Paper Citation Record · LEDGER

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation

As of 5 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.15299.

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

pith.paper-citation-record.v1
2607.15299 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T08:23:14.354745Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

22 of 22 outbound references displayed

verified exact0
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8d6f1a2f-4de4-4484-b97b-8c267e466609 · outbound

This paper cites Making the V in VQA matter: Elevating the role of image understanding in visual question answering,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Making the V in VQA matter: Elevating the role of image understanding in visual question answering,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.297079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7511da-4b47-4900-856e-b327a92142b8 · outbound

This paper cites OK- VQA: A visual question answering benchmark requiring external knowl- edge,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation OK- VQA: A visual question answering benchmark requiring external knowl- edge,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.387098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7589eeb-f542-4c20-acf5-6306847b39e7 · outbound

This paper cites A-OKVQA: A benchmark for visual question answering using world knowledge,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation A-OKVQA: A benchmark for visual question answering using world knowledge,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.539193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 070beb76-55d4-4868-8d81-0e8aaded7ad2 · outbound

This paper cites GQA: A new dataset for real-world visual reasoning and compositional question answering,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation GQA: A new dataset for real-world visual reasoning and compositional question answering,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.616648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b26718d-569d-431e-a5ec-70b24278b39f · outbound

This paper cites OCR- VQA: visual question answering by reading text in images,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation OCR- VQA: visual question answering by reading text in images,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.669130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dda5378-58d8-4dae-b809-4bae903e56da · outbound

This paper cites Textcaps: A dataset for image captioning with reading comprehension,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Textcaps: A dataset for image captioning with reading comprehension,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.749017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde9422d-61ac-439a-96db-62e1e6eab3ef · outbound

This paper cites Visual instruction tuning,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Visual instruction tuning,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.833347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed94dae2-9208-426f-8483-af98f01e7dcc · outbound

This paper cites Sharegpt,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Sharegpt,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.911774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1b76ce2-408b-4eff-a344-2e8c7338d282 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image anno- tations,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Visual genome: Connecting language and vision using crowdsourced dense image anno- tations,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:12.971059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02fa0fda-7c41-40b4-b63a-686b99b42b05 · outbound

This paper cites Generation and comprehension of unambiguous object descriptions,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Generation and comprehension of unambiguous object descriptions,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.053830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f12c14-d9fb-4f90-aa6b-c377820cccc9 · outbound

This paper cites Refer- itgame: Referring to objects in photographs of natural scenes,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Refer- itgame: Referring to objects in photographs of natural scenes,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.092521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1f453a-b2ce-486c-b88c-74f4262453e6 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.162780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f5d8d4c-677f-4598-94ac-0eb6dd580342 · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation MMBench: Is Your Multi-modal Model an All-around Player?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.248396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d0a9e9-c703-4375-8efc-8d5991930764 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.395817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74e29df-3210-4a02-bd52-f2f67d35b039 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Vizwiz grand challenge: Answering visual questions from blind people,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.524066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33885bec-54c8-416b-a3b1-db428c84249b · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answer- ing,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Learn to explain: Multimodal reasoning via thought chains for science question answer- ing,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.604750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19242688-f65a-4278-b718-2d4cd6f0e09a · outbound

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

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Lora: Low-rank adaptation of large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.704757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5469f98-fd0b-4730-9176-40afac55a812 · outbound

This paper cites Microsoft COCO: common objects in context,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Microsoft COCO: common objects in context,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.771956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57656ff4-27ec-42ad-8f40-1ffc53d41149 · outbound

This paper cites Modeling context in referring expressions,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Modeling context in referring expressions,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:13.916582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23af5645-73a3-4504-9f2a-af38d4cbbf08 · outbound

This paper cites Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:14.064741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3880485-2a00-40ba-b9e0-74d8a9587740 · outbound

This paper cites Visual spatial reasoning,.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation Visual spatial reasoning,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:14.194756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c43f9043-16e9-4b09-97ac-6a599b8aa2dd · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T08:23:14.354745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.