Paper Citation Record · LEDGER

Learning Important Features Through Propagating Activation Differences

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:1704.02685.

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

pith.paper-citation-record.v1
1704.02685 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 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 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:30:06.504542Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2380
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 675f4efe-6993-4b44-a5cb-3500bb701eba · inbound

A study on the Interpretability of Neural Retrieval Models using DeepSHAP cites this paper.

A study on the Interpretability of Neural Retrieval Models using DeepSHAP Learning Important Features Through Propagating Activation Differences

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-24T21:29:57.917152Z

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.

Observation 75e2a77b-097e-4f9a-9004-39a300f7d72d · inbound

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation cites this paper.

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation Learning Important Features Through Propagating Activation Differences

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-22T23:42:15.837217Z

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.

Observation e71c7618-c264-473f-870c-39d0299013c5 · inbound

GraphPINE: Graph Importance Propagation for Interpretable Drug Response Prediction cites this paper.

GraphPINE: Graph Importance Propagation for Interpretable Drug Response Prediction Learning Important Features Through Propagating Activation Differences

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-22T20:32:04.701912Z

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.

Observation fb2955fa-c980-43bf-8675-7ee3cc8e4fb1 · inbound

Towards a Science of Causal Interpretability in Deep Learning for Software Engineering cites this paper.

Towards a Science of Causal Interpretability in Deep Learning for Software Engineering Learning Important Features Through Propagating Activation Differences

Reference 255

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:06.504542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6c51a7c-edb3-4245-8373-c256b201d1a8 · inbound

ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Things cites this paper.

ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Things Learning Important Features Through Propagating Activation Differences

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:52:00.299995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b062630-51d7-4802-9225-e9e3f1d9a6de · inbound

Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence cites this paper.

Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence Learning Important Features Through Propagating Activation Differences

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:57:13.034205Z

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.

Observation 4f988c9f-1342-4fdf-988e-16367e8b4591 · inbound

inMOTIFin: a lightweight end-to-end simulation software for regulatory sequences cites this paper.

inMOTIFin: a lightweight end-to-end simulation software for regulatory sequences Learning Important Features Through Propagating Activation Differences

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T22:47:07.056227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0817d12-450e-4c55-8251-e4d2fc251488 · inbound

Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization cites this paper.

Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization Learning Important Features Through Propagating Activation Differences

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T20:22:02.354648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96da55c4-e1c4-4df1-ba41-921fdebdfa03 · inbound

Towards Verified and Targeted Explanations through Formal Methods cites this paper.

Towards Verified and Targeted Explanations through Formal Methods Learning Important Features Through Propagating Activation Differences

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T11:54:05.610252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e141bd0-ef96-40af-a2d4-399d3c63cf45 · inbound

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models cites this paper.

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models Learning Important Features Through Propagating Activation Differences

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:26:09.604896Z

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.

Observation 6af4c60c-d316-426f-8101-40d94595cae8 · inbound

Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality cites this paper.

Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality Learning Important Features Through Propagating Activation Differences

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:26.154901Z

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.

Observation 819df1f1-acf1-4928-8893-edf16c9af887 · inbound

Transferable 3D Convolutional Neural Networks for Elastic Constants Prediction in Nanoporous Metals cites this paper.

Transferable 3D Convolutional Neural Networks for Elastic Constants Prediction in Nanoporous Metals Learning Important Features Through Propagating Activation Differences

Reference 68

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T04:29:34.474856Z

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.

Observation 2e89680d-52ad-4b25-951e-612da51b3d57 · inbound

CNN-Based Online Trigger for QGP Event Selection cites this paper.

CNN-Based Online Trigger for QGP Event Selection Learning Important Features Through Propagating Activation Differences

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:13:52.752978Z

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.

Observation e3346c6a-f2ac-4ba9-90e2-6f4c4e8b33e9 · inbound

How Many Trees in a Random Forest? A Revisited Approach with Plateau Search and Optuna Integration cites this paper.

How Many Trees in a Random Forest? A Revisited Approach with Plateau Search and Optuna Integration Learning Important Features Through Propagating Activation Differences

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.795102Z

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.

Observation 154cab12-7b1a-406b-8967-50542f795779 · inbound

XtrAIn: Training-Guided Occlusion for Feature Attribution cites this paper.

XtrAIn: Training-Guided Occlusion for Feature Attribution Learning Important Features Through Propagating Activation Differences

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:47:38.385019Z

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.

Observation 09fe6d1a-2992-4509-80f7-b6e2eebf6b92 · inbound

Interpreting Parton Distributions with Shapley Values cites this paper.

Interpreting Parton Distributions with Shapley Values Learning Important Features Through Propagating Activation Differences

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T07:57:20.566670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.