Pith. sign in

Paper Citation Record · LEDGER

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation

As of 9 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2508.19856.

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

pith.paper-citation-record.v1
2508.19856 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:27:29.314822Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

25 of 25 outbound references displayed

  • verified exact1
  • verified fuzzy13
  • unresolved11
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 19be52c5-edd4-4957-a74b-d77d3a5855b8 · outbound

This paper cites TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer- based ASR,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer- based ASR,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.542485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.238182Z digest=sha256:418150fbf9b6c9a917acfdaf57c60a2b0b5034e78616c95c3335a4977ae85f60

Observation c5fe06b9-8a39-4da4-bcdc-5842d4966c2a · outbound

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

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Robust speech recognition via large-scale weak super- vision,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.241726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.241726Z digest=sha256:be0da785e0adc4700016caf5042807ab83e88e7bce7a39bc050a3f24686b15f0

Observation e5e98868-9c31-46aa-b1bb-f8e6888612ba · outbound

This paper cites End-to-end Named Entity Recognition from English Speech.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation End-to-end Named Entity Recognition from English Speech

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.244821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.244821Z digest=sha256:a334f84bac3b3d3475a542987608c90a9501e097c459cab6cfaeb3a6b30e7269

Observation 2913fbe3-29e3-4b03-97a0-b4cb9991c2bb · outbound

This paper cites SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-08-05T15:27:29.405180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.248232Z digest=sha256:52c77388531e92987d4617f15abdbda0d536a5e4e12f1717bb5bb06f8457d99b

Observation 9a58c572-1553-4fba-a7d1-9f22e8abdab2 · outbound

This paper cites SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.251796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.251796Z digest=sha256:1739de11ee2ad6a20302711084cbf50773acfc7a1c5e9b0819240dac5707819d

Observation 612daea9-4d17-4202-b167-cc2aa4c16239 · outbound

This paper cites Joint Speech Recognition and Speaker Diarization via Sequence Transduction.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Joint Speech Recognition and Speaker Diarization via Sequence Transduction

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.255358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.255358Z digest=sha256:c1886810f5699ec861e8ed2cb1387af226ef7143f5d67f216c8f6ab8e1cf06e5

Observation d02fc8cb-035e-4fce-b5ce-00e188161e2e · outbound

This paper cites Turn-to-diarize: Online speaker diarization constrained by transformer transducer speaker turn detection,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Turn-to-diarize: Online speaker diarization constrained by transformer transducer speaker turn detection,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.527741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.259382Z digest=sha256:2df5cebc6d162decd8354891606a53c05b9d031cd757ca1fddcf3eebbe524bc1

Observation e5cc6984-ed1b-4866-98be-e9438c816ac1 · outbound

This paper cites Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.518338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.262277Z digest=sha256:d9515d1b229a12ff1e17500a7123b657fb938959d646a76477b0f5a848950f75

Observation 0943d445-279d-4ed3-bd5a-4d56f65597ec · outbound

This paper cites A survey on deep learning for named entity recognition,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation A survey on deep learning for named entity recognition,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.265248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.265248Z digest=sha256:77a0d4936ae7bc5e937fa8e3550b969fd2a2555bad3fbd6f1fd155c05fa9dd72

Observation 76607051-eca9-4ef1-ad70-d28b398e2007 · outbound

This paper cites Topic-oriented spoken dialogue summarization for customer service with saliency-aware topic modeling,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Topic-oriented spoken dialogue summarization for customer service with saliency-aware topic modeling,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.504678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.269033Z digest=sha256:a0bc898f1b2ad0c79211125ead3a9cd436ebcdbd586d8a172a2329924297a1ed

Observation faee5e29-0b8c-473a-9ecc-d2daaeadd33e · outbound

This paper cites Topic-aware multi-turn dialogue mod- eling,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Topic-aware multi-turn dialogue mod- eling,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.495129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.271930Z digest=sha256:a4d0fbf67ef2da5f9b8fc6f61f6fe65b4dfa700d1003b7bfa44733888118c837

Observation 1a112a42-4ff3-4d5d-bf2d-bc3c8e643719 · outbound

This paper cites Multilingual and Fully Non- Autoregressive ASR with Large Language Model Fusion: A Compre- hensive Study,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Multilingual and Fully Non- Autoregressive ASR with Large Language Model Fusion: A Compre- hensive Study,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.486317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.274941Z digest=sha256:8b16eab31f627e46b6d6ff3318e557b2d61f5e85c27120bebee15549be919da9

Observation 272b28aa-34bb-4d5e-8d04-7a8b3cfb568e · outbound

This paper cites Generative Speech Recognition Error Correction With Large Language Models and Task-Activating Prompting,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Generative Speech Recognition Error Correction With Large Language Models and Task-Activating Prompting,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.477689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.277914Z digest=sha256:49d596172a95b9826c940a608a5ab7e898388028f9a34beb87da273eeeca19ba

Observation 38f2f1b3-3766-4a55-a261-a2edd83ae08c · outbound

This paper cites An Embarrassingly Simple Approach for LLM with Strong ASR Capacity.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.280697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.280697Z digest=sha256:72f5b1e988df1a9ed37d7310ecb97d10529d1803b2e826ac8cebd6f855db248c

Observation f54078c4-3e0f-4f78-99d6-2b2fa9376b3c · outbound

This paper cites SpeechVerse: A Large-scale Generalizable Audio Language Model.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation SpeechVerse: A Large-scale Generalizable Audio Language Model

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.283691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.283691Z digest=sha256:1079187bd1a803f725046c7dd7714a0946826aa8c314541ceae652db7f469d30

Observation 6167e64a-8cc2-4515-809e-2f20760abb63 · outbound

This paper cites Performance Evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Performance Evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.469029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.287775Z digest=sha256:c0cbe8bab234cc3b256c082b3e0f70e474d72654cd9655346edf95e3464c4a1a

Observation 54ff0969-699f-43a0-855a-04dfffd1db8d · outbound

This paper cites XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.459470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.290451Z digest=sha256:0ebe3b0e7c23706a8b71d5a92c406856b2244ee6956ec5cfd5b81d11f7096c39

Observation 46789ff2-3e78-473a-a93e-122ba22b07db · outbound

This paper cites PromptASR for Contextualized ASR with Controllable Style,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation PromptASR for Contextualized ASR with Controllable Style,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.450753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.293016Z digest=sha256:04280116e1dfd87d2217bf936e1cce40dd8ceeeae8903f570a01185b95037805

Observation e60ef4a4-5fd5-45c4-841d-f725e87a5e98 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Prefix-Tuning: Optimizing Continuous Prompts for Generation,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.441024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.295718Z digest=sha256:23fb7f30e387190a33d8968d0335dd5d015bbc378d82bcc6d5efa4ee68405cce

Observation bdba9e19-1253-4ff5-b5f6-95e1e8b71720 · outbound

This paper cites GPT Understands, Too.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation GPT Understands, Too

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.299358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.299358Z digest=sha256:9d72f76f18edd2123ee4feef0ce22daa80c5bcf1053ef924b48a96f9576c97e2

Observation 61a49de5-a433-46b5-96b5-a965391d82f3 · outbound

This paper cites Pruned RNN-T for fast, memory-efficient ASR training.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Pruned RNN-T for fast, memory-efficient ASR training

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.302393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.302393Z digest=sha256:af7a2c585d7d8145a8da7ff5de426cf5c68548250b8e727b9a5469c32d4a85e6

Observation 4d132999-bbc4-49b9-9714-7f542ed2407f · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Sequence Transduction with Recurrent Neural Networks

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.306041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.306041Z digest=sha256:03d855141d1af71d2c224349c40f01b2bf3372faea66e9ac98da863819277c20

Observation 8830ce8b-09bc-4675-af92-97d446d65ef9 · outbound

This paper cites Unsupervised Cross-lingual Representation Learning for Speech Recognition.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Unsupervised Cross-lingual Representation Learning for Speech Recognition

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-05T15:27:29.308951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:27:29.308951Z digest=sha256:544d4a096c9a6d25e90bb54ddd513df4959c6d59da58f487a1d11e16c1b94477

Observation d1f216fd-dc2f-4b56-a5fb-1d66ea50a6cc · outbound

This paper cites On two ways to use determi- nantal point processes for monte carlo integration,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation On two ways to use determi- nantal point processes for monte carlo integration,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.431332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.311959Z digest=sha256:4f27ececc160fcc0a5038d0a94f745b4d70ab3e3b0b72d568d255e0ba3baf615

Observation 151101ab-d845-4c47-814d-d482c4b3494a · outbound

This paper cites Common V oice: A Massively-Multilingual Speech Corpus,.

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation Common V oice: A Massively-Multilingual Speech Corpus,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T15:27:29.422651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-05T15:27:29.314822Z digest=sha256:2bbbf2fc82f9149d25a48730a6053725e37825b5c8fb110b4e68733ac7c58f3e

Pith citing papers

No inbound Pith citation observations are available.