Paper Citation Record · LEDGER

Removing Spurious Correlation from Neural Network Interpretations

As of 16 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2412.02893.

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

pith.paper-citation-record.v1
2412.02893 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T23:03:10.792600Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

40 of 40 outbound references displayed

verified exact1
verified fuzzy20
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c0e96038-af1b-42da-a0cd-8cbb53fa2cd3 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Removing Spurious Correlation from Neural Network Interpretations Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.415793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8813695c-9589-4ca4-b227-b68b6be13b96 · outbound

This paper cites End-to-end balancing for causal continuous treatment-effect estimation.

Removing Spurious Correlation from Neural Network Interpretations End-to-end balancing for causal continuous treatment-effect estimation

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.642306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b11f9691-ce65-4dd5-8c6e-a1d43f5ad644 · outbound

This paper cites Doubly robust estimation in missing data and causal inference models.

Removing Spurious Correlation from Neural Network Interpretations Doubly robust estimation in missing data and causal inference models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.444057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39962766-6330-4195-a76e-140c5a28fc1b · outbound

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

Removing Spurious Correlation from Neural Network Interpretations Mechanistic Interpretability for AI Safety -- A Review

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.460413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be338bf-0174-45cb-9930-de80369cec19 · outbound

This paper cites Double/debiased machine learning for treatment and structural parameters.

Removing Spurious Correlation from Neural Network Interpretations Double/debiased machine learning for treatment and structural parameters

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.475716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee864271-5a6f-404b-a52a-aa9888a92e27 · outbound

This paper cites Applied Causal Inference Powered by ML and AI.

Removing Spurious Correlation from Neural Network Interpretations Applied Causal Inference Powered by ML and AI

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.548910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e9d2a4a3-8789-4d2d-b2da-e389ef68ae85 · outbound

This paper cites Constructing inverse probability weights for marginal structural models.

Removing Spurious Correlation from Neural Network Interpretations Constructing inverse probability weights for marginal structural models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.498686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c62d0225-1a9c-49f0-ab68-e6a3effcb39a · outbound

This paper cites Dealing with limited overlap in estimation of average treatment effects.

Removing Spurious Correlation from Neural Network Interpretations Dealing with limited overlap in estimation of average treatment effects

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.496715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8866e95f-7f9b-412a-9b2c-eae5d978fa2a · outbound

This paper cites Causal inference without counterfactuals.

Removing Spurious Correlation from Neural Network Interpretations Causal inference without counterfactuals

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.422120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39e83c64-351a-49f4-b3e7-dfe79847037a · outbound

This paper cites Fitting science into legal contexts: assessing effects of causes or causes of effects? Sociological Methods & Research, 43 0 (3): 0 359--390, 2014.

Removing Spurious Correlation from Neural Network Interpretations Fitting science into legal contexts: assessing effects of causes or causes of effects? Sociological Methods & Research, 43 0 (3): 0 359--390, 2014

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.376827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9a3e67a8-c56c-4d6d-8d57-f89f602f4dc1 · outbound

This paper cites an unresolved cited work.

Removing Spurious Correlation from Neural Network Interpretations Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-11T23:03:12.272746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f91f921c-9d61-479e-b452-bb24ad7085ce · outbound

This paper cites Entropy balancing for causal effects: A multivariate reweighting method to produce balanced samples in observational studies.

Removing Spurious Correlation from Neural Network Interpretations Entropy balancing for causal effects: A multivariate reweighting method to produce balanced samples in observational studies

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.235370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5c9d44bc-0600-456b-8d37-548995291d89 · outbound

This paper cites Nonparametric estimation of mediation effects with a general treatment.

Removing Spurious Correlation from Neural Network Interpretations Nonparametric estimation of mediation effects with a general treatment

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.181322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5e75dc42-9438-4244-8ea0-41c97e46ebb5 · outbound

This paper cites Direct and indirect effects of continuous treatments based on generalized propensity score weighting.

Removing Spurious Correlation from Neural Network Interpretations Direct and indirect effects of continuous treatments based on generalized propensity score weighting

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.146981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6d7e3382-c920-4984-b000-720d00d597e3 · outbound

This paper cites A general approach to causal mediation analysis.

Removing Spurious Correlation from Neural Network Interpretations A general approach to causal mediation analysis

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:12.088239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1e74449e-8bba-4255-858f-1b7156257fe7 · outbound

This paper cites Causal inference in statistics, social, and biomedical sciences.

Removing Spurious Correlation from Neural Network Interpretations Causal inference in statistics, social, and biomedical sciences

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.590686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edf4b4c6-0571-4b6f-8cb4-84049ab20f6d · outbound

This paper cites Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data.

Removing Spurious Correlation from Neural Network Interpretations Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.596447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b31fc431-f57a-4e4f-bd8a-8ff9ab2ab1b6 · outbound

This paper cites Probabilities of Causation for Continuous and Vector Variables.

Removing Spurious Correlation from Neural Network Interpretations Probabilities of Causation for Continuous and Vector Variables

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:03:11.077248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c35cb807-7ccc-4489-9305-7691c197ecc6 · outbound

This paper cites Bloom: A 176b-parameter open-access multilingual language model.

Removing Spurious Correlation from Neural Network Interpretations Bloom: A 176b-parameter open-access multilingual language model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.609185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb54a353-1cb9-4107-82d8-6c2bec01acbf · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Removing Spurious Correlation from Neural Network Interpretations RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.619651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b62b4c9-c4dd-4243-80c8-175b235b8974 · outbound

This paper cites Evaluating causes of effects by posterior effects of causes.

Removing Spurious Correlation from Neural Network Interpretations Evaluating causes of effects by posterior effects of causes

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.935563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 982dd65e-e8ef-4621-899b-f168b1420f37 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Removing Spurious Correlation from Neural Network Interpretations Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.635804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f1edc7d-15b4-425a-8083-58cf74ee515e · outbound

This paper cites Locating and editing factual associations in gpt.

Removing Spurious Correlation from Neural Network Interpretations Locating and editing factual associations in gpt

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.902042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a77b9d1f-9f1f-4195-8630-63059de75c4c · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Removing Spurious Correlation from Neural Network Interpretations Progress measures for grokking via mechanistic interpretability

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.850544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b98c4eb4-1e69-4d53-aa48-c96cd6a08a91 · outbound

This paper cites Zoom in: An introduction to circuits.

Removing Spurious Correlation from Neural Network Interpretations Zoom in: An introduction to circuits

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.807078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e961309f-0e51-4f48-bad5-dd371a60868d · outbound

This paper cites In-context Learning and Induction Heads.

Removing Spurious Correlation from Neural Network Interpretations In-context Learning and Induction Heads

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.662269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb1e8584-239e-447a-ad0d-e8a53816f95d · outbound

This paper cites Causality.

Removing Spurious Correlation from Neural Network Interpretations Causality

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.669065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f2eae3-ea5b-4a32-977f-3914646d5f5e · outbound

This paper cites Mediation analysis methods used in observational research: a scoping review and recommendations.

Removing Spurious Correlation from Neural Network Interpretations Mediation analysis methods used in observational research: a scoping review and recommendations

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.731799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cbca35ab-b8ba-4260-8493-2ded1518caa0 · outbound

This paper cites Marginal structural models and causal inference in epidemiology.

Removing Spurious Correlation from Neural Network Interpretations Marginal structural models and causal inference in epidemiology

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.685001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 581240d9-d479-44e2-94da-35fcb798cc59 · outbound

This paper cites Does matching overcome lalonde's critique of nonexperimental estimators? Journal of econometrics, 125 0 (1-2): 0 305--353, 2005.

Removing Spurious Correlation from Neural Network Interpretations Does matching overcome lalonde's critique of nonexperimental estimators? Journal of econometrics, 125 0 (1-2): 0 305--353, 2005

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.686359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3761583-fe8d-415b-8b4c-de2b927004f5 · outbound

This paper cites A mechanistic interpretation of arithmetic reasoning in language models using causal mediation analysis.

Removing Spurious Correlation from Neural Network Interpretations A mechanistic interpretation of arithmetic reasoning in language models using causal mediation analysis

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.596548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aa236b89-dcb8-49a3-858e-20b570fd5223 · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.

Removing Spurious Correlation from Neural Network Interpretations Investigating gender bias in language models using causal mediation analysis

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.557947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a88242f1-b954-42f1-9658-cdec1aeeca48 · outbound

This paper cites Minimal dispersion approximately balancing weights: asymptotic properties and practical considerations.

Removing Spurious Correlation from Neural Network Interpretations Minimal dispersion approximately balancing weights: asymptotic properties and practical considerations

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.703436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b8df8d1-d9fa-40df-9d40-6a7da5b6a40a · outbound

This paper cites Unlearning bias in language models by partitioning gradients.

Removing Spurious Correlation from Neural Network Interpretations Unlearning bias in language models by partitioning gradients

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.493574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cd67a6fa-275a-493f-b9ba-0fa0d62c964c · outbound

This paper cites Towards best practices of activation patching in language models: Metrics and methods.

Removing Spurious Correlation from Neural Network Interpretations Towards best practices of activation patching in language models: Metrics and methods

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.720899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20aa07d9-6726-448a-8acf-bad55245916b · outbound

This paper cites Conditional counterfactual causal effect for individual attribution.

Removing Spurious Correlation from Neural Network Interpretations Conditional counterfactual causal effect for individual attribution

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.381073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a5b97f54-8da0-4c03-9e27-3c25ba3a4554 · outbound

This paper cites A boosting algorithm for estimating generalized propensity scores with continuous treatments.

Removing Spurious Correlation from Neural Network Interpretations A boosting algorithm for estimating generalized propensity scores with continuous treatments

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:03:11.337964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7a01a4e9-685b-4581-b74d-95a75c0c8869 · outbound

This paper cites @esa (Ref.

Removing Spurious Correlation from Neural Network Interpretations @esa (Ref

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.765880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ada2ef1-5bee-41a8-af19-c473ae27d751 · outbound

This paper cites an unresolved cited work.

Removing Spurious Correlation from Neural Network Interpretations Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.783594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07fe9ccb-2b20-411f-ba91-3906b2393cb6 · outbound

This paper cites Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability.

Removing Spurious Correlation from Neural Network Interpretations Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T23:03:10.792600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.