Paper Citation Record · LEDGER

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

As of 12 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 8 inbound Pith citation observations for arXiv:2510.19316.

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

pith.paper-citation-record.v1
2510.19316 v2

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T05:33:37.865654Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T16:47:41.888680Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T09:07:47.383131Z

Reference resolution

17 of 17 outbound references displayed

verified exact2
verified fuzzy11
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 201e7522-c570-425a-afa1-a9f8c360adaa · outbound

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

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T05:35:56.235395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1e2a1aa6-b3e3-4380-bac8-47bee0aceb92 · outbound

This paper cites Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T05:35:56.226611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 38e7098f-7e00-40af-a7d8-1e32a6970ee9 · outbound

This paper cites MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T05:35:56.230814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 41917c1a-6fca-48a3-9d97-b5cc4656d968 · outbound

This paper cites Evowiki: Evaluating llms on evolving knowledge.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls Evowiki: Evaluating llms on evolving knowledge

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.888364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b5f9bbb6-d433-4940-a845-560752c62408 · outbound

This paper cites ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-30T02:04:17.238145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5ed5bc84-3fdf-40af-acb6-7ba3568bb5d4 · outbound

This paper cites Its key feature is the use of carefully crafted instruction-answer pairs, which facilitates a straightforward assessment without the need for specialized prompt engineering.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls Its key feature is the use of carefully crafted instruction-answer pairs, which facilitates a straightforward assessment without the need for specialized prompt engineering

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.883392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f8009f21-377d-43fa-9c4b-0d90b3af06cb · outbound

This paper cites It features over 3,000 bilingual multiple-choice questions spanning 20 skill dimensions, from visual recognition to abstract reasoning.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It features over 3,000 bilingual multiple-choice questions spanning 20 skill dimensions, from visual recognition to abstract reasoning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.886026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 25ebde76-2603-4c6d-8ca8-d2b1091d79f1 · outbound

This paper cites It uses 2,300 multiple-choice questions to test reasoning capabilities where integrating textual and visual information is essential.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It uses 2,300 multiple-choice questions to test reasoning capabilities where integrating textual and visual information is essential

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.890890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9eddc05f-1c82-48a2-8780-6a058c2b2410 · outbound

This paper cites It focuses on tasks where textual information is essential, requiring tight integration of visual perception and OCR.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It focuses on tasks where textual information is essential, requiring tight integration of visual perception and OCR

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.910782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ba2d7f16-56c8-4bab-84ba-4226329ec2d1 · outbound

This paper cites an unresolved cited work.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-18T05:35:56.908553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 89f7edd4-ed55-4b9d-856f-61fa79449f3a · outbound

This paper cites The benchmark includes 11,500 questions from six disciplines, utilizing 30 image formats to test complex, subject-specific reasoning.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls The benchmark includes 11,500 questions from six disciplines, utilizing 30 image formats to test complex, subject-specific reasoning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.906241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fea3d9ac-b421-40da-8dfb-b2b427fc0222 · outbound

This paper cites It consists of 400 distinct image-prompt combinations engineered to test a model’s ability to comply with detailed and nuanced directives.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It consists of 400 distinct image-prompt combinations engineered to test a model’s ability to comply with detailed and nuanced directives

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.903227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8be44163-38e6-4b0f-b68b-d4c27888f5cb · outbound

This paper cites It specifically assesses a model’s capacity for contextual understanding, temporal reasoning, and maintaining coherence throughout extended interactions.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It specifically assesses a model’s capacity for contextual understanding, temporal reasoning, and maintaining coherence throughout extended interactions

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.895757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dcad8a1e-1c02-4347-8cb2-829595985a89 · outbound

This paper cites It aggregates 6,141 problems from 31 datasets, requiring detailed visual analysis and compositional logic for solution.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It aggregates 6,141 problems from 31 datasets, requiring detailed visual analysis and compositional logic for solution

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.893286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8b314895-b5ef-4484-9e9e-8ebd7e4525f3 · outbound

This paper cites Categorized into 16 mathematical areas and five difficulty tiers, it offers a structured evaluation of advanced reasoning in LMMs.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls Categorized into 16 mathematical areas and five difficulty tiers, it offers a structured evaluation of advanced reasoning in LMMs

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.897962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9d90c7f3-6500-4d8e-8b43-9c4ce618d2a4 · outbound

This paper cites It employs 346 images and 1,129 structured questions to quantitatively analyze the causes of inaccurate or inconsistent model responses.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls It employs 346 images and 1,129 structured questions to quantitatively analyze the causes of inaccurate or inconsistent model responses

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T05:35:56.900642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2f24aaae-13e8-4088-b426-a4294007212a · outbound

This paper cites mlp.down proj.

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls mlp.down proj

Reference 17

Resolution: malformed identifier; arxiv_id, observed 2026-05-18T05:35:56.240287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation 759a171d-d11f-40a0-ac9a-0d4fb1ca4ad1 · inbound

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation cites this paper.

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T19:33:42.366663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation af9e8e87-f201-4917-9773-100218feeb3f · inbound

IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval cites this paper.

IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-02T21:17:24.788458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 63a194eb-071c-4c64-ac31-cf28df9ff988 · inbound

RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval cites this paper.

RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:07:47.384386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1d882e1d-4499-4e0a-b577-612d11c72e25 · inbound

Can Multimodal Large Language Models Understand OCT? cites this paper.

Can Multimodal Large Language Models Understand OCT? KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-01T20:30:30.309800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523eab35-5590-4fad-8a7f-3df1aba4915a · inbound

RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection cites this paper.

RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T11:50:17.583910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caefa43e-66b5-448b-9654-1b652cf39833 · inbound

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning cites this paper.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.116166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfeba3a2-bbd5-41f6-b631-9ee1f3038453 · inbound

OPD-V: Visual On-Policy Self-Distillation with Modality Balance cites this paper.

OPD-V: Visual On-Policy Self-Distillation with Modality Balance KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T04:40:15.261291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e658217-1d48-4b4b-b506-bca35bec248c · inbound

OPD-V: Visual On-Policy Self-Distillation with Modality Balance cites this paper.

OPD-V: Visual On-Policy Self-Distillation with Modality Balance KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T16:47:41.888680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.