Paper Citation Record · LEDGER

Harmonic Loss Trains Interpretable AI Models

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2502.01628.

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

pith.paper-citation-record.v1
2502.01628 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T14:52:24.316919Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

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

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact1
verified fuzzy12
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 102a43c6-6c10-44c2-a2c9-d720c7e8c292 · outbound

This paper cites Sensitivity and Generalization in Neural Networks: an Empirical Study.

Harmonic Loss Trains Interpretable AI Models Sensitivity and Generalization in Neural Networks: an Empirical Study

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.178284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a7662aa-3bf3-4142-a0e0-aa8436a774d3 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Harmonic Loss Trains Interpretable AI Models Mechanistic Interpretability for AI Safety -- A Review

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.183100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44def21d-3d22-47a6-ac37-c4f8835322bd · outbound

This paper cites Deepspeed data efficiency: Improving deep learning model quality and training efficiency via efficient data sampling and routing.

Harmonic Loss Trains Interpretable AI Models Deepspeed data efficiency: Improving deep learning model quality and training efficiency via efficient data sampling and routing

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.905351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 67aba9e7-0b4a-45ed-849d-bae551cd6f3f · outbound

This paper cites Patch diffusion: Faster and more data-efficient training of diffusion models.

Harmonic Loss Trains Interpretable AI Models Patch diffusion: Faster and more data-efficient training of diffusion models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.894701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1680d706-828c-4864-8ef8-9906365643ff · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Harmonic Loss Trains Interpretable AI Models Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.194973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d404136-77dd-4203-bcc0-ae3449fd358f · outbound

This paper cites Towards Out-Of-Distribution Generalization: A Survey.

Harmonic Loss Trains Interpretable AI Models Towards Out-Of-Distribution Generalization: A Survey

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.198888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88716a04-3edf-4fea-9aef-34ed59ddd9fb · outbound

This paper cites The clock and the pizza: Two stories in mechanistic explanation of neural networks.

Harmonic Loss Trains Interpretable AI Models The clock and the pizza: Two stories in mechanistic explanation of neural networks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.883493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 20da7631-c5b4-4c0b-aaf2-9966d38eade9 · outbound

This paper cites Omnigrok: Grokking Beyond Algorithmic Data.

Harmonic Loss Trains Interpretable AI Models Omnigrok: Grokking Beyond Algorithmic Data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.206473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7334ddb7-91ef-42aa-a822-410f898160cb · outbound

This paper cites Zoom in: An introduction to circuits.

Harmonic Loss Trains Interpretable AI Models Zoom in: An introduction to circuits

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.210577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578f3ed6-7282-4f8e-9702-7dc8d71f438c · outbound

This paper cites Function Vectors in Large Language Models.

Harmonic Loss Trains Interpretable AI Models Function Vectors in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.214327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a4bad1f-eefa-4a1c-99a3-97f616ee2db1 · outbound

This paper cites Language Models Represent Space and Time.

Harmonic Loss Trains Interpretable AI Models Language Models Represent Space and Time

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.218471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc1cf0a9-e9ab-4928-923d-493eadee344d · outbound

This paper cites Implicit Representations of Meaning in Neural Language Models.

Harmonic Loss Trains Interpretable AI Models Implicit Representations of Meaning in Neural Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.222318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef7e79c9-0a31-4841-af6c-f798d1e5a39b · outbound

This paper cites Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color.

Harmonic Loss Trains Interpretable AI Models Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.225953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab92dcf-5c92-422e-ac3c-5366dc57c62b · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Harmonic Loss Trains Interpretable AI Models The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.229613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07a406c5-166e-43b3-be6d-e6a19395c2e7 · outbound

This paper cites Monotonic Representation of Numeric Properties in Language Models.

Harmonic Loss Trains Interpretable AI Models Monotonic Representation of Numeric Properties in Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-09T14:52:24.656332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2b9a855a-6b4b-4a76-a015-8918834e4232 · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Harmonic Loss Trains Interpretable AI Models The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.236880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4de17097-1730-48ff-ba7a-b9005720c448 · outbound

This paper cites Opening the AI black box: program synthesis via mechanistic interpretability.

Harmonic Loss Trains Interpretable AI Models Opening the AI black box: program synthesis via mechanistic interpretability

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.240283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b3b621-fc1d-42a2-a252-82566c9b5a5e · outbound

This paper cites The Geometry of Concepts: Sparse Autoencoder Feature Structure.

Harmonic Loss Trains Interpretable AI Models The Geometry of Concepts: Sparse Autoencoder Feature Structure

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.243940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53388a2-3ccf-4462-b05b-63196849e882 · outbound

This paper cites ICLR: In-Context Learning of Representations.

Harmonic Loss Trains Interpretable AI Models ICLR: In-Context Learning of Representations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.247836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0596d9c-7117-44d0-aabd-2f8668a99bfb · outbound

This paper cites Towards understanding grokking: An effective theory of representation learning.

Harmonic Loss Trains Interpretable AI Models Towards understanding grokking: An effective theory of representation learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.872293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bd548730-d06c-4725-b01c-4da06c7ccaeb · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

Harmonic Loss Trains Interpretable AI Models Not All Language Model Features Are One-Dimensionally Linear

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.255125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8975b174-8c9b-47c2-a032-a986e02cb2b7 · outbound

This paper cites Enhancing hydrological extremes prediction accuracy: Integrating diverse loss functions in transformer models.

Harmonic Loss Trains Interpretable AI Models Enhancing hydrological extremes prediction accuracy: Integrating diverse loss functions in transformer models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.861861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation df756787-b901-4e34-b28d-b81c9d32969a · outbound

This paper cites Echocardiographic image segmenta- tion with vision transformers: A comparative analysis of different loss functions.

Harmonic Loss Trains Interpretable AI Models Echocardiographic image segmenta- tion with vision transformers: A comparative analysis of different loss functions

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.851232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e4651027-5d4f-4418-8be0-da4ca17e263e · outbound

This paper cites Gener- alised dice overlap as a deep learning loss function for highly unbalanced segmentations.

Harmonic Loss Trains Interpretable AI Models Gener- alised dice overlap as a deep learning loss function for highly unbalanced segmentations

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.840529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation adcc43a8-544c-40d9-8262-02ae7ae3f4d8 · outbound

This paper cites Topology-aware focal loss for 3d image segmentation.

Harmonic Loss Trains Interpretable AI Models Topology-aware focal loss for 3d image segmentation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.829391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c38495d7-4411-404c-9824-1f9b2efd383e · outbound

This paper cites Tversky loss function for image segmentation using 3d fully convolutional deep networks.

Harmonic Loss Trains Interpretable AI Models Tversky loss function for image segmentation using 3d fully convolutional deep networks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.273581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93213a57-2a8b-4f5d-9f71-8accc736c23e · outbound

This paper cites Hybrid wind speed forecasting using iceemdan and transformer model with novel loss function.

Harmonic Loss Trains Interpretable AI Models Hybrid wind speed forecasting using iceemdan and transformer model with novel loss function

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.807305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fef288ef-69fb-4244-a4ea-d2999bdd3ab1 · outbound

This paper cites Predicting o-glcnacylation sites in mammalian proteins with transformers and rnns trained with a new loss function.

Harmonic Loss Trains Interpretable AI Models Predicting o-glcnacylation sites in mammalian proteins with transformers and rnns trained with a new loss function

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.281383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913822dd-9408-4016-852b-5bb9354c221b · outbound

This paper cites I-Con: A Unifying Framework for Representation Learning.

Harmonic Loss Trains Interpretable AI Models I-Con: A Unifying Framework for Representation Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.285184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04f2b07-6152-4a75-b14c-e52c1a0d58a8 · outbound

This paper cites A comprehensive survey of loss functions in machine learning.

Harmonic Loss Trains Interpretable AI Models A comprehensive survey of loss functions in machine learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.796127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e5c3c3f3-b9fa-47d6-8663-35f5875bf35a · outbound

This paper cites Contrastive learning models for sentence representations.

Harmonic Loss Trains Interpretable AI Models Contrastive learning models for sentence representations

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.784963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6e8fb561-82e6-4c68-b26e-9f4f1f776fdf · outbound

This paper cites A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks.

Harmonic Loss Trains Interpretable AI Models A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.296587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbea4976-f0b0-4229-a84f-bc63b8832c69 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Harmonic Loss Trains Interpretable AI Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.300509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8d7f559-92ca-4b96-aa49-1e2bb29e670f · outbound

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

Harmonic Loss Trains Interpretable AI Models Imagenet: A large- scale hierarchical image database

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.304482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972686be-12cd-484a-bb15-64753c8c0ff5 · outbound

This paper cites Supervised contrastive learning.

Harmonic Loss Trains Interpretable AI Models Supervised contrastive learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.308447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600f3437-2ef5-41e2-9932-cfbdf4ce259c · outbound

This paper cites Neural Network Acceptability Judgments.

Harmonic Loss Trains Interpretable AI Models Neural Network Acceptability Judgments

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T14:52:24.312828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d97207b-9cda-404d-81c0-91e8d275e313 · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank.

Harmonic Loss Trains Interpretable AI Models Recursive deep models for semantic compositionality over a sentiment treebank

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:52:24.762016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.