Paper Citation Record · LEDGER

ChipChat: Low-Latency Cascaded Conversational Agent in MLX

As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2509.00078.

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

pith.paper-citation-record.v1
2509.00078 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:52:44.063178Z

measured 31 of 31 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 2026-06-27T05:37:17.684884Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:28:39.173248Z

Reference resolution

30 of 30 outbound references displayed

verified exact1
verified fuzzy12
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 210b6a31-f6b4-4795-a824-d106484f97b9 · outbound

This paper cites Challenges for spoken dialogue systems,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Challenges for spoken dialogue systems,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.414455Z

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 23a36ea7-ee72-4e24-9a47-3ae69bfe782c · outbound

This paper cites Audiogpt: understanding and generating speech, music, sound, and talking head,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Audiogpt: understanding and generating speech, music, sound, and talking head,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.405739Z

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 68cec5fa-6e82-430a-9de6-d6b07383d68e · outbound

This paper cites FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:43.983527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77452af-1d4c-488c-a6c1-1289c8895fc1 · outbound

This paper cites Spirit-lm: Interleaved spoken and written language model,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Spirit-lm: Interleaved spoken and written language model,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:43.986720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c06824-02bd-471a-a036-1b51426eb800 · outbound

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

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Speechgpt: Empowering large language models with intrinsic cross- modal conversational abilities,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.391397Z

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 475e38b1-d61e-44eb-856b-508b5a88f2c5 · outbound

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

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Salmonn: Towards generic hearing abilities for large language models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.381935Z

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 02ca8321-78ec-4eb2-b703-385c09149a7c · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Moshi: a speech-text foundation model for real-time dialogue

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:43.995448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc1e401d-6272-4516-afe5-6481c35deecb · outbound

This paper cites LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:43.998471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8362019c-aecb-4e9d-b76c-9df83d3e9899 · outbound

This paper cites Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.001757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad84be4-165c-46f6-8296-91c3874ee16c · outbound

This paper cites Qwen2.5-Omni Technical Report.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Qwen2.5-Omni Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.004784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f744dbb-9fdf-44a8-9b65-209172234df5 · outbound

This paper cites WavChat: A Survey of Spoken Dialogue Models.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX WavChat: A Survey of Spoken Dialogue Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.007778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6a5060d-d085-4918-baeb-8d7d1e5fdb24 · outbound

This paper cites GPT-4o System Card.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX GPT-4o System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.010758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75d50dca-13ca-4fdc-8b39-9466ed8ef06f · outbound

This paper cites Text-to-speech latency benchmark,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Text-to-speech latency benchmark,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.373389Z

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 95803793-cf9b-4a5f-b7a4-302fa30345f3 · outbound

This paper cites Espnet-sds: Unified toolkit and demo for spoken dialogue systems,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Espnet-sds: Unified toolkit and demo for spoken dialogue systems,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.365354Z

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 6a031a1b-4cb6-44ca-b5bc-59d91c8d13ae · outbound

This paper cites VoiceBench: Benchmarking LLM-Based Voice Assistants.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX VoiceBench: Benchmarking LLM-Based Voice Assistants

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.018833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 845e1fa3-fa9e-45d5-984e-0a3e97857dd9 · outbound

This paper cites Mmau: A massive multi- task audio understanding and reasoning benchmark,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Mmau: A massive multi- task audio understanding and reasoning benchmark,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.355896Z

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 f7cb344a-b86a-4438-9f0e-98ab1e06fbff · outbound

This paper cites Talking turns: Benchmarking audio foundation models on turn-taking dynamics,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Talking turns: Benchmarking audio foundation models on turn-taking dynamics,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.347241Z

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 3717c928-7578-4cd5-aba3-c9a697f47d54 · outbound

This paper cites Discrete audio tokens: More than a survey!.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Discrete audio tokens: More than a survey!

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.028245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff7c396-6c60-4f2c-a589-5d1972445af7 · outbound

This paper cites MLX: Efficient and flexible machine learning on apple silicon,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX MLX: Efficient and flexible machine learning on apple silicon,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.031148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77143eb6-39a0-4c0c-af04-8a4eb9fb6809 · outbound

This paper cites Rabbitmq documentation,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Rabbitmq documentation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.331904Z

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 3e6149bd-5727-489d-a361-dd1a51c98d25 · outbound

This paper cites Omni-router: Sharing routing decisions in sparse mixture-of-experts for speech recognition,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Omni-router: Sharing routing decisions in sparse mixture-of-experts for speech recognition,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.036924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9503a6-b389-4f35-abc9-e6634bf64631 · outbound

This paper cites Connectionist temporal classification,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Connectionist temporal classification,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.323097Z

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 3f767078-70cd-43ff-af5f-56b3f532caa0 · outbound

This paper cites Speaker- ipl: Unsupervised learning of speaker characteristics with i-vector based pseudo-labels,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Speaker- ipl: Unsupervised learning of speaker characteristics with i-vector based pseudo-labels,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.314413Z

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 d15b2a77-7753-4446-8d77-b971816f4a01 · outbound

This paper cites SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:52:44.118273Z

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 ef2ca495-4485-4c7b-a800-045cf749afb6 · outbound

This paper cites Mixtral of Experts.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Mixtral of Experts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.047819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44973b3-acaa-49c9-a5d4-0f2df3031107 · outbound

This paper cites an unresolved cited work.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:52:44.305333Z

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 5fea5dc5-c540-4237-bc1d-d1f003ccf490 · outbound

This paper cites SpeakStream: Streaming Text-to-Speech with Interleaved Data.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX SpeakStream: Streaming Text-to-Speech with Interleaved Data

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.054140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f4de98-71b0-488c-8cb7-8cc9426eef7a · outbound

This paper cites dMel: Speech Tokenization made Simple.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX dMel: Speech Tokenization made Simple

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.057119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f79f85e-e15e-4b00-b736-f1b9c1e1a3ae · outbound

This paper cites Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:44.060088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 262168fa-c2c7-4a8e-b12c-1d2c7320b5f3 · outbound

This paper cites Kyutai unmute,.

ChipChat: Low-Latency Cascaded Conversational Agent in MLX Kyutai unmute,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:52:44.295856Z

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 82ce1eb1-839d-48e2-84ac-3cd5c3e16217 · inbound

Endpoint Anticipation for Low-Latency Spoken Dialogue cites this paper.

Endpoint Anticipation for Low-Latency Spoken Dialogue ChipChat: Low-Latency Cascaded Conversational Agent in MLX

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-21T01:20:36.421604Z

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.