Pith. sign in

Paper Citation Record · LEDGER

ShieldGemma 2: Robust and Tractable Image Content Moderation

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 18 inbound Pith citation observations for arXiv:2504.01081.

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

pith.paper-citation-record.v1
2504.01081 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:49:20.328915Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:09:54.641120Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 513fb847-4e87-4aea-995d-80b531f0503d · inbound

VLMs Can Aggregate Scattered Training Patches cites this paper.

VLMs Can Aggregate Scattered Training Patches ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T11:04:05.817517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:04:05.817517Z digest=sha256:60584e8964a66f88b60e75697b84d0a6d1e57c3f5a38c06385e09d1fd63e8cdf

Observation 565c71ff-9edc-481f-a63f-4b03b833470d · inbound

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values cites this paper.

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T05:43:07.193249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:43:07.193249Z digest=sha256:0661742b1f9ce9b479c9defe588fc0f9e77e3d74614a2092e7f8826cedbc8267

Observation 2a9a2bfd-6676-4cfc-a215-84e3404c3bd1 · inbound

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models cites this paper.

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-06T17:08:20.214896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:08:20.214896Z digest=sha256:a8b16eac5d5e44bd8db4ec4dfa2ad751e0ba50c2b53157ca2e7d7be3b7a6eede

Observation 2600760a-ae98-4cd1-ba21-1b45ed2c279a · inbound

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models cites this paper.

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 64

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T12:42:36.804758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-05-18T12:41:48.620040Z digest=sha256:ca7b34c580c3bb9056aed9ee4d41ab69e67060e553d6c217bd778020b4926155

Observation 67bafbe8-bdda-4c3d-b079-f68e55ebbcbc · inbound

SenBen: Sensitive Scene Graphs for Explainable Content Moderation cites this paper.

SenBen: Sensitive Scene Graphs for Explainable Content Moderation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 40

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T08:01:01.787041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-10T16:51:01.201885Z digest=sha256:6df7539ff6d271a99f4b57960cda75546c34e6503b422bfe2cd8a868f9cab42a

Observation 979ac981-a85c-492d-89d3-fdc54b545123 · inbound

SenBen: Sensitive Scene Graphs for Explainable Content Moderation cites this paper.

SenBen: Sensitive Scene Graphs for Explainable Content Moderation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-12T23:42:32.347933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T23:42:32.347933Z digest=sha256:5350fc35194679e9b6f141d7d01a193d2a636a1ac7161c84da362fdbdb1cb5e3

Observation 0c507a52-f587-4a0c-b449-40a5acdee1e3 · inbound

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening cites this paper.

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 18

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T14:08:21.190297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-20T14:03:56.859481Z digest=sha256:7ac908695fab1324f441f1aca35d53570901afe2a9326a84db0f43ebe164a536

Observation 39cc81f6-7e92-4b9c-bec5-2603223e608c · inbound

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South cites this paper.

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 97

Resolution
verified exact
arxiv_id, observed 2026-05-20T07:08:07.042646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-20T07:06:57.555070Z digest=sha256:ef60bc9dfdeca1b2da1f05a4ece44078607811032e5c2de702438d5069f2965b

Observation e011571c-b4a4-4314-b45c-b3ef1731047a · inbound

Boundary-targeted Membership Inference Attacks on Safety Classifiers cites this paper.

Boundary-targeted Membership Inference Attacks on Safety Classifiers ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-22T08:11:17.541591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-22T08:06:45.896332Z digest=sha256:a1afdc367ad63ae7d1b3a4e1e3cf8549ef1c79e2a5d8a91e30df7479d6cce2ed

Observation b6096ed2-305c-4eb0-bcc7-4120c3746323 · inbound

Boundary-targeted Membership Inference Attacks on Safety Classifiers cites this paper.

Boundary-targeted Membership Inference Attacks on Safety Classifiers ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-25T05:45:24.307746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-25T05:42:55.999769Z digest=sha256:8e641f44090812cb38087d6e2928a803c2f4783aae02e868f8489874094b3c1d

Observation d826f66f-91a9-43c1-bd93-c860745488c3 · inbound

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing cites this paper.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 25

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T22:03:59.797888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:7514175b67e5c4e9ad4f934ef36cb7b2b1ac5b68ef4de572d981cfe2907c82f3

Observation de449355-e559-4c24-be03-4f26a87095cd · inbound

No Safe Dose: How Training Data Drives Unsafe Image Generation cites this paper.

No Safe Dose: How Training Data Drives Unsafe Image Generation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 67

Resolution
verified exact
arxiv_id, observed 2026-06-29T13:43:28.537424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-29T13:41:53.768791Z digest=sha256:96f6f1b0a2e6234bbe6e709ebcdb0b07be9361aca6b1a2dda2831fdb412c9d1b

Observation 46013750-9652-46f7-955c-fef2a5b8773d · inbound

MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.

MIRAGE: Protecting against Malicious Image Editing via False Moderation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 74

Resolution
verified exact
arxiv_id, observed 2026-07-04T15:09:54.643230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-26T01:52:12.291420Z digest=sha256:df0be7749df2a39f7d63095af78dc0110ebd48eafb2d01894bdf68eeb27e689e

Observation 373824c2-71b4-4cbe-b72d-ac420de6a596 · inbound

MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.

MIRAGE: Protecting against Malicious Image Editing via False Moderation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 74

Resolution
verified exact
arxiv_id, observed 2026-06-29T19:13:53.510290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-29T04:46:56.552601Z digest=sha256:05edeb5266e323260f82e914da927916fcabce4f928bed4a18883d521ddbe779

Observation 6ba0bf05-8920-416b-95e3-1cf68579ff61 · inbound

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing cites this paper.

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 47

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T06:34:18.821395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-30T06:31:55.631719Z digest=sha256:9daccdcf21b46773c8bda23645d47ec849e1dca0d91786704e0086c140e5b4c8

Observation 2c519ab3-a279-4d56-80a5-5161116b8721 · inbound

Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints cites this paper.

Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 97

Resolution
unresolved
no resolver link, observed 2026-07-13T05:26:06.829382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T05:26:06.829382Z digest=sha256:95e247e1f9874ed2307445423b342a8ddfd2c7dee7480531e4a3c9fbcb762cad

Observation 37172ff4-17a5-4710-a802-65f27e690df0 · inbound

Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation cites this paper.

Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-31T15:15:01.267197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T15:15:01.267197Z digest=sha256:b97c904d23dbc71445faf806f5c9ae11574d93dec7df8b4ca09fe58f9aadadf7

Observation 1bb3a7de-1f5f-4050-a77e-f2a6c3ae0335 · inbound

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions cites this paper.

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-12T20:49:20.328915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T20:49:20.328915Z digest=sha256:5e48db59304905fc83cd73231c069522f9fbe7b4591153cd93bad00f3d1dd1e7