Paper Citation Record · LEDGER

Synthetic Document Question Answering in Hungarian

As of 13 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 2 inbound Pith citation observations for arXiv:2505.23008.

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

pith.paper-citation-record.v1
2505.23008 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:59:27.623302Z

measured 48 of 48 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T09:17:43.418144Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T21:48:58.926645Z

Reference resolution

46 of 46 outbound references displayed

verified exact0
verified fuzzy34
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 34f28efe-e7fa-49fb-838b-a515d442af40 · outbound

This paper cites Mistral small 3.1.https : / / mistral.ai/news/mistral-small-3-1,.

Synthetic Document Question Answering in Hungarian Mistral small 3.1.https : / / mistral.ai/news/mistral-small-3-1,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:36.414761Z

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 6fb94bb8-91a9-49cd-8fb7-e9743acd75c5 · outbound

This paper cites Artifex Software.

Synthetic Document Question Answering in Hungarian Artifex Software

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:36.197136Z

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 e84698f3-cceb-487b-9b75-5ba67a01885f · outbound

This paper cites Qwen2.5-VL Technical Report.

Synthetic Document Question Answering in Hungarian Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:24.420751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14161ecd-3705-426a-958d-d25c69fd7919 · outbound

This paper cites Enriching word vectors with subword information, 2017.

Synthetic Document Question Answering in Hungarian Enriching word vectors with subword information, 2017

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:36.048905Z

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 9462729c-b5b2-4003-a4b4-84de13285631 · outbound

This paper cites MaXM: Towards Multilingual Visual Question Answering.

Synthetic Document Question Answering in Hungarian MaXM: Towards Multilingual Visual Question Answering

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:24.610695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f5e6e4-7b4e-42e3-81e1-9c05c4c47877 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Synthetic Document Question Answering in Hungarian Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:24.706741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 493b48e2-acb7-4a34-afc8-f0d2a7a0b26f · outbound

This paper cites The warc format 1.1.https : / / iipc.

Synthetic Document Question Answering in Hungarian The warc format 1.1.https : / / iipc

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:35.837874Z

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 f6e42df9-dd6f-4e80-994e-5963e0eccae7 · outbound

This paper cites Common crawl - open repository of web crawl data.https://commoncrawl.

Synthetic Document Question Answering in Hungarian Common crawl - open repository of web crawl data.https://commoncrawl

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:35.615671Z

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 3994c93f-b1eb-44df-b05c-02bf8b4730b3 · outbound

This paper cites langdetect: Port of google’s language-detection library to python, 2018.

Synthetic Document Question Answering in Hungarian langdetect: Port of google’s language-detection library to python, 2018

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:35.402529Z

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 87fc1629-ea78-448b-87e9-cb1e49938def · outbound

This paper cites Exams-v: A multi-discipline multilingual multimodal exam benchmark for eval- uating vision language models, 2024.

Synthetic Document Question Answering in Hungarian Exams-v: A multi-discipline multilingual multimodal exam benchmark for eval- uating vision language models, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:35.177579Z

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 2d0b0b18-a30c-4148-8e29-8c9c162dabe3 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering, 2017.

Synthetic Document Question Answering in Hungarian Making the v in vqa matter: Elevating the role of image understanding in visual question answering, 2017

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:34.991208Z

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 c81f4910-8d3f-40b4-99fc-49fecf467cb1 · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:59:34.705856Z

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 42f4108a-e107-4517-9df5-6f8afeb86606 · outbound

This paper cites pytesser- act: A python wrapper for google’s tesseract-ocr.

Synthetic Document Question Answering in Hungarian pytesser- act: A python wrapper for google’s tesseract-ocr

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:34.556252Z

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 875af6df-6e0d-47d9-b1ab-89cac20632f2 · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

Synthetic Document Question Answering in Hungarian Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:34.394740Z

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 e7e31bb7-5154-4708-9956-23042b1b8895 · outbound

This paper cites Llama3-gaja-hindi-8b-v0.1,.

Synthetic Document Question Answering in Hungarian Llama3-gaja-hindi-8b-v0.1,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:34.175332Z

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 1e6e45b5-0aea-4765-ab58-82950e97442a · outbound

This paper cites Building and better understand- ing vision-language models: insights and future di- rections, 2024.

Synthetic Document Question Answering in Hungarian Building and better understand- ing vision-language models: insights and future di- rections, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:33.983613Z

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 b1a80324-69e6-451c-b39e-bef591453de4 · outbound

This paper cites What matters when building vision-language models?, 2024.

Synthetic Document Question Answering in Hungarian What matters when building vision-language models?, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:33.824497Z

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 9e0431e0-ee02-432a-9765-eb7c9f141bda · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, 2024.

Synthetic Document Question Answering in Hungarian Llava-next: Improved reasoning, ocr, and world knowledge, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:33.652528Z

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 9e987cbe-aab5-4a16-b2a6-78c32b3b1be2 · outbound

This paper cites Anwer, Tim Baldwin, Michael Felsberg, and Fahad S.

Synthetic Document Question Answering in Hungarian Anwer, Tim Baldwin, Michael Felsberg, and Fahad S

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:33.479010Z

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 c153eccc-5743-408f-941a-2db496a10764 · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:25.681665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76ac9f72-9fb3-4591-9737-7693ced687e5 · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:59:33.192400Z

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 1d903287-defd-46c8-b5b5-b8873a81dfec · outbound

This paper cites CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages.

Synthetic Document Question Answering in Hungarian CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:25.835410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c979da35-beeb-4e79-8297-fbd9317e5393 · outbound

This paper cites JDocQA: Japanese document question answering dataset for generative language models.

Synthetic Document Question Answering in Hungarian JDocQA: Japanese document question answering dataset for generative language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:32.909011Z

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 37ea6d1f-f8ad-41e8-830d-ca7edf8f75f6 · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:59:32.622011Z

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 42ad3ccf-10b9-4150-8621-1b7b2814fc13 · outbound

This paper cites Qwen2.5 technical report, 2025.

Synthetic Document Question Answering in Hungarian Qwen2.5 technical report, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:32.360434Z

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 b096422b-b188-4122-a9b0-0aa4b7fa10b8 · outbound

This paper cites Learning transferable visual models from natural language supervision, 2021.

Synthetic Document Question Answering in Hungarian Learning transferable visual models from natural language supervision, 2021

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:26.073516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22a563f-fc35-4346-a427-70b4095092cf · outbound

This paper cites multilingual.

Synthetic Document Question Answering in Hungarian multilingual

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:32.076932Z

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 e78dd8d0-622b-47af-aded-0f9c4e533c27 · outbound

This paper cites Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset.

Synthetic Document Question Answering in Hungarian Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:26.206216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20908dc2-f813-437d-9e49-23a48f79cd40 · outbound

This paper cites Nllb-clip – train performant multilingual image retrieval model on a budget,.

Synthetic Document Question Answering in Hungarian Nllb-clip – train performant multilingual image retrieval model on a budget,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:31.807559Z

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 29cc413c-0f13-447a-88df-5eeeb390f7ee · outbound

This paper cites Llama3.1-8b-chinese-chat,.

Synthetic Document Question Answering in Hungarian Llama3.1-8b-chinese-chat,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:31.573643Z

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 60d17dbb-7116-4b0c-84a4-0840c217c821 · outbound

This paper cites Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt.

Synthetic Document Question Answering in Hungarian Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:31.407238Z

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 90b4bff7-61ce-4a21-95e2-7edeae2c08bd · outbound

This paper cites mt5: A massively mul- tilingual pre-trained text-to-text transformer, 2021.

Synthetic Document Question Answering in Hungarian mt5: A massively mul- tilingual pre-trained text-to-text transformer, 2021

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:31.187525Z

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 ef8f2037-304e-4450-acf1-5edc590f140f · outbound

This paper cites Pangea: A fully open multilingual multimodal llm for 39 languages, 2024.

Synthetic Document Question Answering in Hungarian Pangea: A fully open multilingual multimodal llm for 39 languages, 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:30.971343Z

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 c983b055-b71c-4a84-9b82-afe002da8604 · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Synthetic Document Question Answering in Hungarian Xing, Hao Zhang, Joseph E

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:30.753640Z

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 f400be24-c05a-411b-bcf8-8cd89b8ef2bd · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models, 2024.

Synthetic Document Question Answering in Hungarian Llamafactory: Unified efficient fine-tuning of 100+ language models, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:30.546249Z

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 ecf03d7c-1ac8-4f43-95f4-167d3e61c1ed · outbound

This paper cites DocVQA DocVQA [20] is the seminal dataset and bench- mark on the Document Visual Question Answer- ing task.

Synthetic Document Question Answering in Hungarian DocVQA DocVQA [20] is the seminal dataset and bench- mark on the Document Visual Question Answer- ing task

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:30.281779Z

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 78ce555a-a072-4228-8433-e67439410c90 · outbound

This paper cites Number of synthetic QAs filtered out for each of the filters applied Tab.

Synthetic Document Question Answering in Hungarian Number of synthetic QAs filtered out for each of the filters applied Tab

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:30.074278Z

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 399e0474-9802-41ab-871b-f8641eab1791 · outbound

This paper cites While ANLS serves as a fine metric for English DocVQA, in early exper- iments with HuDocVQA-manual that it often went 1 against human judgment on model response cor- rectness.

Synthetic Document Question Answering in Hungarian While ANLS serves as a fine metric for English DocVQA, in early exper- iments with HuDocVQA-manual that it often went 1 against human judgment on model response cor- rectness

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:29.884608Z

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 2c951dff-e660-4787-9eb0-2b50e745d9a5 · outbound

This paper cites 6 shows 3 documents from HuDocVQA- manual and their corresponding human-annotated questions and answers.

Synthetic Document Question Answering in Hungarian 6 shows 3 documents from HuDocVQA- manual and their corresponding human-annotated questions and answers

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:29.622446Z

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 90b188e6-503b-4347-aea5-5fe20da7667b · outbound

This paper cites Kérdés:.

Synthetic Document Question Answering in Hungarian Kérdés:

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:29.411948Z

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 38492a35-47ee-471d-9a2c-1f2f1ba99b71 · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:59:29.181579Z

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 6012c8ec-eb13-4fd7-b946-959c6285d3b2 · outbound

This paper cites 8 outlines all datasets comprising our SFT mixture in Tab.

Synthetic Document Question Answering in Hungarian 8 outlines all datasets comprising our SFT mixture in Tab

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:28.985805Z

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 4cae1a4d-67e6-40e3-8041-cc159bfaa503 · outbound

This paper cites HuDocVQA Filtering Ablation In Tab.

Synthetic Document Question Answering in Hungarian HuDocVQA Filtering Ablation In Tab

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:28.813883Z

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 9aad9875-a8a2-4f78-9f54-22af07021546 · outbound

This paper cites 10 compares the accuracy of the final check- point versus a merged checkpoint for each training experiment on Sec.

Synthetic Document Question Answering in Hungarian 10 compares the accuracy of the final check- point versus a merged checkpoint for each training experiment on Sec

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:28.490539Z

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 720eca03-41e6-4d28-90c6-ac978932edae · outbound

This paper cites an unresolved cited work.

Synthetic Document Question Answering in Hungarian Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:59:28.236171Z

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 8c67bd9b-11be-436c-9e46-95563551de34 · outbound

This paper cites 05 of these regulations.

Synthetic Document Question Answering in Hungarian 05 of these regulations

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:59:27.948652Z

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 bf8930d1-5899-4765-8374-6a8b7a534ad1 · inbound

LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration cites this paper.

LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration Synthetic Document Question Answering in Hungarian

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:48:58.928341Z

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 54719c90-447a-40ba-a687-3ad3f9686278 · inbound

LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration cites this paper.

LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration Synthetic Document Question Answering in Hungarian

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T09:17:43.418144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.