Pith. sign in

Paper Citation Record · LEDGER

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures

As of 21 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2501.15074.

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

pith.paper-citation-record.v1
2501.15074 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:42:12.418855Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T12:32:45.130763Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

19 of 19 outbound references displayed

  • verified exact0
  • verified fuzzy11
  • unresolved7
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 36b370a1-de44-4aa9-bfc3-40e80eef2bf3 · outbound

This paper cites To rectify this automatically, we compared the average length of OCR tokens extracted using PaddleOCR (Du et al.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures To rectify this automatically, we compared the average length of OCR tokens extracted using PaddleOCR (Du et al

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.547375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.389956Z digest=sha256:c3b99b0d9302a1c6d70fbef6f1d7f33030d3a6133ca379cf5cedd1db99028aa8

Observation fb89b5e5-33f8-4f74-a93e-e31cea92865b · outbound

This paper cites an unresolved cited work.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-10T14:42:12.540154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.392607Z digest=sha256:069c6d56604d2cb9850f749c16f9fcfabc999915be8a34f822c81ebbcfa25311

Observation ea25361d-6cb6-406a-94fb-5ff94af3750d · outbound

This paper cites To maintain a focus on singular representative visuals per image, we extract figure labels using PaddleOCR (Du et al.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures To maintain a focus on singular representative visuals per image, we extract figure labels using PaddleOCR (Du et al

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.532359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.395294Z digest=sha256:f4ebdca5faea83db3cec463b11f89b617043908694f83df8c4ee52dcac7ba2e2

Observation 58d0edb2-0c69-4986-a24a-906e81802cfc · outbound

This paper cites Prior works (Tang, Boggust, and Satyanarayan 2023; Mahin- pei, Kostic, and Tanner 2022; Masry et al.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Prior works (Tang, Boggust, and Satyanarayan 2023; Mahin- pei, Kostic, and Tanner 2022; Masry et al

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.524377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.397769Z digest=sha256:f526d14eb48cfd77f16c8b5abb4798f33674ff8c03d13753545a475cb042e659

Observation 96a010f3-762c-4196-aa83-52c3e33495d7 · outbound

This paper cites brief” with “detailed.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures brief” with “detailed

Reference 5

Resolution
malformed identifier
raw_fallback, observed 2026-08-10T14:42:12.517048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.400204Z digest=sha256:20cc6223450147675250f63f9b378eb5a0b8c37ed69ab9348511d19cc365eef3

Observation 9bb311fb-1820-44e3-9e19-0c99cb8d0743 · outbound

This paper cites an unresolved cited work.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-10T14:42:12.554364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.386458Z digest=sha256:64a66649bca1bef57e50b09cd4b83c0a2318039568de4689a69ad2afa1806192

Observation 87f73be5-94a8-412e-a2df-6b0aa96c5d91 · outbound

This paper cites The rack management system 100 communicates with managed devices 170.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures The rack management system 100 communicates with managed devices 170

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.463763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.416283Z digest=sha256:6202da979f824147fa6579061a128ffaf91f9f9c31d4e7e5793f89d53cb58a10

Observation 40cff4e6-2aff-48ec-9b88-84cbce534ca0 · outbound

This paper cites Each seller system 130 is associated with one or more sellers.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Each seller system 130 is associated with one or more sellers

Reference 110

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.455127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.418855Z digest=sha256:0def10b6883df41d2fe5ebe03d49e39be345112f600344e42b265487a10cdd5a

Observation c57b5b36-b4f7-4fdd-8b8e-1ea66e449caf · outbound

This paper cites For instance, the KPI definition component 134 can be associated with an enterprise and can provide KPI definition(s) that are specific to the enterprise.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures For instance, the KPI definition component 134 can be associated with an enterprise and can provide KPI definition(s) that are specific to the enterprise

Reference 120

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.471779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.414109Z digest=sha256:f4ce2f9ac91b0f44a054cb31e65e0a6098ce82b475dea42f39789b144d80d1d4

Observation 9e91619a-03f7-4da8-80cf-5e018c7a3453 · outbound

This paper cites an unresolved cited work.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Unresolved cited work

Reference 216

Resolution
unresolved
raw_fallback, observed 2026-08-10T14:42:12.494056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.407613Z digest=sha256:56f73c1fc16fd5e8dd2055126842b6683753615d926972770fa4dccb074c6dab

Observation f9e61778-eda5-4ece-88bd-27bfe5033d22 · outbound

This paper cites The web browser 222 may be a web browser such as Internet Explorer, Mozilla Firefox, Safari, or other similar web browser.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures The web browser 222 may be a web browser such as Internet Explorer, Mozilla Firefox, Safari, or other similar web browser

Reference 220

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.501268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.405370Z digest=sha256:1e095fb4eb3a186d775688675e03e2109ea5083e4029d298a979423966584c17

Observation 22e9acff-6f4a-4ba8-85aa-75fa7794d400 · outbound

This paper cites The computing device 2 220 may include a web browser 222 and an application 224.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures The computing device 2 220 may include a web browser 222 and an application 224

Reference 240

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.509448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.403145Z digest=sha256:bf078f474e456d8e3dab20a6085093a4fb2595203e1044f4ae4dddbd0851db92

Observation acd1642f-190d-4cd8-8e7f-104dada173d2 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-10T14:42:12.366963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T14:42:12.366963Z digest=sha256:98a556819134a7a2791c9371c938c8a29c76f9d10c78d59cb48b314393482411

Observation 15ccd717-c8d3-4682-888f-ec3a256cafd9 · outbound

This paper cites SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-10T14:42:12.383586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T14:42:12.383586Z digest=sha256:fc497052007950e7569c12e2139d03107de7d8ed60ae8fd20baa4d6d69e8fb1f

Observation 0b72fa7b-3854-41b4-9b7c-b2e8b236ce9a · outbound

This paper cites In ACL (Findings), 2263–2279.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures In ACL (Findings), 2263–2279

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.560908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.376061Z digest=sha256:94e7f9572e91b672985926af0a915279d8369bae35a38208ae1ba4266ed2684d

Observation 75ce9d2f-b65f-4dd8-b986-f2e4acf08358 · outbound

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

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Gemini: A Family of Highly Capable Multimodal Models

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-10T14:42:12.379324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T14:42:12.379324Z digest=sha256:720a494165ce5ad4662fe0444370b549a72cb609ba5685d3c5f3aed98159ccb0

Observation 6019738a-e725-4e80-adfb-d6180709b4b1 · outbound

This paper cites an unresolved cited work.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Unresolved cited work

Reference 2024

Resolution
unresolved
raw_fallback, observed 2026-08-10T14:42:12.567686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.372574Z digest=sha256:a7d6101ca9c4d760ee3d7c6a292985319d3f315a5c91835f9a8e667b32d9945f

Observation e421fdd5-8011-4ee4-87e2-8fd07a06ed38 · outbound

This paper cites The application displays an entire list of the open orders window in the master trade screen.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures The application displays an entire list of the open orders window in the master trade screen

Reference 2725

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.486845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.409669Z digest=sha256:a45f2b80a6e6e489d1c9140e519083a93c40912817e7aaaa5f1cc3c7b6ad3b69

Observation a6208314-84a9-43c9-83ee-77c2fe2ccbd0 · outbound

This paper cites Step 3445.

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures Step 3445

Reference 3440

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T14:42:12.479284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-10T14:42:12.411694Z digest=sha256:e50ada69e8c9ff9ed1bc4554f38930b8b83400828d7407933547a6599ddfc20a

Pith citing papers

Observation 89981770-886c-45bc-9848-2329d63551f8 · inbound

FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions cites this paper.

FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures

Reference 9554

Resolution
unresolved
no resolver link, observed 2026-08-03T12:32:45.130763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T12:32:45.130763Z digest=sha256:3b0e768e5a88bc60424bf2c5556491999543f044e07724a40e4698e18c697401