Pith. sign in

Paper Citation Record · LEDGER

Improving MLLM Historical Record Extraction with Test-Time Image

As of 14 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2509.09722.

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

pith.paper-citation-record.v1
2509.09722 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T21:01:35.003144Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

29 of 29 outbound references displayed

  • verified exact2
  • verified fuzzy20
  • unresolved3
  • parse uncertain0
  • malformed identifier4
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7d88f87b-fc42-4580-8963-5be758363305 · outbound

This paper cites Advancements and Challenges in Handwritten Text Recognition: A Comprehensive Survey,.

Improving MLLM Historical Record Extraction with Test-Time Image Advancements and Challenges in Handwritten Text Recognition: A Comprehensive Survey,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:38.581082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.477849Z digest=sha256:5ccb9257d3c266457ba1e380c79b95e9b5dff81a0a0f6af80abb42d84afbd683

Observation 043e0b3d-5ae7-4317-9206-ad0d51bbae32 · outbound

This paper cites Yang et al.,The Dawn of LMMs: Preliminary Ex- plorations with GPT-4V(ision), Oct.

Improving MLLM Historical Record Extraction with Test-Time Image Yang et al.,The Dawn of LMMs: Preliminary Ex- plorations with GPT-4V(ision), Oct

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:38.398856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.527130Z digest=sha256:2e9ccf13e026cece8459e43a03d8183de32c080fdf62b221c962310f5ab86964

Observation c4032cdc-d1c4-4ec6-a253-dd8c83537032 · outbound

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

Improving MLLM Historical Record Extraction with Test-Time Image Gemini: A Family of Highly Capable Multimodal Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T21:01:33.551218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:33.551218Z digest=sha256:7f0c18fd342708082d8fea2cac45060b02e9335d2207dd93d537963f0f9fb7e2

Observation cbbe1509-b2e6-4ce4-9110-c2d36eb4d834 · outbound

This paper cites Kim et al.,Early evidence of how LLMs out- perform traditional systems on OCR/HTR tasks for historical records, Jan.

Improving MLLM Historical Record Extraction with Test-Time Image Kim et al.,Early evidence of how LLMs out- perform traditional systems on OCR/HTR tasks for historical records, Jan

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:38.175021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.604119Z digest=sha256:ce95330c7fa35f3651c7d7a836001643e7a3e429b346efba453acff448a9ac68

Observation 46b4bcd8-55a3-4de7-9c2e-0034c309ca83 · outbound

This paper cites Confidence in the Rea- soning of Large Language Models,.

Improving MLLM Historical Record Extraction with Test-Time Image Confidence in the Rea- soning of Large Language Models,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:38.014445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.700269Z digest=sha256:68e72e00c999829778ba9be21f218afb130822cc10616fcc92372bfdb03014b5

Observation 64c781e7-29a5-4a1b-b785-596b755b99f0 · outbound

This paper cites A general method applicable to the search for similarities in the amino acid sequence of two proteins,.

Improving MLLM Historical Record Extraction with Test-Time Image A general method applicable to the search for similarities in the amino acid sequence of two proteins,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.883009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.725662Z digest=sha256:3fcbb3cf953675d615e86ec478b14ee4c2f39a48c5529061c4312d3a52a17378

Observation 01ef42f7-6683-475f-95ee-6e3b6b2e06cb · outbound

This paper cites Large language models for generative information extraction: A survey,.

Improving MLLM Historical Record Extraction with Test-Time Image Large language models for generative information extraction: A survey,

Reference 9

Resolution
malformed identifier
no resolver link, observed 2026-08-04T21:01:33.770762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:33.770762Z digest=sha256:d11e06dd23ae35f1f014b2f1a724f33b36e0ebef3485bb3e9387b41b908e9fd2

Observation afb55a80-f7e7-4c36-a32b-cb78bbe226e9 · outbound

This paper cites LayoutLM: Pre-training of Text and Layout for Document Image Understanding,.

Improving MLLM Historical Record Extraction with Test-Time Image LayoutLM: Pre-training of Text and Layout for Document Image Understanding,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T21:01:33.844671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:33.844671Z digest=sha256:2eeba1e0f7a45709c7a71fad18b683cd7010340dbeeb62b4d398e008d96fce4c

Observation 11a0e32b-f556-42d1-ae71-d9f541fb1363 · outbound

This paper cites OCR-Free Document Understand- ing Transformer,.

Improving MLLM Historical Record Extraction with Test-Time Image OCR-Free Document Understand- ing Transformer,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.750004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.897496Z digest=sha256:c10a679b48c97cc69738b4cbd5adfce72dec4602453798521da27b1c101cbf4c

Observation 6380a5b7-2ab0-4a77-b2c0-f0c359bfba03 · outbound

This paper cites End-to-End Document Recognition and Understanding with Dessurt,.

Improving MLLM Historical Record Extraction with Test-Time Image End-to-End Document Recognition and Understanding with Dessurt,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.561854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.926464Z digest=sha256:feb317413cbd7f6495462d0e916d27d573f3318c42595c46b3ecc098e37f974e

Observation 5e467c8f-1747-46e5-ac45-c81aeb1d1d85 · outbound

This paper cites Robustness of Struc- tured Data Extraction from In-plane Rotated Docu- ments using Multi-Modal Large Language Models (LLM),.

Improving MLLM Historical Record Extraction with Test-Time Image Robustness of Struc- tured Data Extraction from In-plane Rotated Docu- ments using Multi-Modal Large Language Models (LLM),

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.378793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:33.978567Z digest=sha256:0e62ab7c4cdcd1529b3efa41c06b89e1cb656a693269712fadd228e2c3d0a142

Observation c7b1059a-b308-4644-8d2c-063b02ab6236 · outbound

This paper cites Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Lan- guage Models Fine-Tuned with Human Feedback,.

Improving MLLM Historical Record Extraction with Test-Time Image Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Lan- guage Models Fine-Tuned with Human Feedback,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.194923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.031009Z digest=sha256:86e6b8982df974bdc54f38c97c05b3adf1d855150ad0179324779ad543a133a3

Observation b7ca4180-52b2-4836-af5c-1ec8392560a1 · outbound

This paper cites Can LLMs Express Their Uncer- tainty? An Empirical Evaluation of Confidence Elic- itation in LLMs,.

Improving MLLM Historical Record Extraction with Test-Time Image Can LLMs Express Their Uncer- tainty? An Empirical Evaluation of Confidence Elic- itation in LLMs,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:37.041011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.062033Z digest=sha256:d8f333475eb20a1638e12b4f9d3db3bebbab297d45137ffafa6af58053c98e4b

Observation 78d477b0-a382-442a-bac3-f107bf2d26d8 · outbound

This paper cites Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models.

Improving MLLM Historical Record Extraction with Test-Time Image Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models

Reference 17

Resolution
verified exact
local_arxiv, observed 2026-08-04T21:01:35.413549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.115666Z digest=sha256:7ce8b45ee7f9c0911769fe2b2d6f0f57e490aa80f4bff3731b6fbaa4c57e0016

Observation 39e0bab1-ccc4-411e-944f-f3f4269c2154 · outbound

This paper cites A post-processing system to yield reduced word error rates: Recognizer Output V oting Error Re- duction (ROVER),.

Improving MLLM Historical Record Extraction with Test-Time Image A post-processing system to yield reduced word error rates: Recognizer Output V oting Error Re- duction (ROVER),

Reference 18

Resolution
malformed identifier
no resolver link, observed 2026-08-04T21:01:34.176324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:34.176324Z digest=sha256:a57024e6b915cacb6a732ffbe31d743e9148fc868fec3383612ca299970a7aa6

Observation 87817408-50cc-4de4-a291-0e41b55bc55f · outbound

This paper cites Using Consensus Sequence V oting to Correct OCR Errors,.

Improving MLLM Historical Record Extraction with Test-Time Image Using Consensus Sequence V oting to Correct OCR Errors,

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-08-04T21:01:35.662594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.211582Z digest=sha256:91a1b98503f946293fd838607266f35bc49e9bcbb4c40e4d3ee880ad05d4a71a

Observation b6a4d6ea-be6a-4f00-aac9-c8a2afc1991b · outbound

This paper cites Hidden Markov model- based ensemble methods for offline handwritten text line recognition,.

Improving MLLM Historical Record Extraction with Test-Time Image Hidden Markov model- based ensemble methods for offline handwritten text line recognition,

Reference 20

Resolution
malformed identifier
doi_truncated, observed 2026-08-04T21:01:35.227084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.235445Z digest=sha256:8c8085f951777aedf3142c48a90dab883b106dfb5a20699042286002f608a744

Observation ac5983bd-ad79-4d98-a443-07c266a24b5c · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models,.

Improving MLLM Historical Record Extraction with Test-Time Image Self-Consistency Improves Chain of Thought Reasoning in Language Models,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.889095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.289537Z digest=sha256:da59e0a94bc0fd26b04b7c7f7f29e965a7347de231f13a1db4379a15024e4ceb

Observation 05fab63d-64ba-462c-97c0-1f86a1b04387 · outbound

This paper cites Benchmarking Multiple Large Language Models for Automated Clinical Trial Data Extraction in Ag- ing Research,.

Improving MLLM Historical Record Extraction with Test-Time Image Benchmarking Multiple Large Language Models for Automated Clinical Trial Data Extraction in Ag- ing Research,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.731292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.335695Z digest=sha256:a40e877248f26cfd04efdcc5fc9f8f953af2d3e12d9163438b8868226efa9593

Observation 63bce70b-bbe5-44fc-990c-bdcf9b7ce532 · outbound

This paper cites Confidence-Aware Document OCR Error Detection,.

Improving MLLM Historical Record Extraction with Test-Time Image Confidence-Aware Document OCR Error Detection,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.597283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.426654Z digest=sha256:9ae2a91237141d0c49f66256add7ffc2d19c5db1cea21ae040bae86fb1e874ec

Observation 84ebb4c7-3e43-4261-a143-6855cdb9169d · outbound

This paper cites Zhang et al.,Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self- Improving OCR, Apr.

Improving MLLM Historical Record Extraction with Test-Time Image Zhang et al.,Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self- Improving OCR, Apr

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.483257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.481897Z digest=sha256:174b2f6db7e6bf6fcc877bbdd1730678a7446fad8d0bde98826fc4183498831d

Observation a7b46743-1197-4c4f-9edc-636ac4788a16 · outbound

This paper cites Ma et al.,Test-Time Generative Augmentation for Medical Image Segmentation, Jun.

Improving MLLM Historical Record Extraction with Test-Time Image Ma et al.,Test-Time Generative Augmentation for Medical Image Segmentation, Jun

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.360417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.526173Z digest=sha256:ac55a83a641792765ab8875d1edd49def9c08cbc6bb6314794f2d495b7ccd995

Observation 29f355d5-5bad-4487-a089-a43783010f85 · outbound

This paper cites Zhang et al.,A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?May 2025.DOI:10.48550/arXiv.

Improving MLLM Historical Record Extraction with Test-Time Image Zhang et al.,A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?May 2025.DOI:10.48550/arXiv

Reference 26

Resolution
malformed identifier
no resolver link, observed 2026-08-04T21:01:34.579703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:34.579703Z digest=sha256:814b6e9e5eda7468fddebf29e250b083e3026c6d99cce609e9a1667c3535d98a

Observation 334350e1-2925-446f-9893-4e1c31c7e061 · outbound

This paper cites Kish,Survey Sampling(Survey Sampling).

Improving MLLM Historical Record Extraction with Test-Time Image Kish,Survey Sampling(Survey Sampling)

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.255602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.633942Z digest=sha256:c7e7f0ea9d4d9fa2ed4938ba4ce8ac5775015cf3cbbae89e70a1762b342837e1

Observation b9fc0188-c12b-43ef-b903-ca40e7f2b8f4 · outbound

This paper cites Probability Inequalities for sums of Bounded Random Variables,.

Improving MLLM Historical Record Extraction with Test-Time Image Probability Inequalities for sums of Bounded Random Variables,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:36.188003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.686594Z digest=sha256:fa45e26cba0df70f03ebffbcfe600ecc16e196f7a7717153ddd378617fca2e78

Observation debc31eb-f10b-48fd-8c93-1f7d8e57772e · outbound

This paper cites Data Augmentation for Recog- nition of Handwritten Words and Lines Using a CNN-LSTM Network,.

Improving MLLM Historical Record Extraction with Test-Time Image Data Augmentation for Recog- nition of Handwritten Words and Lines Using a CNN-LSTM Network,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:35.998027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.723816Z digest=sha256:98fc72422ded00f3630731252715f2a792fd7a2bf0778711ce320974c88dc123

Observation 6b8855a5-6868-4c6b-9383-1a5ebcd875a0 · outbound

This paper cites Wang et al.,Scaling Laws in Patchification: An Im- age Is Worth 50,176 Tokens And More, Feb.

Improving MLLM Historical Record Extraction with Test-Time Image Wang et al.,Scaling Laws in Patchification: An Im- age Is Worth 50,176 Tokens And More, Feb

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T21:01:34.747791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T21:01:34.747791Z digest=sha256:80383da274719c08926598854ed38c1b7c2e7ae9a4cd8f50b56bce93dce52cea

Observation e7b486cf-2231-43fc-bb27-a8e7b31008a6 · outbound

This paper cites Three Things Everyone Should Know About Vision Transformers,.

Improving MLLM Historical Record Extraction with Test-Time Image Three Things Everyone Should Know About Vision Transformers,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:35.919875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:34.871739Z digest=sha256:f98ba51ecb27aab3a975e33316cc8b4dcfd6d4913f7412f4aaf92e3bc0615dc9

Observation 322f62ca-35c7-4298-9d0b-23d2e3bdada4 · outbound

This paper cites Qiao et al.,UniViTAR: Unified Vision Trans- former with Native Resolution, May 2025.DOI:10.

Improving MLLM Historical Record Extraction with Test-Time Image Qiao et al.,UniViTAR: Unified Vision Trans- former with Native Resolution, May 2025.DOI:10

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T21:01:35.826747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-04T21:01:35.003144Z digest=sha256:a2714c0e44284d9d6a7b8e51eaf691abc7e3cf325f690838dae236b9f48686fc

Pith citing papers

No inbound Pith citation observations are available.