Paper Citation Record · LEDGER

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization

As of 13 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 1 inbound Pith citation observation for arXiv:2506.01562.

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

pith.paper-citation-record.v1
2506.01562 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:47:49.751969Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:00:14.874974Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

51 of 51 outbound references displayed

verified exact2
verified fuzzy28
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ab3b4c37-b4bb-472e-aa64-032669103ab5 · outbound

This paper cites A winner-take-all circuit with controllable soft max property.Advances in neural information processing systems, 12, 1999.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization A winner-take-all circuit with controllable soft max property.Advances in neural information processing systems, 12, 1999

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.571351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9d75b7ac-6440-42fb-8c66-cb78ae20f921 · outbound

This paper cites softmax.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization softmax

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.533455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8437d16b-a3de-4daa-9928-c0887467c068 · outbound

This paper cites A new method for mapping optimization problems onto neural networks.International Journal of Neural Systems, 01(01):3–22, 1989.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization A new method for mapping optimization problems onto neural networks.International Journal of Neural Systems, 01(01):3–22, 1989

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.511609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4f742ca0-9cad-459b-9a06-2244323bace2 · outbound

This paper cites Vision Transformers Need Registers.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Vision Transformers Need Registers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.112259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4b6c1e4-3096-4514-b3d3-3a6639d37572 · outbound

This paper cites Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:47:50.296691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0180009e-c6fa-4221-bed8-b9445945debb · outbound

This paper cites A Study on ReLU and Softmax in Transformer.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization A Study on ReLU and Softmax in Transformer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.179741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a76731f-eeea-45cb-b6fd-293fcb67fe68 · outbound

This paper cites Stabilizing transformer training by preventing attention entropy collapse.ICML, 2023.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Stabilizing transformer training by preventing attention entropy collapse.ICML, 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.482434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8ebed281-e686-4580-8573-9687df3802a8 · outbound

This paper cites Attention is all you need.Advances in Neural Information Processing Systems, 2017.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Attention is all you need.Advances in Neural Information Processing Systems, 2017

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.260038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93713977-decc-4c99-9c24-831e584a387a · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.294009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a4efe5-5535-4ade-bb54-d010c379fc7f · outbound

This paper cites Rethink- ing softmax: Self-attention with polynomial activations.arXiv preprint arXiv:2410.18613, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Rethink- ing softmax: Self-attention with polynomial activations.arXiv preprint arXiv:2410.18613, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.337504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c125d649-43ce-4369-910f-d547675c7ca4 · outbound

This paper cites Theory, Analysis, and Best Practices for Sigmoid Self-Attention.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.381114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 502f144d-255c-4571-a1f7-9cbd9963274d · outbound

This paper cites Softmax is not Enough (for Sharp Size Generalisation).

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Softmax is not Enough (for Sharp Size Generalisation)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.416924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76bd1fc5-fcc7-4dfb-8808-c289325cccb3 · outbound

This paper cites an unresolved cited work.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.451983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dadcae8-70f2-4fab-abe3-67306367b0f5 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.487110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f34807-3851-4804-9898-79fe0263527f · outbound

This paper cites Symmetry induces structure and constraint of learning, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Symmetry induces structure and constraint of learning, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.434075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e582693a-02fc-4ce6-a280-a07b03afd34a · outbound

This paper cites Neural collapse: A review on modelling principles and generalization, 2023.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Neural collapse: A review on modelling principles and generalization, 2023

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.410135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b618e917-f7e9-425b-9b5c-a8be1b53e2e9 · outbound

This paper cites The impact of geometric complexity on neural collapse in transfer learning, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization The impact of geometric complexity on neural collapse in transfer learning, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.389578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dd3c4ada-fabc-41f5-b9f3-ec02d214ae92 · outbound

This paper cites Linking neural collapse and l2 normaliza- tion with improved out-of-distribution detection in deep neural networks, 2023.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Linking neural collapse and l2 normaliza- tion with improved out-of-distribution detection in deep neural networks, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.368180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 37d1e400-f529-4401-b89d-b1d304182c1d · outbound

This paper cites Neco: Neural collapse based out-of-distribution detection, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Neco: Neural collapse based out-of-distribution detection, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.345945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 17a45861-3a9b-430d-b69e-eb6bd4bef5b9 · outbound

This paper cites Controlling neural collapse enhances out-of-distribution detection and transfer learning, 2025.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Controlling neural collapse enhances out-of-distribution detection and transfer learning, 2025

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.324376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f9916fa9-17f8-4c9b-b127-e4d703f27fe6 · outbound

This paper cites Stabilizing contrastive RL: Techniques for robotic goal reach- ing from offline data.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Stabilizing contrastive RL: Techniques for robotic goal reach- ing from offline data

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.306838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1250c486-98ec-44e8-95c4-37b2615cb2d7 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization A simple framework for contrastive learning of visual representations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.815739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e5f79c7-3b23-4e39-a161-1d9f4de7e87a · outbound

This paper cites Understanding dimensional collapse in contrastive self-supervised learning.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Understanding dimensional collapse in contrastive self-supervised learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:04.276406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3c85aade-ac9c-4e0d-a313-5ab7023053c1 · outbound

This paper cites Layer Normalization.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Layer Normalization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.897192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e1ced30-9038-400b-8fa3-03406285e9e9 · outbound

This paper cites Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:47:50.044834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fbd41b7d-22a3-453c-8b6a-f76976d1a7c1 · outbound

This paper cites Feature learning in deep classifiers through intermediate neural collapse.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Feature learning in deep classifiers through intermediate neural collapse

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:48:03.972561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 05ef6ed1-0d12-43d4-8af4-8e4876df592e · outbound

This paper cites Neural collapse in the intermediate hidden layers of classification neural networks, 2023.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Neural collapse in the intermediate hidden layers of classification neural networks, 2023

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:52.174772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 21844186-37e1-4f96-b804-5419f7f75c88 · outbound

This paper cites Neural collapse for unconstrained feature model under cross- entropy loss with imbalanced data.Journal of Machine Learning Research, 25(192):1–48, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Neural collapse for unconstrained feature model under cross- entropy loss with imbalanced data.Journal of Machine Learning Research, 25(192):1–48, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:52.057386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2fee971d-efc5-4ff8-95c9-9a66d31d565c · outbound

This paper cites Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.091855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52792a87-8b2a-43f7-8cbb-92e2ff5f2999 · outbound

This paper cites On calibration of modern neural networks.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization On calibration of modern neural networks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:52.005226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7ae6816f-d2d6-4704-90b9-7095994821fd · outbound

This paper cites Aero: Softmax-only llms for efficient private inference, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Aero: Softmax-only llms for efficient private inference, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.919074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fff056e8-939e-4b96-9a16-edfdd7cd2435 · outbound

This paper cites What Variables Affect Out-of-Distribution Generalization in Pretrained Models?.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization What Variables Affect Out-of-Distribution Generalization in Pretrained Models?

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:47:49.916692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 241cd7df-ff91-44f2-8a33-67774fb6abf3 · outbound

This paper cites The tunnel effect: Building data representations in deep neural networks.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization The tunnel effect: Building data representations in deep neural networks

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.859474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f97d748b-3052-415c-8409-b0cf00cc9c0a · outbound

This paper cites Head2toe: Utilizing intermediate representations for better transfer learning.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Head2toe: Utilizing intermediate representations for better transfer learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.280377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d11e27b-ac49-4526-aa05-3f1b4104e563 · outbound

This paper cites Linguistic collapse: Neural collapse in (large) language models, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Linguistic collapse: Neural collapse in (large) language models, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.798211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9af57330-f6fa-465d-9566-12e8e8dd8470 · outbound

This paper cites Very deep convolutional networks for large-scale image recognition.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Very deep convolutional networks for large-scale image recognition

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.358091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e19a2b-a102-4200-bdd1-8bbfd518ab86 · outbound

This paper cites Deep residual learning for image recognition.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Deep residual learning for image recognition

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.394697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5da4a5e3-79cd-48db-9fc0-e1d966cb20ec · outbound

This paper cites Feed-forward neural networks.Ieee Potentials, 13(4):27–31, 1994.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Feed-forward neural networks.Ieee Potentials, 13(4):27–31, 1994

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.594432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1119e0c4-4989-4419-abd2-aed413efc3bc · outbound

This paper cites Learning multiple layers of features from tiny images, 2009.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Learning multiple layers of features from tiny images, 2009

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.483397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c0651f-884b-46ca-be12-4b649a223759 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Imagenet: A large-scale hierarchical image database

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.430508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e100bf5f-04b2-4174-9093-575d3203b65d · outbound

This paper cites Pytorch image models.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Pytorch image models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.582764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a91398a-6149-4c93-86b1-37b250663ff7 · outbound

This paper cites Rethinking the value of network pruning, 2019.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Rethinking the value of network pruning, 2019

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.214752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6fdf9718-f5e1-4444-9883-9b0a72542c85 · outbound

This paper cites Deep neural collapse is provably optimal for the deep unconstrained features model.Advances in Neural Information Processing Systems, 36:52991–53024, 2023.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Deep neural collapse is provably optimal for the deep unconstrained features model.Advances in Neural Information Processing Systems, 36:52991–53024, 2023

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:51.043847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 44943e71-f571-46ba-9a5e-e8a56a75dc74 · outbound

This paper cites Weight decay induces low-rank attention layers.Advances in Neural Information Processing Systems, 37:4481–4510, 2024.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Weight decay induces low-rank attention layers.Advances in Neural Information Processing Systems, 37:4481–4510, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:50.916520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 31365ae5-0ae5-4e4e-a73a-38888e2adc1d · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, 2015.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, 2015

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T11:47:00.718513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cf670d5-a2d1-450c-b15e-e54db2d4217a · outbound

This paper cites An unconstrained layer- peeled perspective on neural collapse.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization An unconstrained layer- peeled perspective on neural collapse

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:50.847224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bccc7a54-32d1-4ecd-8284-a823f7765990 · outbound

This paper cites Gerschgorin.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Gerschgorin

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:50.736202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ab369cdd-b8f9-45bd-822b-5dba8436f324 · outbound

This paper cites This differs fundamentally from our direct measurement of pre-softmaxlogits, which directly impact model decisions.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization This differs fundamentally from our direct measurement of pre-softmaxlogits, which directly impact model decisions

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:50.645779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 29f20ba1-5b15-4cd5-b787-b93ec021ce11 · outbound

This paper cites This setup was recently shown to induce a low-rank bias [44].

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization This setup was recently shown to induce a low-rank bias [44]

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:47:50.572938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bff357f1-3844-4637-86d8-075749bd45b4 · outbound

This paper cites an unresolved cited work.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:47:50.477179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c404b6df-405a-4881-be73-981cb9e1096f · outbound

This paper cites an unresolved cited work.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:47:50.385895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation 7eb00b84-6ccc-4e33-91f7-944b3fd7f28d · inbound

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization cites this paper.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:14.874974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.