Paper Citation Record · LEDGER

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 2 inbound Pith citation observations for arXiv:2506.14445.

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

pith.paper-citation-record.v1
2506.14445 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:23:18.773662Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:23:15.642048Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T08:13:15.097149Z

Reference resolution

35 of 35 outbound references displayed

verified exact3
verified fuzzy13
unresolved18
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 92d2b08f-0ae8-4e2a-a849-14f74b4de845 · outbound

This paper cites Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:15.642048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d7d56aa-8fac-4490-b5b9-b7fe1844e710 · outbound

This paper cites an unresolved cited work.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:23:19.872287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6de713e2-bfdf-48a2-bedc-8b0e509dd27e · outbound

This paper cites an unresolved cited work.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:23:19.849966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a587ad28-d860-45e0-a8c9-83d37b4d677f · outbound

This paper cites (1) In thetrainingstage, by unifying multimodal representations into the same embedding space, Vela improves multimodal embeddings usingonly contrastive learning on text pairs.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval (1) In thetrainingstage, by unifying multimodal representations into the same embedding space, Vela improves multimodal embeddings usingonly contrastive learning on text pairs

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.827814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 36072b47-8846-45f2-b5f4-cc95fe952309 · outbound

This paper cites in one word.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval in one word

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.790304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cbb6639b-791e-494a-bc7f-299299a3f86e · outbound

This paper cites Datasets For the training data, we use NLI [18], which contains approx- imately 273k sentence pairs.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Datasets For the training data, we use NLI [18], which contains approx- imately 273k sentence pairs

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.766028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 133ae229-6bb5-4a42-b85a-323034cf5a79 · outbound

This paper cites in one word.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval in one word

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T00:23:19.727739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 58f87e0e-9792-458c-b02e-1d7cd375e1a1 · outbound

This paper cites an unresolved cited work.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:23:19.688912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6076796a-ac42-411b-95aa-81896bc425c8 · outbound

This paper cites Pioneer” and “Lead- ing Goose.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Pioneer” and “Lead- ing Goose

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.659669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 56e5fd14-df51-4958-83a5-9fbf72c1ac10 · outbound

This paper cites Natural Language Supervision for General-Purpose Audio Representations.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Natural Language Supervision for General-Purpose Audio Representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:16.501373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8861ca3d-b434-43fd-9a37-004cdc0e5959 · outbound

This paper cites Large-scale contrastive language-audio pretrain- ing with feature fusion and keyword-to-caption augmentation,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Large-scale contrastive language-audio pretrain- ing with feature fusion and keyword-to-caption augmentation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.620030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 63575974-ea51-4c1e-b2d0-1f91f3a867ce · outbound

This paper cites Wavcaps: A chatgpt-assisted weakly- labelled audio captioning dataset for audio-language multimodal research,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Wavcaps: A chatgpt-assisted weakly- labelled audio captioning dataset for audio-language multimodal research,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.588446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d4795b6c-b14e-4649-ba61-c559c05a85d5 · outbound

This paper cites AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:23:19.253506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e0db3dfc-e0cf-46ae-90ce-2fd5d84c5395 · outbound

This paper cites Auto-acd: A large-scale dataset for audio-language representation learning,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Auto-acd: A large-scale dataset for audio-language representation learning,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.566004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ae836ea5-c0ba-4d47-ae03-83dd62965443 · outbound

This paper cites Grounding language models for visual entity recog- nition,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Grounding language models for visual entity recog- nition,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.540632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 44f06b76-705b-4f28-87f0-59fca8532628 · outbound

This paper cites Improving clip training with language rewrites,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Improving clip training with language rewrites,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.516980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 170d5e1b-d45d-4bd5-b171-84c2eb50ed2b · outbound

This paper cites MATE: Meet At The Embedding -- Connecting Images with Long Texts.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval MATE: Meet At The Embedding -- Connecting Images with Long Texts

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:23:19.214601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6490dd53-93a4-4064-b166-ea18c5020fc0 · outbound

This paper cites MetaMorph: Multimodal Understanding and Generation via Instruction Tuning.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.301298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55daae4-eb1e-4855-b42d-edbaa6ebe0d3 · outbound

This paper cites It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.368291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01cbf8ab-f77c-469a-b7aa-740d2e687b6a · outbound

This paper cites E5-V: Universal Embeddings with Multimodal Large Language Models.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval E5-V: Universal Embeddings with Multimodal Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.464515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b4ba41e-5177-4dae-9255-b868ae0bb404 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Learning transferable visual models from natural language supervision,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.617017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f15b79a-3f1c-400c-9acc-0ca07c27cef8 · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal con- trastive representation learning,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Mind the gap: Understanding the modality gap in multi-modal con- trastive representation learning,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.475811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b30d69b7-e188-43b7-a9ef-617c3899c70a · outbound

This paper cites DefSent: Sentence Embeddings using Definition Sentences.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval DefSent: Sentence Embeddings using Definition Sentences

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:23:19.089736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9bcfe10a-71cd-4a1b-ad24-1104ed40c164 · outbound

This paper cites GPT-4 Technical Report.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval GPT-4 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.933544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2047d02-e3f2-4446-81cb-9199c939b801 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Gemini: A Family of Highly Capable Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.989473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8427953-163d-46a7-909c-1a0335f0905f · outbound

This paper cites Breaking the length barrier: Llm-enhanced ctr pre- diction in long textual user behaviors,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Breaking the length barrier: Llm-enhanced ctr pre- diction in long textual user behaviors,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.450427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9398214e-f5a2-49e6-b4a4-c6df3d59032e · outbound

This paper cites SimCSE: Simple Contrastive Learning of Sentence Embeddings.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval SimCSE: Simple Contrastive Learning of Sentence Embeddings

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.247673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a539ff0-0b44-4f33-989c-e56e5cffcd67 · outbound

This paper cites Clotho: An audio cap- tioning dataset,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Clotho: An audio cap- tioning dataset,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.346676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380a3921-f767-4491-8122-9e123b36e99a · outbound

This paper cites Fsd50k: an open dataset of human-labeled sound events,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Fsd50k: an open dataset of human-labeled sound events,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.465156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d21cce4-bdcb-4393-9b1c-4332cefd3df7 · outbound

This paper cites Audiocaps: Generat- ing captions for audios in the wild,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Audiocaps: Generat- ing captions for audios in the wild,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.394524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 71e4145e-c544-4d9b-8c55-318401a0c01d · outbound

This paper cites Qwen2-Audio Technical Report.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Qwen2-Audio Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.677734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825f3886-9ccf-4810-a33d-33846519efae · outbound

This paper cites Qwen Technical Report.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Qwen Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.744126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf11e42-7a0b-4500-8708-691084e9f4e8 · outbound

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

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Robust speech recognition via large-scale weak supervision,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.754048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb102d5b-958d-461e-b25e-492a2fa22f31 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms,.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Qlora: Efficient finetuning of quantized llms,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.344994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a298787-e643-4b26-9dbb-44ad3a01906d · outbound

This paper cites From Matching to Generation: A Survey on Generative Information Retrieval.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval From Matching to Generation: A Survey on Generative Information Retrieval

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.773662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 92d2b08f-0ae8-4e2a-a849-14f74b4de845 · inbound