Paper Citation Record · LEDGER

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters

As of 12 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2501.16677.

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

pith.paper-citation-record.v1
2501.16677 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T11:32:52.154908Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

41 of 41 outbound references displayed

verified exact1
verified fuzzy34
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14d3fc98-f16f-4b4f-8eee-1af16f91246c · outbound

This paper cites an unresolved cited work.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T11:32:52.802992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8db2d3f0-12e2-4df1-b6de-7a5aba065397 · outbound

This paper cites Constraint answer set programming without grounding.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Constraint answer set programming without grounding

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.789067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fc72755d-0790-40db-979e-cf86471404d6 · outbound

This paper cites Knowledge representation, reasoning and declarative problem solving.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Knowledge representation, reasoning and declarative problem solving

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.775091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a31e186b-d073-4d31-8171-41f103d2b6ab · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T11:32:51.985922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2c5387a-b433-4a39-8daa-bda702d6c688 · outbound

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

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Imagenet: A large-scale hierarchical image database

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.761023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 49d140bc-365c-4e6b-a50f-68a6c92c642d · outbound

This paper cites Extraction of Salient Sentences from Labelled Documents.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Extraction of Salient Sentences from Labelled Documents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T11:32:51.996324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d869f987-e973-4151-bb8a-e04810b0724e · outbound

This paper cites Accelerating convolutional neural networks via activation map compression.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Accelerating convolutional neural networks via activation map compression

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.746011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 84d29843-e496-4108-b94b-6157f34be560 · outbound

This paper cites an unresolved cited work.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-10T11:32:52.731861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 587588be-2e3f-4629-8269-afdf6a5ef1bb · outbound

This paper cites Deep learning using computer vision in self driving cars for lane and traffic sign detection.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Deep learning using computer vision in self driving cars for lane and traffic sign detection

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.717636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7ec34b2c-3d8b-4783-9b91-59193ffc4373 · outbound

This paper cites Elite backprop: Training sparse interpretable neurons.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Elite backprop: Training sparse interpretable neurons

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.702570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e652e7fe-cb75-4748-8d05-22e8e9142184 · outbound

This paper cites Sparseout: Controlling sparsity in deep networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Sparseout: Controlling sparsity in deep networks

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.687629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b145313b-9b8d-4c77-af72-9727bcabb4c9 · outbound

This paper cites Kingma and Jimmy Ba.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Kingma and Jimmy Ba

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.672306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db18f75c-983b-41aa-a614-ee88e17d6104 · outbound

This paper cites Survey of computer vision-based natural disaster warning systems.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Survey of computer vision-based natural disaster warning systems

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.656599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7e07c972-2b66-4245-a379-ed4c54a0864f · outbound

This paper cites Inducing and exploiting activation sparsity for fast inference on deep neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Inducing and exploiting activation sparsity for fast inference on deep neural networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.640343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 44c22370-ba91-4a76-849c-7bb8996a1e4d · outbound

This paper cites Human evaluation of models built for interpretability.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Human evaluation of models built for interpretability

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.625016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 554948d1-f779-4375-bf73-56eaf2d585a0 · outbound

This paper cites Boser, John S.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Boser, John S

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.609753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 693406c0-79d8-404d-9e62-68eff65cdacc · outbound

This paper cites Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.594877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 10d15724-04e7-403c-8d88-37192f7101ef · outbound

This paper cites Training interpretable convolutional neural networks by differentiating class-specific filters.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Training interpretable convolutional neural networks by differentiating class-specific filters

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.579788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 716cf457-32f6-439c-afcd-b7f4c29f299f · outbound

This paper cites A survey of sparse-learning methods for deep neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters A survey of sparse-learning methods for deep neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.565067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b82596f0-1272-4d37-a5d0-7e1c7e627495 · outbound

This paper cites Extracting meaningful high-fidelity knowledge from convolutional neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Extracting meaningful high-fidelity knowledge from convolutional neural networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.550865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 79290388-0f69-4d25-bb6c-c48e8e01fe4d · outbound

This paper cites Nesyfold: A framework for interpretable image classification.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Nesyfold: A framework for interpretable image classification

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.535618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fb1b4db8-c131-4553-81be-86d661dcdfce · outbound

This paper cites Using logic programming and kernel-grouping for improving interpretability of convolutional neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Using logic programming and kernel-grouping for improving interpretability of convolutional neural networks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.520201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4d7c583b-1908-47f3-bed4-9fc692c6bb43 · outbound

This paper cites A neurosymbolic framework for bias correction in convolutional neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters A neurosymbolic framework for bias correction in convolutional neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.503866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 588aab22-0dd3-4a5c-b233-b90d84c7921b · outbound

This paper cites Toward transparent ai: A survey on interpreting the inner structures of deep neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Toward transparent ai: A survey on interpreting the inner structures of deep neural networks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.488699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e82e04e0-4281-422d-9fce-b8ac289d6d24 · outbound

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

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.473405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eee9b09a-8340-4a8a-82f0-ac854e484c33 · outbound

This paper cites Interpretable Compositional Convolutional Neural Networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Interpretable Compositional Convolutional Neural Networks

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-10T11:32:52.216630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b4786d22-9c95-4193-a4ae-543af7e3634f · outbound

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

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T11:32:52.090430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75daf983-68df-4bc1-ad6e-a9ad283f49ae · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Dropout: a simple way to prevent neural networks from overfitting

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.458184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6fe596e4-9e5f-4cd1-a553-9222dd5be815 · outbound

This paper cites Stallkamp, M.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Stallkamp, M

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.443397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8c7a8b10-c7f4-481b-a89f-f14d43f52be2 · outbound

This paper cites Sun, Bin Zheng, and Wei Qian.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Sun, Bin Zheng, and Wei Qian

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.429085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2aebf047-ab92-4c00-9880-fc05b9a2ae85 · outbound

This paper cites Tickle, R.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Tickle, R

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.413444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 016cb92e-aa73-486a-8ef5-ed9dad7f1b99 · outbound

This paper cites Eric: Extracting relations inferred from convolutions.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Eric: Extracting relations inferred from convolutions

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.398016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 87b5c97d-edf9-4f7f-90c1-19be3aa52dec · outbound

This paper cites On the explainability of convolutional layers for multi-class problems.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters On the explainability of convolutional layers for multi-class problems

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.383127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4a3e6669-28f4-429a-8993-a09d8352ef53 · outbound

This paper cites FOLD-SE: an efficient rule-based machine learning algorithm with scalable explainability.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters FOLD-SE: an efficient rule-based machine learning algorithm with scalable explainability

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.368442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 26d2b18c-fc7d-4977-9198-134500c02bfe · outbound

This paper cites Dasnet: Dynamic activation sparsity for neural network efficiency improvement.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Dasnet: Dynamic activation sparsity for neural network efficiency improvement

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.353837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9663c9f3-1da9-43ba-b7fe-d28b747b6608 · outbound

This paper cites Visualizing and understanding convolutional networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Visualizing and understanding convolutional networks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.337655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 493b5fc3-465f-4d13-b294-f08a69952793 · outbound

This paper cites Interpretable convolutional neural networks.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Interpretable convolutional neural networks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.322091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6e11a1cb-1f7b-499f-a386-a9bcd53d8ddd · outbound

This paper cites A survey on neural network interpretability.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters A survey on neural network interpretability

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.306917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bb3234f1-1892-40e4-addc-387ae7694b8a · outbound

This paper cites Object detectors emerge in deep scene cnns.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Object detectors emerge in deep scene cnns

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.290984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7338714f-ac22-4c52-a950-f9f332bc5daf · outbound

This paper cites Places: A 10 million image database for scene recognition, 2017.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters Places: A 10 million image database for scene recognition, 2017

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T11:32:52.275592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7bedd5c4-64a9-428d-bf83-884a5abc8d83 · outbound

This paper cites write newline.

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters write newline

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T11:32:52.154908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.