Pith. sign in

Paper Citation Record · LEDGER

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes

As of 23 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2504.21226.

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

pith.paper-citation-record.v1
2504.21226 v3

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:13:23.880032Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:51:44.681867Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T20:51:44.823981Z

Reference resolution

13 of 13 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved11
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 313e1211-d5b2-47b4-91f8-8ae9c348c37e · outbound

This paper cites The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.655097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.655097Z digest=sha256:07c55d9e099d9022f988a9ab9225ef115b24ac2e371e4e6af701c44c039490da

Observation fed6e665-833b-4c46-81cb-bf5bf226d795 · outbound

This paper cites MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.660143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.660143Z digest=sha256:a974e265bf9748bc25f90da4aacadef1947a85143855da2deff9012d98165a5a

Observation ae7fb6bd-133a-49ed-9058-537e1cbda2bb · outbound

This paper cites HateCLIPper: A CLIP- based Framework for Multimodal Hate Speech Detec- tion.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes HateCLIPper: A CLIP- based Framework for Multimodal Hate Speech Detec- tion

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T05:13:24.192300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-16T05:13:23.663835Z digest=sha256:c25a068666c296dfa2501ffcaa2d24daabcb2f2acb709d8625bbbc56c6dcfb31

Observation 7443c08d-58bf-4963-a643-e663beb775f6 · outbound

This paper cites B., Shiwakoti, S., Chaudhary, M., & Wang, H.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes B., Shiwakoti, S., Chaudhary, M., & Wang, H

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T05:13:24.093444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-16T05:13:23.745844Z digest=sha256:b4e23c1d7a77d45d57be442ffb5249ba1e4028463589881410f0d6a360510b0c

Observation 42146ad3-b134-4b69-961b-dbbfd3f5cb50 · outbound

This paper cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.796291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.796291Z digest=sha256:b2d8f2b63fd4f3bb2fdff289965afffb6671cd4b4d1a05abaa89288c3e25dec3

Observation d0cde4c9-0eb0-4c11-921b-b0649978634f · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.857358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.857358Z digest=sha256:07b061254f9a640462fd30acb81aa301bb016dbdbef52c57cce0eb92bd23d385

Observation 1a59acc0-79f6-4a84-a69d-10ef283432d0 · outbound

This paper cites Decoupled Weight Decay Regularization.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Decoupled Weight Decay Regularization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.861867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.861867Z digest=sha256:468e70eb1c794e25de234b8162e63130b3d5a458f91c2362fb9e13013c528f31

Observation 45341ce4-534f-4ebd-bc93-5652e485860a · outbound

This paper cites Parameter-Efficient Transfer Learning for NLP.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Parameter-Efficient Transfer Learning for NLP

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.865464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.865464Z digest=sha256:d0bd2e5986f7f5f59479267e46070f266a55beb4bd51f025f3758471c136c225

Observation f7b69670-4620-4028-b8ad-cb7b15430ad9 · outbound

This paper cites Gaussian Error Linear Units (GELUs).

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Gaussian Error Linear Units (GELUs)

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.869155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.869155Z digest=sha256:ce40fdcf3c13654aaea6d83a2caeab453f14c70ce3cb911e233fc0b33d857874

Observation 8fce1050-c130-41d1-862f-d791ae94bfc7 · outbound

This paper cites Attention Is All You Need.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Attention Is All You Need

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.872607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.872607Z digest=sha256:e175496f68fc368dbc99857a1d9f001b25b3cba18a5bddd76a173dd6fc279a34

Observation 641733c1-916e-44b8-9bfc-466a189ff995 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Learning Transferable Visual Models From Natural Language Supervision

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.876081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.876081Z digest=sha256:dcf0d7a6675dd12989caca39f9dc6c4009a58a4520e014a55386ac7afa44fa23

Observation 32531665-abea-421d-9f3a-2ef86ddda8c3 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.880032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.880032Z digest=sha256:3b90b92c00d119edb844b942c1a5987902f4886676fa46f1393e6676ac82c56b

Observation 73e3623a-cd0d-4a07-825a-2dcb9d8c35c3 · outbound

This paper cites Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features.

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-16T05:13:23.685018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:13:23.685018Z digest=sha256:7d3bd9a7e9b0de3e83fa34c87b096023273d82b2946eba123b52fcc2044f526e

Pith citing papers

Observation da83ec06-0f40-4791-8ced-1e64241c6cf6 · inbound

Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healing cites this paper.

Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healing MemeBLIP2: A novel lightweight multimodal system to detect harmful memes

Reference 19

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:51:44.830371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-15T20:51:44.681867Z digest=sha256:8503770ee9a7edf4ab5611cd72f549ac83880efa61bec8dd1d8ebb4cb4d56311