Paper Citation Record · LEDGER

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks

As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.09164.

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

pith.paper-citation-record.v1
2607.09164 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T04:59:35.053286Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bbfee72e-257c-4359-8be0-248b36cff804 · outbound

This paper cites On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e21f141-ff79-4c50-a96e-0f0bb8f9c700 · outbound

This paper cites Legrad: An ex- plainability method for vision transformers via feature formation sensitivity.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Legrad: An ex- plainability method for vision transformers via feature formation sensitivity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a17bf99b-3ca4-43f5-9da6-c958a3c65a3f · outbound

This paper cites What made you do this? understanding black-box decisions with sufficient input subsets.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks What made you do this? understanding black-box decisions with sufficient input subsets

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b648b7e4-d987-4aea-a46d-bbe325d321c3 · outbound

This paper cites Grad-cam++: Gener- alized gradient-based visual explanations for deep con- volutional networks.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Grad-cam++: Gener- alized gradient-based visual explanations for deep con- volutional networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1368e75a-23eb-4794-92a3-593d8dd164c7 · outbound

This paper cites Transformer inter- pretability beyond attention visualization.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Transformer inter- pretability beyond attention visualization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8afc0452-1de8-457e-b15b-3be8c00ff815 · outbound

This paper cites Real time image saliency for black box classifiers.Advances in neural information processing systems, 30, 2017.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Real time image saliency for black box classifiers.Advances in neural information processing systems, 30, 2017

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c99b49f-22e1-4c9f-82d8-052072aed5d5 · outbound

This paper cites Under- standing deep networks via extremal perturbations and smooth masks.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Under- standing deep networks via extremal perturbations and smooth masks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 736b8a52-afa5-4ea8-a090-43a25a454349 · outbound

This paper cites Interpretable explana- tions of black boxes by meaningful perturbation.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Interpretable explana- tions of black boxes by meaningful perturbation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168c6443-59bf-4dda-88d9-e59c98356b59 · outbound

This paper cites Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c690cbbe-f640-403a-9681-e1dca22175f8 · outbound

This paper cites Alignsam: Aligning seg- ment anything model to open context via reinforcement learning.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Alignsam: Aligning seg- ment anything model to open context via reinforcement learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70e421b7-f991-4f20-867a-23d1c32109e2 · outbound

This paper cites Layercam: Exploring hierarchical class activation maps for localization.IEEE transactions on image processing, 30:5875–5888, 2021.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Layercam: Exploring hierarchical class activation maps for localization.IEEE transactions on image processing, 30:5875–5888, 2021

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d694554d-1e70-488f-94b2-97401642f459 · outbound

This paper cites igos++ integrated gradient optimized saliency by bilateral per- turbations.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks igos++ integrated gradient optimized saliency by bilateral per- turbations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bfc659-23f0-40fe-b1b2-0ba92d6aa96e · outbound

This paper cites Segment anything.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Segment anything

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a535c7f-0d3b-4fcc-b3de-617109c2c0ed · outbound

This paper cites Vision diffmask: Faithful interpretation of vision trans- formers with differentiable patch masking.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Vision diffmask: Faithful interpretation of vision trans- formers with differentiable patch masking

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 217d718d-0a48-44f6-bc19-685d3492b641 · outbound

This paper cites RISE: Randomized Input Sampling for Explanation of Black-box Models.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks RISE: Randomized Input Sampling for Explanation of Black-box Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4afd0c40-fa9e-4de7-aa10-ba80e9ec3faa · outbound

This paper cites Visualizing deep networks by optimizing with integrated gradients.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Visualizing deep networks by optimizing with integrated gradients

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faaf8d5b-86d0-40fa-9322-8ae3ebf3443c · outbound

This paper cites Grad-cam: Visual explanations from deep net- works via gradient-based localization.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Grad-cam: Visual explanations from deep net- works via gradient-based localization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15b6996b-c2c3-487c-a7ce-7521bad36841 · outbound

This paper cites Learning important features through propagating activation differences.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Learning important features through propagating activation differences

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67221fc0-7e1e-47dd-9047-610052173e76 · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f15ece5-3e2f-4a5f-94a6-e5a281cb71da · outbound

This paper cites SmoothGrad: removing noise by adding noise.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks SmoothGrad: removing noise by adding noise

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007af550-fd6c-407c-8073-bb727a0bc5b8 · outbound

This paper cites Ax- iomatic attribution for deep networks.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Ax- iomatic attribution for deep networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c9fdad7-2a3b-4127-8eeb-b3e92011e254 · outbound

This paper cites Diffuse attend and seg- ment: Unsupervised zero-shot segmentation using sta- ble diffusion.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Diffuse attend and seg- ment: Unsupervised zero-shot segmentation using sta- ble diffusion

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6edf706-74f6-4ce5-b22c-e60b22a790e0 · outbound

This paper cites Score-cam: Score-weighted visual explanations for con- volutional neural networks.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Score-cam: Score-weighted visual explanations for con- volutional neural networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b92084-ac3d-49c9-9461-2ecc8d13aaa0 · outbound

This paper cites Salient object detection: a mini review.Frontiers in Signal Pro- cessing, 4:1356793, 2024.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Salient object detection: a mini review.Frontiers in Signal Pro- cessing, 4:1356793, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21869549-ca5a-4640-b08e-587eb84d3cd2 · outbound

This paper cites Dave: Distribution-aware attribution via vit gradient decompo- sition.arXiv preprint arXiv:2602.06613, 2026.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Dave: Distribution-aware attribution via vit gradient decompo- sition.arXiv preprint arXiv:2602.06613, 2026

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa8ab7f-f167-42f5-894f-4a3319f007c1 · outbound

This paper cites Learning deep features for discriminative localization.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Learning deep features for discriminative localization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35dbe31d-a43b-4b0a-806b-e1a1a9c1884c · outbound

This paper cites Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac3c488-cbdf-4e40-8d65-134a03dec76d · outbound

This paper cites informa- tion removal.

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks informa- tion removal

Reference 28

Resolution: malformed identifier; no resolver link, observed 2026-07-13T04:59:35.053286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.