Pith. sign in

Paper Citation Record · LEDGER

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

As of 15 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 2 inbound Pith citation observations for arXiv:2506.17664.

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

pith.paper-citation-record.v1
2506.17664 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:34:56.649817Z

measured 20 of 20 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-11T01:49:15.136031Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T16:01:22.762740Z

Reference resolution

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a01c9e40-12ba-4f38-aed7-c5675210c69f · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.081734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.081734Z digest=sha256:33164791a859a2bd44c7d55b31c6a5c2cb6380a28bf71b8213a73745d51b13c1

Observation 5381a6ff-955e-46b2-a247-d81895bd4159 · outbound

This paper cites Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.164743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.164743Z digest=sha256:cc0ca65b8cfda405411e1ec2bee607ecd667770292d438eb86ea0a53755b9f71

Observation 3acb9a3f-0ac5-4fc1-9016-dfa90bb4677d · outbound

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

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.278265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.278265Z digest=sha256:c3194470b2fe6d53dc9800b73a8c1ad2a8d32f62c1a5ec00f86adb3365a96796

Observation 8b2b0a8f-af0a-4306-ae4a-dd4706c9bad8 · outbound

This paper cites GPT-4o System Card.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation GPT-4o System Card

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.465653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.465653Z digest=sha256:18221ce602a730dad9da9d1d27df3527c00df8376de4ea9cf1ec12296ad911e7

Observation 58ef4792-b290-4307-9c93-f8f8618fade0 · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.674752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.674752Z digest=sha256:dfc154834976f9e183dfcf8e51baa0d37f62b07ed94e3231d36dc0172bd2dc70

Observation f5974394-d72d-41d7-8774-134f78e52d20 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.735935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.735935Z digest=sha256:c147ca8b8f38ba4bf1fb43aabb744960e155240997871186b059267505d12ea7

Observation 6876b6ee-b62b-4f54-bc7e-060ab3694c6a · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.885669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.885669Z digest=sha256:91e48e8d70d01830ec841f84e536323cca243d41e476645b07a2dc6a6d97df71

Observation b08c0987-0469-4868-ad41-5cf26c981d82 · outbound

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

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Gemini: A Family of Highly Capable Multimodal Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.934743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.934743Z digest=sha256:a96ba4eea195363ccbe844209643964de877cc71ff3765dbe4ca5bd9cfd74501

Observation b6bd49ea-46fc-4c65-836e-cf82d369b442 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.992900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.992900Z digest=sha256:536f49ed128a14fc113a4bbc4bfba94f0c7fa9f88a921f553a3b26b59f597382

Observation ded3c166-299f-491a-8d8a-cf7f8be290b8 · outbound

This paper cites Caption Anything: Interactive Image Description with Diverse Multimodal Controls.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:56.110735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:56.110735Z digest=sha256:da0fa82e392d2e40f409000631166601336a20acf63cde5db850d815724479f4

Observation 0bdd5568-3306-4e1c-9e9b-31e075c5403e · outbound

This paper cites DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:56.275773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:56.275773Z digest=sha256:a545879c2187ecbfb6171ed554ed6d4fc0288e0322f11e469da8ea1f224dd732

Observation abe0cc92-da89-4367-a161-33631ac7882e · outbound

This paper cites mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:56.417716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:56.417716Z digest=sha256:dcb28b6deef764900be62f81ac9b69fcbe0611229bba7ccc03dae2ed72deeec6

Observation a95efcf4-84f7-4b69-8af0-693b4a982f1e · outbound

This paper cites Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:56.541827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:56.541827Z digest=sha256:3e77e84deef04547d5a6b3bd4b6a200e0ba9bbd6d59d373af21957fbeb48d0bc

Observation 921ef3b2-bdf5-4337-85df-c2d8e04ff6f1 · outbound

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

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:56.649817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:56.649817Z digest=sha256:d3d44fe8d4004ecad964b6d6bcdc1ab94079c2d04f10392570a06af94fa37a15

Observation 39332d3d-a380-49ed-9974-bd42dc128f82 · outbound

This paper cites Object Hallucination in Image Captioning.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Object Hallucination in Image Captioning

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.813461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.813461Z digest=sha256:1a43d257c3cae31f433388fb272e4d397d4ff48455184677dc1659bd0a4e11d8

Observation 751df6f5-9b7c-486d-b97a-77f3358bb160 · outbound

This paper cites VisualBERT: A Simple and Performant Baseline for Vision and Language.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation VisualBERT: A Simple and Performant Baseline for Vision and Language

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.544749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.544749Z digest=sha256:d08754f3876d4ea3b4743b8df23a8448554e310e410d69d35f95070d97e8cc5e

Observation 400765dc-0cac-40bc-a2aa-1021cce2aab4 · outbound

This paper cites MultiModal-GPT: A Vision and Language Model for Dialogue with Humans.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation MultiModal-GPT: A Vision and Language Model for Dialogue with Humans

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:55.367724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:55.367724Z digest=sha256:309fa720e1b2def51a2ae6202de174cfa94965713a3b7dadf9828b4809a83a2c

Observation 629c7d3e-52de-4b5f-9070-f98089e618c2 · outbound

This paper cites Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention.

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T23:34:54.937267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:34:54.937267Z digest=sha256:b8e47231594ebe8ed9f17d50d4e235e4ce2b762207552161465edd4ac5c89bb0

Pith citing papers

Observation a6efc5ab-82e8-46db-9ee7-616d25da5476 · inbound

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs cites this paper.

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

Reference 53

Resolution
verified exact
arxiv_id, observed 2026-05-11T16:01:22.777348Z

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=2026-05-09T18:53:06.494640Z digest=sha256:c2a1dd277d93641c90d9091f3ea768e64efb1c473971782635c3de757cc26aa8

Observation c1436332-d86a-4610-9ff0-277a199108ba · inbound

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs cites this paper.

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

Reference 53

Resolution
verified exact
arxiv_id, observed 2026-05-11T01:50:51.532867Z

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=2026-05-11T01:49:15.136031Z digest=sha256:c6bb5c1f4f3296737c100af6df8e3b27d9d474d946ac863d5aead35c5b73d8ee