Paper Citation Record · LEDGER

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

As of 4 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 3 inbound Pith citation observations for arXiv:2511.19339.

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

pith.paper-citation-record.v1
2511.19339 v2

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T05:53:18.934088Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:47:11.611722Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T16:59:58.221288Z

Reference resolution

51 of 51 outbound references displayed

verified exact6
verified fuzzy40
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ad1f5114-dcd6-4c6b-9d2a-d035c836e8e4 · outbound

This paper cites Choquette-Choo, Haoche Jia, Adeline Travers, Benjamin Zhang, David Lie, and Nicolas Papernot.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Choquette-Choo, Haoche Jia, Adeline Travers, Benjamin Zhang, David Lie, and Nicolas Papernot

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.679685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 246622b9-6166-43b7-853c-c095ab93b4df · outbound

This paper cites Deep Unlearn: Benchmarking Machine Unlearning for Image Classification.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Deep Unlearn: Benchmarking Machine Unlearning for Image Classification

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:54:08.296493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e122e18e-77e9-49fb-aa0e-acca1c121ff1 · outbound

This paper cites Towards making systems forget with machine unlearning.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Towards making systems forget with machine unlearning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.685852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bd59e9fb-df09-4a39-ba48-b2c380da4f6f · outbound

This paper cites California consumer privacy act of 2018.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse California consumer privacy act of 2018

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.692504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d7c04dae-3d9e-45d3-973c-001db3437437 · outbound

This paper cites Learning to unlearn: Instance- wise unlearning for pre-trained classifiers.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Learning to unlearn: Instance- wise unlearning for pre-trained classifiers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.682678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2b10baca-d693-4d4d-9d47-59ee29d218d4 · outbound

This paper cites Boundary unlearning: Rapid forgetting of deep net- works via shifting the decision boundary.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Boundary unlearning: Rapid forgetting of deep net- works via shifting the decision boundary

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.735791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 42d921d7-2dae-4212-ad6f-eaf792459cfc · outbound

This paper cites Chundawat, Ayush K.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Chundawat, Ayush K

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.768391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a95e553e-1461-47d9-b203-83175cb84bb8 · outbound

This paper cites Chundawat, Ayush K.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Chundawat, Ayush K

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.765915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f3978e26-f783-4125-aef3-7f135eea89f1 · outbound

This paper cites DUCK: Distance-based Unlearning via Centroid Kinematics.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse DUCK: Distance-based Unlearning via Centroid Kinematics

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:54:08.266922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 05247120-5fe3-4605-8360-e493ecfd914e · outbound

This paper cites Neural collapse for cross-entropy class-imbalanced regime.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Neural collapse for cross-entropy class-imbalanced regime

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.751369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f1150826-c2b0-4b17-a43c-937e7d56ebf4 · outbound

This paper cites an unresolved cited work.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-17T05:54:08.773997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f8c6a596-05bb-43f8-9fc6-64402d244133 · outbound

This paper cites Regulation (eu) 2016/679 of the european parliament and of the council of 27 april 2016 (general data protection regulation).

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Regulation (eu) 2016/679 of the european parliament and of the council of 27 april 2016 (general data protection regulation)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.786899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4e930b34-961d-4555-9ce5-019eaf5dafda · outbound

This paper cites Eternal sunshine of the spotless net: Selective forgetting in deep networks.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Eternal sunshine of the spotless net: Selective forgetting in deep networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.704436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 934f736c-b905-4abe-883d-b608604b6f36 · outbound

This paper cites For- getting outside the box: Scrubbing deep networks of informa- tion accessible from input-output observations.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse For- getting outside the box: Scrubbing deep networks of informa- tion accessible from input-output observations

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.745329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation af5cbf4a-906c-4f70-a230-79bbbd3ca882 · outbound

This paper cites Amnesiac machine learning.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Amnesiac machine learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.719471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0be9ecfc-2c29-42f5-8722-d7a74f20b5bf · outbound

This paper cites Certified Data Removal from Machine Learning Models.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Certified Data Removal from Machine Learning Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:54:08.290406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8b29e409-4e9c-4a7c-a99e-ec9e3cc3ba1e · outbound

This paper cites an unresolved cited work.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-17T05:54:08.729280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9e1e7206-23d2-4abd-a4e5-6be249bf9ee4 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Distilling the Knowledge in a Neural Network

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-17T05:54:08.275957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a18474cf-a2cf-4493-ae7a-699c4b5346a7 · outbound

This paper cites Neural collapse for un- constrained feature model under class-imbalanced regime.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Neural collapse for un- constrained feature model under class-imbalanced regime

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.763261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 47273bb1-c2ff-4335-8d9c-cee74a770028 · outbound

This paper cites Wide neural networks trained with weight decay prov- ably exhibit neural collapse.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Wide neural networks trained with weight decay prov- ably exhibit neural collapse

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.817777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ccbf3e2e-74e3-401b-b4f9-e1f65433b43f · outbound

This paper cites Are we truly forgetting? a critical re-examination of machine unlearn- ing evaluation protocols.arXiv preprint arXiv:2503.06991.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Are we truly forgetting? a critical re-examination of machine unlearn- ing evaluation protocols.arXiv preprint arXiv:2503.06991

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:54:08.284097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5632bd3a-99b1-480b-a01b-c70d6e8a1712 · outbound

This paper cites Deep unlearning: Fast and efficient gradient-free class forgetting.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Deep unlearning: Fast and efficient gradient-free class forgetting

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.713834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 15cbd41e-5594-4436-8fb2-17d46a0ae4bd · outbound

This paper cites Similarity of neural network representations revisited.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Similarity of neural network representations revisited

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.689514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0d68600-6ecb-40e9-8190-d2728d3d55ba · outbound

This paper cites Namboodiri.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Namboodiri

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.809260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6d138e96-819a-4034-bac7-1531b2892c53 · outbound

This paper cites Machine unlearning: Taxonomy, metrics, applications, challenges, and prospects.IEEE Trans- actions on Neural Networks and Learning Systems.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Machine unlearning: Taxonomy, metrics, applications, challenges, and prospects.IEEE Trans- actions on Neural Networks and Learning Systems

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.771404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation eeef6aed-48f1-4cc3-b11c-7be67c025e5c · outbound

This paper cites Neural collapse under cross-entropy loss.Applied and Computational Harmonic Analysis, 59:224–241.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Neural collapse under cross-entropy loss.Applied and Computational Harmonic Analysis, 59:224–241

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.803013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d5e9b24e-040d-44c6-8e11-32aa77f01c34 · outbound

This paper cites Han, and David L.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Han, and David L

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.812788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 75ca5fe8-d7f1-4e95-92b3-a95cd7a29e09 · outbound

This paper cites Personal information protection law of the people’s republic of china.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Personal information protection law of the people’s republic of china

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.748299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 331f7d29-10f7-421c-adc1-1e6f933471ef · outbound

This paper cites Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:54:08.256165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 324ed418-70ed-47f4-a067-b3040c4ca016 · outbound

This paper cites Remember what you want to forget: Algorithms for machine unlearning.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Remember what you want to forget: Algorithms for machine unlearning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.726054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2e864658-0c9a-4323-aae0-42efaf495e45 · outbound

This paper cites Fast yet effective machine unlearning.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Fast yet effective machine unlearning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.796562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5cc5630f-49e6-42a9-9bfc-0b5b5b4ed195 · outbound

This paper cites an unresolved cited work.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-05-17T05:54:08.716446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e684d3f3-6f39-4262-a0ec-367457e0ae19 · outbound

This paper cites Neural collapse to multiple centers for imbalanced data.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Neural collapse to multiple centers for imbalanced data

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.790353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74fc9ba9-c965-4c3a-b058-cfb444c0d9ba · outbound

This paper cites Medmnist v2- a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific Data, 10(1):41.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Medmnist v2- a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific Data, 10(1):41

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.698188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation af529448-b8d8-42aa-b90f-51d1ed7fc132 · outbound

This paper cites CLIPErase: Efficient unlearning of visual-textual associations in CLIP.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse CLIPErase: Efficient unlearning of visual-textual associations in CLIP

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.760558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6c1b13af-53a4-40e9-ae63-37b96f88d9cf · outbound

This paper cites Forget-me-not: Learning to forget in text-to- image diffusion models.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Forget-me-not: Learning to forget in text-to- image diffusion models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.783732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 55aa6c0d-e065-4a39-b0ae-e2c478cf8a4c · outbound

This paper cites Decoupled distillation to erase: A general unlearning method for any class-centric tasks.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Decoupled distillation to erase: A general unlearning method for any class-centric tasks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.732828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 51461632-ae0f-4501-b827-38c2c86e4b2f · outbound

This paper cites A geometric analysis of neural collapse with unconstrained features.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse A geometric analysis of neural collapse with unconstrained features

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.738820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9b38c1ab-76b1-41e6-a36d-a7b151005868 · outbound

This paper cites Proof on Decomposition ofK-Bound 1.2.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Proof on Decomposition ofK-Bound 1.2

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.707525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fb9a89a4-2a92-4dc0-a54b-8fd673273c8a · outbound

This paper cites Training Assumptions 2.2.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Training Assumptions 2.2

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.695290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50a2a605-e06d-43aa-919b-839ee7df558d · outbound

This paper cites Geometric Optimality of the Simplex ETF 3.2.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Geometric Optimality of the Simplex ETF 3.2

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.722556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7ed0c2c3-efcf-432f-a083-dbcc7fe784fe · outbound

This paper cites Closure of Projection 4.2.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Closure of Projection 4.2

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.757375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f45a6f16-aba5-4434-9f8b-61d89c69388c · outbound

This paper cites right to be forgotten.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse right to be forgotten

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.754503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e3c3c729-1450-49e7-a63b-8c28cc1ad8f8 · outbound

This paper cites Sekhari et al.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Sekhari et al

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.776902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6767e9b-d24c-49c9-8559-6cfd1d4d7ef2 · outbound

This paper cites Yet, none of the previous approaches con- nects to the phenomenon of Neural Collapse [27], wherein class features converge to a simplex equiangular tight frame.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Yet, none of the previous approaches con- nects to the phenomenon of Neural Collapse [27], wherein class features converge to a simplex equiangular tight frame

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.701557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3c0d5256-8a18-4179-afe3-3c7a1124f93f · outbound

This paper cites an unresolved cited work.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-05-17T05:54:08.742216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c53b1f3c-d8b6-4e58-a84a-3938067020f7 · outbound

This paper cites Proof on Decomposition of K-Bound Let Z denote the feature space and P(Z) the set of prob- ability measures on it.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Proof on Decomposition of K-Bound Let Z denote the feature space and P(Z) the set of prob- ability measures on it

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.799718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bac1d026-69e1-4ba4-b2ca-6603cd443a9d · outbound

This paper cites Training and modeling assumptions.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Training and modeling assumptions

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.805995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 505f7536-70c3-4adc-8bc8-aae244c6c56b · outbound

This paper cites an unresolved cited work.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-05-17T05:54:08.710864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 008fe764-e2c4-4f99-a6b3-3d2825e74093 · outbound

This paper cites Closure of Projection Note that asimplex ETF{v i}C i=1 ⊂R C−1 satisfies ∥vi∥= 1, v ⊤ i vj =− 1 C−1 (i̸=j), CX i=1 vi = 0.

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse Closure of Projection Note that asimplex ETF{v i}C i=1 ⊂R C−1 satisfies ∥vi∥= 1, v ⊤ i vj =− 1 C−1 (i̸=j), CX i=1 vi = 0

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.793483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 28b82201-8dd2-46aa-b09b-b2a8ff7a73cf · outbound

This paper cites 2.(Isotropic Gaussian conditionals)conditional on classi, θ(x)|(y=i)∼ N(µ i, σ2Id), with ∥µi∥= 1 and {µi}C i=1 coinciding with the ETF directions{v i}from NC (i.e.µ i =v i).

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse 2.(Isotropic Gaussian conditionals)conditional on classi, θ(x)|(y=i)∼ N(µ i, σ2Id), with ∥µi∥= 1 and {µi}C i=1 coinciding with the ETF directions{v i}from NC (i.e.µ i =v i)

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T05:54:08.780518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 280c8fa6-0f0f-427a-a528-5ce847e35ff2 · inbound

Erased, but Not Gone: Output Forgetting Is Not True Forgetting cites this paper.

Erased, but Not Gone: Output Forgetting Is Not True Forgetting POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-04T16:59:58.222712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 93f88a65-2018-4b9b-97c4-286e4147dd17 · inbound

Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning cites this paper.

Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T07:47:11.611722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66c8fddf-7666-49b5-949a-a8610fe68cc1 · inbound

DECAF: De-Clustering for Adaptive Representational Unlearning cites this paper.

DECAF: De-Clustering for Adaptive Representational Unlearning POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T23:33:50.093698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.