Pith. sign in

Paper Citation Record · LEDGER

Optimizers Qualitatively Alter Solutions And We Should Leverage This

As of 8 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 7 inbound Pith citation observations for arXiv:2507.12224.

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

pith.paper-citation-record.v1
2507.12224 v1

Coverage vector

measured 81 of 81 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:56:21.795284Z

measured 88 of 88 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T04:22:15.304977Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

81 of 81 outbound references displayed

  • verified exact6
  • verified fuzzy38
  • unresolved34
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch3

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 13570ae0-c803-4c82-a256-42816735eadf · outbound

This paper cites High-dimensional dynamics of generalization error in neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This High-dimensional dynamics of generalization error in neural networks

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.467822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.467822Z digest=sha256:a2778cb8e75ddfbbbcba086d12437bac1a2a0b821b69b4a4b01c0f1d11cc364b

Observation c861194e-09b7-4c0a-9422-0e3ca5c8b8ce · outbound

This paper cites Selfless Sequential Learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Selfless Sequential Learning

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:56:23.128971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.475398Z digest=sha256:f881f6114f7a8490a0725e7cade1eeea81026b205dc2d51368c90ce1b6e2f6ba

Observation 1ced9c68-3efb-49c0-841c-13e4a47293cb · outbound

This paper cites Learning and generalization in overparame- terized neural networks, going beyond two layers.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Learning and generalization in overparame- terized neural networks, going beyond two layers

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.479422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.479422Z digest=sha256:0106d689db79df5b7a6c1a026e44e430a33ad9260cce362ea1887f9f0805756a

Observation c6b3db26-9fae-4090-bc2b-9192ce5efafe · outbound

This paper cites Natural gradient works efficiently in learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Natural gradient works efficiently in learning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.483888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.483888Z digest=sha256:4de0b607590aaa14d2004c70fccdc31685be5890f90a01c4571e19107490a31e

Observation bd3a1dca-2e74-4d63-807d-c75ec80a60bf · outbound

This paper cites When does preconditioning help or hurt generalization? 2020.

Optimizers Qualitatively Alter Solutions And We Should Leverage This When does preconditioning help or hurt generalization? 2020

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:30.616739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.488150Z digest=sha256:1eda90144103f2a1a26e8b7b72eb8491ecf4588b7e59ff5a8339405dcaffcd39

Observation 75d79d22-da28-4cff-8d4b-0e060bc218a3 · outbound

This paper cites Implicit Regularization in Deep Matrix Factorization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Implicit Regularization in Deep Matrix Factorization

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.492418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.492418Z digest=sha256:e444b6cb3cf58a742be9501fb6aa6a934d051f6b99d6df778bd4046546fdde91

Observation 469237c1-e7b6-4730-92df-245978afd23e · outbound

This paper cites Implicit Gradient Regularization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Implicit Gradient Regularization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.496667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.496667Z digest=sha256:250ea13ecd844a2bdb5468a1d44843a585f7e9c7a66b86f29818b4dfceb5918c

Observation d74e641f-4675-4159-b3b4-deee2d616393 · outbound

This paper cites Reconciling modern machine- learning practice and the classical bias–variance trade-off.Proceedings of the National Academy of Sciences, 116(32):15849–15854, July 2019.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Reconciling modern machine- learning practice and the classical bias–variance trade-off.Proceedings of the National Academy of Sciences, 116(32):15849–15854, July 2019

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.500701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.500701Z digest=sha256:3cd50303d83c46893e5a515f5ca1d03203676b07b02682d3675945f35792ef66

Observation 6c954426-2e54-4417-9e31-17200f66ee3f · outbound

This paper cites Learning deep architectures for ai.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Learning deep architectures for ai

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:30.433864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.504094Z digest=sha256:94b7d81e05680d7e4d0c865e219c2378dc56aa1309dc80cb73abc4e44ad606b2

Observation 7a367dce-023b-49e0-8bfc-301d37fdac82 · outbound

This paper cites Scaling Learning Algorithms towards AI.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Scaling Learning Algorithms towards AI

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:30.261518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.508763Z digest=sha256:d2c477fa19b10afac2370d8643b56682c0e39b54df612675b00a014a3961b46a

Observation f8b94d34-9176-4b24-85ca-32bdc4d9e6a5 · outbound

This paper cites Greedy layer-wise training of deep networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Greedy layer-wise training of deep networks

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:30.092830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.512251Z digest=sha256:d05dba3c6ccca53bff6668378d28fc3d6c89f0e4a926f62a990d04336e5bd24f

Observation f437dcf3-da5b-4491-ae2a-ae9c67b16592 · outbound

This paper cites Old Optimizer, New Norm: An Anthology.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Old Optimizer, New Norm: An Anthology

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.515682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.515682Z digest=sha256:0a9f96a1c2f2e76342661442b58718982d3248a452fe10b62d1c5b94b66683fe

Observation b4d81502-93b5-4350-9b9e-fc621a306351 · outbound

This paper cites The tradeoffs of large scale learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This The tradeoffs of large scale learning

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.873526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.519396Z digest=sha256:e2ef3d49f0fdd968352a3038baa4cafde6c3e4aee6806f477322c81294e7763d

Observation a88f1dc2-487e-4c30-acd5-6bf3c6df2934 · outbound

This paper cites Large scale online learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Large scale online learning

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.734055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.522553Z digest=sha256:fd907cce03cb947c46e060d322cc5c9a5d0a3e8c755fe0bb91795eaa5183d426

Observation cccf5ace-63da-43b2-b3e6-004ac0f53179 · outbound

This paper cites Entropy-SGD: Biasing Gradient Descent Into Wide Valleys.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.526427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.526427Z digest=sha256:45f45df4d1cbec1d6b507fdf76806b77e8f401f1ce7e47bf3034342d002db546

Observation 5c1c6b40-1bd1-4546-b316-d76d6c9cba97 · outbound

This paper cites On lazy training in differentiable program- ming.

Optimizers Qualitatively Alter Solutions And We Should Leverage This On lazy training in differentiable program- ming

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.654561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.530713Z digest=sha256:a94b241005fe3434003499b6abcbfbc9e5269d7698546d813c72332228e658a9

Observation 897a9b41-108d-48dd-8398-a46d9495f9e3 · outbound

This paper cites Open problem: The landscape of the loss surfaces of multilayer networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Open problem: The landscape of the loss surfaces of multilayer networks

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.463766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.534425Z digest=sha256:85d9942aa6982c1cdeaf43e301bfa958f3c8a37a72c527b14a2c2b9b009f3505

Observation 2c8e19f8-6588-489a-bffe-2d40ea1ab63f · outbound

This paper cites Turing completeness of bounded-precision recurrent neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Turing completeness of bounded-precision recurrent neural networks

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.323915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.537875Z digest=sha256:139d115af27fde8ca432583b8dc4a974ebcc9dfb320bc45ce8f8bcc4cadfa92f

Observation cb33a1e1-0e8e-4737-b102-94d04b97af92 · outbound

This paper cites Dauphin, Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, Surya Ganguli, and Yoshua Bengio.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Dauphin, Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, Surya Ganguli, and Yoshua Bengio

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.166063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.541561Z digest=sha256:098d878c02abec5df73b91783e80a9d13cfe664094a9390e3a6d356d51de77bf

Observation 2f3d241c-f3e2-4a1f-87b8-a99034d1aba4 · outbound

This paper cites A continual learning survey: Defying forgetting in classification tasks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This A continual learning survey: Defying forgetting in classification tasks

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.545762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.545762Z digest=sha256:969806149c5026d4cd248a6221c012e42707cb80c8e2970e2d60367972cf96bd

Observation f38362ca-12a6-4277-bd76-3dc258c2e9a9 · outbound

This paper cites Sharp Minima Can Generalize For Deep Nets.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Sharp Minima Can Generalize For Deep Nets

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.549446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.549446Z digest=sha256:b8f92880a9efedb780e27d72dc0cb0369b080b948f6ce31387869c722d6ecd44

Observation 747d978e-5c6b-4ff7-b248-63468021947f · outbound

This paper cites A theoretical analysis of catastrophic forgetting through the ntk overlap matrix.

Optimizers Qualitatively Alter Solutions And We Should Leverage This A theoretical analysis of catastrophic forgetting through the ntk overlap matrix

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:29.005838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.554410Z digest=sha256:e751c31571510a2b837e7d853a114d7fc430bac63918018b7cc239858371cc7c

Observation 6141deb0-1f43-459e-96cb-e193431be8df · outbound

This paper cites Continual Backprop: Stochastic Gradient Descent with Persistent Randomness.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Continual Backprop: Stochastic Gradient Descent with Persistent Randomness

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.558771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.558771Z digest=sha256:1fde1dab343d24ca800049e085716c045b86e3d27c407f332072fcb09367b15a

Observation 533c354a-1237-4521-8eea-3d0e96f81c26 · outbound

This paper cites Asynchronous Algorithmic Alignment with Cocycles.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Asynchronous Algorithmic Alignment with Cocycles

Reference 24

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:56:22.860575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.562471Z digest=sha256:23c59418095fd3125694b7567021da14271c3acfcc0ded07374bb097f3027893

Observation 5a17fd0e-87a3-43c1-91bb-c1fa4d784c60 · outbound

This paper cites an unresolved cited work.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:56:28.862630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.566076Z digest=sha256:1efad4bfd616e6ac2d5f753d3988874c95e41e23e7a26fdad4a20d6eaeff9c97

Observation 2ce53fbe-13c8-4c2b-8b45-f872f7a585b7 · outbound

This paper cites Model-agnostic meta-learning for fast adap- tation of deep networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Model-agnostic meta-learning for fast adap- tation of deep networks

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:28.723255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.569208Z digest=sha256:6e9cbba386e9a80be7d3755258ff45883860072369f1d95d4b0f87a8cd028f1f

Observation 748c4011-b463-402d-bf87-4c1765fdf4d1 · outbound

This paper cites Sharpness-aware min- imization for efficiently improving generalization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Sharpness-aware min- imization for efficiently improving generalization

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:28.523574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.572373Z digest=sha256:9ccf35b166f8ab863657bd8d80ecc529748d90214777a82ca0560c136d6cac80

Observation 3d8970fe-db91-4f42-9aad-da7d2f3aef40 · outbound

This paper cites Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error

Reference 28

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:56:22.690277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.576383Z digest=sha256:9bf86a25cfd23ed9c0a57c5e2610b60ba592cacba1b5a71a836e6edb88016295

Observation 4423f3ef-2552-47a3-8430-f043af68336f · outbound

This paper cites Revisiting "Qualitatively Characterizing Neural Network Optimization Problems".

Optimizers Qualitatively Alter Solutions And We Should Leverage This Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.580819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.580819Z digest=sha256:38b4b6692579e868af415da2748a0b72460f26718cbad65e6a5fc05b29dc8925

Observation e99111d3-feea-48eb-9c4c-a060c2c3a578 · outbound

This paper cites Catastrophic forgetting in connectionist networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Catastrophic forgetting in connectionist networks

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.585238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.585238Z digest=sha256:b12723bcc77ca9f6a7c43d78207859f30676e50aa9a25346a9238efe87eb95dd

Observation 8fc44f1c-50f2-4069-aedb-1965d9cbc189 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Understanding the difficulty of training deep feedforward neural networks

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.590032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.590032Z digest=sha256:94ed87e9229ce11c52beb10214675922bfa72390d49d7c75be87bb56b6cc4151

Observation 74f2a661-6894-4837-87f7-d2b82d47b602 · outbound

This paper cites Qualitatively characterizing neural network optimization problems.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Qualitatively characterizing neural network optimization problems

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.594131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.594131Z digest=sha256:e28c761f926e5d7dd4ac4f90b5735b6e7f47ca1912e2afe1976719c78300a6d9

Observation 649a1ff6-5400-477a-baf2-c2bdd9b365ac · outbound

This paper cites Understanding Human Intelligence through Human Limitations.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Understanding Human Intelligence through Human Limitations

Reference 33

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:56:22.572734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.598106Z digest=sha256:4abfe1b1a25dbd30b290f6ec88d730b701f44a1feb268a8731459c9cd7c56d9a

Observation e096c52e-540f-41ac-81ed-8e44415590fe · outbound

This paper cites Shampoo: Preconditioned Stochastic Tensor Optimization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Shampoo: Preconditioned Stochastic Tensor Optimization

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.602594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.602594Z digest=sha256:0cdeb08e0bae09db505130b70475450019857c1bc2e87d94ec93e2261d47ef36

Observation db15b856-f66e-4d4e-b3ec-c971c6daf38f · outbound

This paper cites Embracing change: Con- tinual learning in deep neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Embracing change: Con- tinual learning in deep neural networks

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:28.383613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.606621Z digest=sha256:3d9e2ef5e6fe7811e4c377d1580d44c69f23dde9fbbe016c0a1914faafd3df35

Observation 183dc493-937b-4249-b4c0-1c1bde22c7eb · outbound

This paper cites Hinton, Simon Osindero, and Yee-Whye Teh.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Hinton, Simon Osindero, and Yee-Whye Teh

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.610852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.610852Z digest=sha256:42cb31cb97ed42536a06f25b49921e359d442372d17a642a17fcb255b7834c59

Observation 307206eb-0756-4a36-8062-2ba85e6ca0c7 · outbound

This paper cites Flat minima.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Flat minima

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:28.254650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.614692Z digest=sha256:fd3ed72116965756e4ac5c0fd58e799e77e8f49c343baf00c54046ecd3f909eb

Observation 5d73982b-3a2c-4759-8c88-2b84449b89f0 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Neural tangent kernel: Convergence and generalization in neural networks

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:28.078427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.623377Z digest=sha256:c61f5ec5bb0f30c8e78cb948d7f54f49919b18791900236498b9608083100b63

Observation ee7fef34-9400-438d-b218-134a9bf34e45 · outbound

This paper cites On large-batch training for deep learning: Generalization gap and sharp minima.

Optimizers Qualitatively Alter Solutions And We Should Leverage This On large-batch training for deep learning: Generalization gap and sharp minima

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:27.930579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.627836Z digest=sha256:7aa99a339941170f4017eefc33cd4c1ca684c33c6afda497590e71db64303d67

Observation a6fe436c-01cc-4d29-9308-3ea4bb61447d · outbound

This paper cites Overcoming catastrophic forgetting in neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Overcoming catastrophic forgetting in neural networks

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:27.752349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.631796Z digest=sha256:83dbffe58c6461c56f9c7a63e37675e4f39b91b3e0b746d7b8e79f5bcd84ea47

Observation 48c7779c-780a-4606-80b1-9b85a2aeab88 · outbound

This paper cites an unresolved cited work.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:56:27.484674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.635133Z digest=sha256:b410d7daa960f1b14c05279677b8e3c7cc65b44d6dd4409b799533dda7bf159c

Observation db085b21-2a5c-4f87-9168-714a28f61086 · outbound

This paper cites Continual learning as computationally constrained reinforcement learning,.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Continual learning as computationally constrained reinforcement learning,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:27.212185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.639198Z digest=sha256:24a42e1d7b3824d35d5fc52d5f93edc09a08810ffec05e08b38081d56fd4310e

Observation 819bd0a4-46c5-4350-af74-4e54a6d3fd83 · outbound

This paper cites Maintaining plasticity in continual learning via regenerative regularization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Maintaining plasticity in continual learning via regenerative regularization

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:26.926652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.647639Z digest=sha256:799fd7294e0356460f1c8aed722fe4220a465579e0f75e2a57d9d6fcc2ff78e8

Observation 63676b0b-fc29-4d39-8843-a0624f97ee0a · outbound

This paper cites Asam: Adaptive sharpness- aware minimization for scale-invariant learning of deep neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Asam: Adaptive sharpness- aware minimization for scale-invariant learning of deep neural networks

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:26.601834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.651391Z digest=sha256:f9a9a5e0c65526740ac97563518160c4c2b297a28fde1899f88ac713be7b6eb8

Observation 2aa990dd-260d-4548-ac0f-1101d963f5c6 · outbound

This paper cites Directions of Curvature as an Explanation for Loss of Plasticity.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Directions of Curvature as an Explanation for Loss of Plasticity

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.655160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.655160Z digest=sha256:338473ce11beeb6cac2fb6e1d59028100d55cda75cff035a2612829651c81bb9

Observation adc807cc-fcd1-4d0e-a0a9-53bb9be0348c · outbound

This paper cites Visualizing the loss landscape of neural nets.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Visualizing the loss landscape of neural nets

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.658641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.658641Z digest=sha256:8deb97a38ea762f3ce9b2965a48b99e586ef89ca18e651402d96a8d5ea82e359

Observation 7fd628e2-70aa-47bf-9edf-94d1570dffcf · outbound

This paper cites Lifelong machine learning: a paradigm for continuous learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Lifelong machine learning: a paradigm for continuous learning

Reference 47

Resolution
verified exact
doi, observed 2026-08-06T16:56:21.855586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.662211Z digest=sha256:fa982ed7d9360e2b769d4a15887695dc34d56c3450b7bb1a44c5e2dae2faf1d4

Observation 913c656a-b05d-4b2f-91cf-253cc678ab29 · outbound

This paper cites Decoupled weight decay regularization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Decoupled weight decay regularization

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:26.384343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.665480Z digest=sha256:63079a824d5ea48bfc5f98a3446f216a42705decff6c1f594084113f04788929

Observation 17701754-01ef-4999-b64c-6710e8f1b639 · outbound

This paper cites Understanding and preventing capacity loss in reinforcement learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Understanding and preventing capacity loss in reinforcement learning

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:26.153675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.669910Z digest=sha256:2548fd234fef9f0603a8aaca47b14729a5fed33c6318683718b73887c73d0ebf

Observation 630a4362-d18f-413f-b6a6-adf0362d1db5 · outbound

This paper cites Normalization and effective learning rates in reinforcement learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Normalization and effective learning rates in reinforcement learning

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.673962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.673962Z digest=sha256:3843b037cd8ca03d34043182c1da66806d0c1778a98e8b02b622301a4e5306ac

Observation d6fa2383-3b1f-46e4-992d-8a1fb0ec6dd6 · outbound

This paper cites Deep learning via hessian-free optimization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Deep learning via hessian-free optimization

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.989876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.678241Z digest=sha256:652fd74fdc257b9e8555f96009f35ceb1064463201f47ad7a8a483512780dfaf

Observation 5af0d7bc-5368-4437-852f-fb5568339785 · outbound

This paper cites Optimizing neural networks with kronecker-factored approximate curvature.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Optimizing neural networks with kronecker-factored approximate curvature

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.854507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.682177Z digest=sha256:6735712567806398899b2e0f0b29e3d3dddc09d7e6dda7f9c23efe62311c9e12

Observation caf21fdf-cd44-4892-81fc-b19b2cc60d3c · outbound

This paper cites A logical calculus of ideas immanent in nervous activity.

Optimizers Qualitatively Alter Solutions And We Should Leverage This A logical calculus of ideas immanent in nervous activity

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.654686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.685963Z digest=sha256:a2e47f194ca19907a1cd6ad948c306057a388ebe221a243b2ebf8f6f017206fc

Observation 82978154-a992-458c-a17e-dc9b852ae374 · outbound

This paper cites Minsky and S.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Minsky and S

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.690306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.690306Z digest=sha256:adee0fbc7ba213b89000d9ff68e957b7e17e1ff02a3291e5b8ce7003a7de8bc6

Observation 970ae01c-cc50-475c-bf09-adef742c8997 · outbound

This paper cites Deep Double Descent: Where Bigger Models and More Data Hurt.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Deep Double Descent: Where Bigger Models and More Data Hurt

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.695553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.695553Z digest=sha256:9cb89985330cbe30eff8430d79501592cd495036453cad96b939ff62f1081978

Observation cea9d834-c83b-450e-8b08-1d6be0821226 · outbound

This paper cites Adding Gradient Noise Improves Learning for Very Deep Networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Adding Gradient Noise Improves Learning for Very Deep Networks

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.702106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.702106Z digest=sha256:4eb11adeb90bf6220eeaaf9b960d605f369212952fb521c2c0584cc3a0bd5577

Observation 01faa2ae-dc30-4a2b-87ba-cd6e7f7ea44f · outbound

This paper cites Nerem, Samantha Chen, Sanjoy Dasgupta, and Yusu Wang.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Nerem, Samantha Chen, Sanjoy Dasgupta, and Yusu Wang

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.453270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.706811Z digest=sha256:f8183a6a550353b985fed4b75615fa2959fbabf51dd460857d747e3a009fcf44

Observation e9fd9b8b-fbad-451d-9a91-2826cd7e9c6d · outbound

This paper cites The role of over-parametrization in generalization of neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This The role of over-parametrization in generalization of neural networks

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.287275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.711669Z digest=sha256:4b585378176e31546ffbf078d89a9cbef5f24a9936beb68c6e5077d23817c217

Observation 14ad059f-ef90-43f4-9999-33d25112112b · outbound

This paper cites The primacy bias in deep reinforcement learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This The primacy bias in deep reinforcement learning

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:25.084726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.716896Z digest=sha256:3fb58e2dbcd9d1e53b7310e659f4e9aba56bae8be19dfef3d9e2939966825cff

Observation 2af4951e-ab45-44ef-9173-c56ed9f9879d · outbound

This paper cites an unresolved cited work.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Unresolved cited work

Reference 60

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:56:24.884761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.720672Z digest=sha256:aa9f7685925950b351d67aad4dda37f78b682731785abd45abbd4db49b69a39d

Observation 8e907d35-ea9a-4bbd-9ef6-088c10674983 · outbound

This paper cites Parisi, Ronald Kemker, Jose L.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Parisi, Ronald Kemker, Jose L

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.724002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.724002Z digest=sha256:cab10a11dc60e0a96cac57555b9a155c69d95dc822414dab79bf2eb220b1f53c

Observation 70c4ea2c-accf-4f09-a21d-989d6c64c7ec · outbound

This paper cites On the difficulty of training recurrent neural networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This On the difficulty of training recurrent neural networks

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:24.683654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.729228Z digest=sha256:b61239a1f47ae2353a654389ee786c00b31f7f39b639416cb80be2e837d99b49

Observation ba82417c-4173-43cb-94cc-50a52999137c · outbound

This paper cites Attention is turing-complete.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Attention is turing-complete

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:24.486896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.733132Z digest=sha256:0abf8f38e43f594964287e196987fefe0dd74b99c396759e87925e68b15febb8

Observation ccc01c0b-7d82-4986-9011-f4fb2b6bae0a · outbound

This paper cites Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards.Advances in Neural Information Processing Systems, 36:71095–71134, 2023.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards.Advances in Neural Information Processing Systems, 36:71095–71134, 2023

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.736663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.736663Z digest=sha256:3da00ab518cf834d02d8efa91ddea1a39dcdd3adaf0d2d274c48a1e3831f809a

Observation 41fefeee-fcff-4ced-afe2-5453345380fe · outbound

This paper cites Sparse feature learning for deep belief networks.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Sparse feature learning for deep belief networks

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:24.314260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.740365Z digest=sha256:8d3a9202588b8f48b177b9be6d3424f3880da3ae536e77b999767ee5acbfa5a6

Observation 2abcd8ad-7b84-4540-803b-2e23f22134c1 · outbound

This paper cites Catastrophic forgetting, rehearsal and pseudorehearsal.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Catastrophic forgetting, rehearsal and pseudorehearsal

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:24.150680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.745316Z digest=sha256:2b86df750d35a059015a9207c4058f9374148d96477bbd699a40c4ca89842fd0

Observation d0787047-6e70-4db6-8cb5-1eb6f747225c · outbound

This paper cites Learning representations by back-propagating errors.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Learning representations by back-propagating errors

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.749382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.749382Z digest=sha256:eac2586fb0d51a3781cb5f804d66820923dcd91bf0f078a426bbb7ffcaf3224c

Observation 6d4b1a62-8a4b-4cd1-9609-d6012d52c572 · outbound

This paper cites Powerpropagation: A sparsity inducing weight reparameterisation.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Powerpropagation: A sparsity inducing weight reparameterisation

Reference 68

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T16:56:22.402190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.753998Z digest=sha256:660ca6769796c5857613db8550e6acebd3bf88dbb196a9e4b14a011ce3563ec5

Observation 5d888c67-2052-4fc8-a5d2-9c29096aaf87 · outbound

This paper cites Siegelmann and Eduardo D.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Siegelmann and Eduardo D

Reference 69

Resolution
metadata mismatch
raw_fallback, observed 2026-08-06T16:56:22.315614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.758148Z digest=sha256:957916acd0a109bc36e66f66248d927370d7da86c7c4ca098a8d7c03efabaf34

Observation 60bd0630-9ce9-4918-898c-aa2c69d96970 · outbound

This paper cites Mas- tering the game of go with deep neural networks and tree search.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Mas- tering the game of go with deep neural networks and tree search

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.761700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.761700Z digest=sha256:a77545aaff41fdfe92f1c0ae11d5b78d945accb2829730cd3a6c8703cfe2a5c4

Observation 41cc8397-c1ef-4b93-9646-216a1161b522 · outbound

This paper cites WoodFisher: Efficient Second-Order Approximation for Neural Network Compression.

Optimizers Qualitatively Alter Solutions And We Should Leverage This WoodFisher: Efficient Second-Order Approximation for Neural Network Compression

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.765182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.765182Z digest=sha256:6d44f75eec597f40a45a014f08067551f2cc2988337bce4231cc96248fb51946

Observation 39c4365f-3c07-4803-b417-de3d7d4e2665 · outbound

This paper cites Smith, Benoit Dherin, David G.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Smith, Benoit Dherin, David G

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:23.935503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.768961Z digest=sha256:270c9154c150b825bd2069359573f3cde2726ee323e0f2e7c4770dbcbfde9e60

Observation 10454d02-8d6a-44cb-b5a3-6814fff80c8f · outbound

This paper cites The dormant neuron phenomenon in deep reinforcement learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This The dormant neuron phenomenon in deep reinforcement learning

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:23.767904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.772384Z digest=sha256:c3a4db0373da57d291b666f802e87de2d70247b1dc22424d7b9e85bb413b26a8

Observation ad3d97d5-c93b-44aa-89c3-64d736760e38 · outbound

This paper cites an unresolved cited work.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Unresolved cited work

Reference 74

Resolution
metadata mismatch
raw_fallback, observed 2026-08-06T16:56:22.072229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.776254Z digest=sha256:3d5c00e274d22bfee7310f9fcae81cfc1a52ef17a2bb540a8d748aba1d5aeabf

Observation de7735b9-1187-464c-bb52-f47bd1ca6156 · outbound

This paper cites Practical issues in temporal difference learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Practical issues in temporal difference learning

Reference 75

Resolution
verified exact
doi, observed 2026-08-06T16:56:21.830160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.780085Z digest=sha256:57554b86f8c404ccbe2d4da5b09f80905d1f00bfe53b10648b5110e9355a7585

Observation 2bdeb531-d658-48bc-84d6-22d574178a35 · outbound

This paper cites softmax is not enough (for sharp out-of-distribution), 2024.

Optimizers Qualitatively Alter Solutions And We Should Leverage This softmax is not enough (for sharp out-of-distribution), 2024

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:23.620325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.784093Z digest=sha256:9e9e7d57a467b509952f2fb944e88aeb7fb8b5f80fc9bb9d08f2bf25e367c4a6

Observation 68a370e2-71c8-466f-a177-0ae4efb0e478 · outbound

This paper cites an unresolved cited work.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Unresolved cited work

Reference 77

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:56:23.476911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.787654Z digest=sha256:0b555d0d13977511be182771e4baf2a8b32e31173ba7580a4c9fe5d0156da381

Observation e2fdba17-1994-4f6a-8d86-50d22a5138f6 · outbound

This paper cites Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:23.367835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.791861Z digest=sha256:6d835c510897af23a95fe71cd9100bb9c113dfd86700c457fab5be4a0ec230f5

Observation 9d010b2b-867e-4758-8081-bdf40138134c · outbound

This paper cites Understanding deep learning requires rethinking generalization.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Understanding deep learning requires rethinking generalization

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:56:23.232897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:56:21.795284Z digest=sha256:7d24e6290f9949632fc87fbd2418b58b766b7b343d499b1df84d87471ece5573

Observation d7fdcfc5-ba3f-4363-82b7-80dd833a5ddb · outbound

This paper cites doi: 10.1162/neco.1997.9.1.1.

Optimizers Qualitatively Alter Solutions And We Should Leverage This doi: 10.1162/neco.1997.9.1.1

Reference 1997

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.618591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.618591Z digest=sha256:d482a6749ac9b7779b5d6236eb1641a3d28d6ad063847263e7e50703e32b9ff0

Observation c080a08e-0bfc-46c1-a6fa-cf97e8b436c5 · outbound

This paper cites Continual Learning as Computationally Constrained Reinforcement Learning.

Optimizers Qualitatively Alter Solutions And We Should Leverage This Continual Learning as Computationally Constrained Reinforcement Learning

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T16:56:21.643315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:56:21.643315Z digest=sha256:891a204e635e424fc585770b60e668efd68ec909b86f07f713b24fd16412736d

Pith citing papers

Observation 125f7d68-abbc-497f-a761-6eddc3f384fd · inbound

Cross-Model Semantics in Representation Learning cites this paper.

Cross-Model Semantics in Representation Learning Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T04:22:15.304977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T04:22:15.304977Z digest=sha256:93354812af31b1e0e3c7566a51999a9af1726cb9f67af5fa85bf7778fcc5eee7

Observation 558ba87f-680f-4c22-aa79-602ef4f30be9 · inbound

How does the optimizer implicitly bias the model merging loss landscape? cites this paper.

How does the optimizer implicitly bias the model merging loss landscape? Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-05-18T09:51:13.425976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-18T09:49:41.550981Z digest=sha256:42ff4acfaae25809caa31586563f204a49439490449484d1516dc70df56228cb

Observation 3ef28a47-5dc6-4f83-a96d-f73b047389de · inbound

Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization cites this paper.

Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 30

Resolution
metadata mismatch
arxiv_id, observed 2026-05-10T00:24:46.477571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-10T00:21:37.686664Z digest=sha256:2bd0ddd000e1abdbaef8bbc32bb18cf40b44a90de6b2602d1e00cf4329da793f

Observation 79f339b7-602b-4362-8404-1d07f0f08213 · inbound

Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws cites this paper.

Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-22T08:51:18.269939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-22T08:49:32.864065Z digest=sha256:917d7677eb5e05745ad74e4c11fa3b0b4d993efa2939da504c5c62491f7ee4a8

Observation 0751ef79-8d03-46b6-8692-4a2254da0e66 · inbound

How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks cites this paper.

How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 4

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T18:03:48.001449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-29T17:59:03.152111Z digest=sha256:7068361c85678d0be88faad42ae18c0858aeae1859972738578e492517a8181f

Observation e611b25f-9546-4e74-86f1-1ac495debd39 · inbound

Overcoming Rank Collapse in Feedback Alignment cites this paper.

Overcoming Rank Collapse in Feedback Alignment Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-07-03T04:27:37.207966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-27T13:52:57.960921Z digest=sha256:f10ab7e7f56f1bd55395b51529dd40f55f568806dc05973ef0af81bec88314c8

Observation 8f9fb4d3-38b5-4b8a-b259-256ee344464b · inbound

Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks cites this paper.

Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks Optimizers Qualitatively Alter Solutions And We Should Leverage This

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T17:31:48.677047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T17:31:48.677047Z digest=sha256:67c5c9ec6f62d04658de8cc04127fcc146d446243ed438b53f76e75c3876a57f