation 3cdd2d12-ce2a-4035-9784-14c100d47df8 · outbound

This paper cites Gigaspeech: An evolving, multi-domain asr cor- pus with 10,000 hours of transcribed audio,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Gigaspeech: An evolving, multi-domain asr cor- pus with 10,000 hours of transcribed audio,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:ce6b2df3eeb7e5471f2067d9a913fc2bd6bf943c875026911fffe080e3bfb4f0

Observation b47761c7-f254-4d3a-9afa-934c9feee09d · outbound

This paper cites The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:c4074698cfeb66aa7d132f6164687d036e2653ced220cbe9d40530f5aa81438f

Observation 0674b929-6ebc-437d-8d59-cddda19d9584 · outbound

This paper cites Ascend: A spontaneous chinese-english dataset for code-switching in multi-turn conversation,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Ascend: A spontaneous chinese-english dataset for code-switching in multi-turn conversation,

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b3478a3f6e86ec2226a58420fb3bf27b04201c0766cac58f96cb32c70611c8a2

Observation 2527ec4f-f60a-48e0-963b-a9979f609f1b · outbound

This paper cites The ami meeting corpus: A pre- announcement,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR The ami meeting corpus: A pre- announcement,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:b081e46709e4a9bbbeb08d49c713b52872631b5d98d00ab229a57a58cfc0a8e9

Observation ee17691e-041d-489d-8e61-c02e83e11e19 · outbound

This paper cites Ted-lium: an auto- matic speech recognition dedicated corpus,.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Ted-lium: an auto- matic speech recognition dedicated corpus,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:958ed916bf20fa356dd3b1f528644217241cb095be27bbb04700bd5d2e068816

Pith citing papers

Observation b38bedaa-8812-49b1-9758-d60a44115457 · inbound

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR cites this paper.

Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-11T09:35:44.381743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T09:35:44.381743Z digest=sha256:a47524ec368c96f7ac9b0e4019f8ad3dfb1e5660630e42b7422fe47c61d94e62