Pith. sign in

Paper Citation Record · LEDGER

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

As of 22 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 4 inbound Pith citation observations for arXiv:2502.09022.

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

pith.paper-citation-record.v1
2502.09022 v2

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T22:56:40.340931Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:00:23.921056Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T20:02:11.896730Z

Reference resolution

63 of 63 outbound references displayed

  • verified exact1
  • verified fuzzy3
  • unresolved59
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0813fec4-f6cd-4ee8-8e8a-34cf80573ef4 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.873432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.155024Z digest=sha256:dbc53b585296c1ad7a4dcae8bc7b9c70fb33d400d189494f993de69c86abc23b

Observation dc75dc88-8d34-4e7d-a13a-e84b71cc1b7b · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.864491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.158961Z digest=sha256:c810f814caf7af90493f2ec56bb6ce43ed9542e4c8f83ef91bcb9b8a176035a6

Observation 99622c61-d6ba-49a4-addd-7c2519cc15e8 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.162530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.162530Z digest=sha256:c94eeed1697e188f8e7c760bfc394e21528a62291f319b07bf2d56f9977bb712

Observation 02ca970c-d00c-494a-bc2c-2ad6094ef1d4 · outbound

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

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Mechanistic Interpretability for AI Safety -- A Review

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.165340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.165340Z digest=sha256:03a04ba9c850d62df094e7be50c550d4cccc19a03368f231002edbeb1f11c871

Observation be6e1077-d496-46f9-9846-5ab9447e4428 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.168723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.168723Z digest=sha256:cfb2a92a79c96810c6d9559d75bbf7b9be967d1b405e31c1bcbdf72f28f03eb7

Observation 5055ac35-f778-48a6-9173-281356906a89 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.844230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.171548Z digest=sha256:4785cdac757da20e516dd7f57d985dc2a7569cc2826e311bc637b9d70905c451

Observation c956cc55-282c-41fc-85f3-5de6739c306d · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.836468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.174806Z digest=sha256:f31005c4baef6f461080dc23dd5693dfa81e72d49e67ccd6f4f371f4f32085ca

Observation 830b46c1-2b7b-4a40-8070-eaa6cfe44703 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.827974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.177643Z digest=sha256:e83038162de2e569be31b9160c7ed2704d2733589e9f46f7c2635c91372462ff

Observation 9614c710-d999-4c6c-aebc-89a4d137535e · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.819250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.180341Z digest=sha256:8b75a871b5aa1560b0c9c23bced625408b70f86e5c23fd607d91fe9fb84041b0

Observation 9157f702-fcf4-42c0-8bb7-a2b75177e045 · outbound

This paper cites RECKONING: Reasoning through Dynamic Knowledge Encoding.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning RECKONING: Reasoning through Dynamic Knowledge Encoding

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-07T22:56:40.545638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.182915Z digest=sha256:c8ae48612c3b11148bb70cb2dc2b6219c9d6f40e7be5463b889f253630fee034

Observation 5fd1340d-2d41-4ab9-92cf-b08b1c078f09 · outbound

This paper cites Multi-hop Question Answering under Temporal Knowledge Editing.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Multi-hop Question Answering under Temporal Knowledge Editing

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.186806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.186806Z digest=sha256:3ad27236baef31b72fcd4c57a34a909d00387a0c9f64cbe2c1775b1d658f88e2

Observation 3ceb66c1-0b85-4148-82f8-51f03f0e6352 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.810373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.190218Z digest=sha256:10f0dcf0fe3a3177b38e82b5403f9b13648efa7a4ed84eb7d497138b2bd91c36

Observation a9e5c785-dbac-4b0f-858e-a63d09f1fcef · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.801725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.193257Z digest=sha256:392274e50a3dbe55ca18f52593a952cc67574158bc85d719f3e0bced8b3bcf73

Observation e38b4eb0-27d5-44dc-b03b-b720da7adb99 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.792817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.196313Z digest=sha256:7d2d24114512873b7cbe8e39285f546ccbe4bbb224842532e8b8016702db6a17

Observation 45a55f26-0091-456b-a444-d65c05c6e830 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 15

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.784182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.199439Z digest=sha256:542573159c2741ce2f56c21e974c9ca8f74c28c96302d31f1e5736c858831033

Observation b7740c2f-69f3-4a16-a198-602dd61e6a97 · outbound

This paper cites Faithful Reasoning Using Large Language Models.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Faithful Reasoning Using Large Language Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.202648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.202648Z digest=sha256:988659c7f15c52c7a132b37588c03a0f079aadfb61de3fc6fd1ff4b4a2eb5382

Observation a6b2b545-194e-4679-99ad-827c8b864ab8 · outbound

This paper cites Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.206040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.206040Z digest=sha256:a86e63a6f9484189dc96bafd9505543fddd88aee4c8ee123ca746a3bc233dbbc

Observation 79ffdcff-7271-49b9-9b45-2e7c3a338afa · outbound

This paper cites Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, and Yejin Choi.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, and Yejin Choi

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:56:40.775040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.209232Z digest=sha256:76ac99435f8ee135986da7a9100a79049b94a40a5565da7aed1a1ed7d2d8b21a

Observation b4080695-b426-4a33-bb45-7fb03d297750 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.765792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.211903Z digest=sha256:e42169a4b5ba73792305261c82d41d8c0f457f452ff0fe2dc323966055a49c80

Observation afb39936-4507-44ca-bfb8-2d42cead22de · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Transformer Feed-Forward Layers Are Key-Value Memories

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.214436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.214436Z digest=sha256:46bf0a0620ce29e0568ef4d51b50f54658810eac04d77a9e006869ddc647c49d

Observation addf6e6b-f2da-4623-a3a6-41358854bf14 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.756792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.217439Z digest=sha256:1353f460f90cebf26b62d09f9eb053c2ead1ed93519079ab5cd795d2bbed4432

Observation da0795b6-72dc-4baf-bbc0-4b8b5c5ac6fd · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.747551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.219910Z digest=sha256:10f83fd101ae92229d79238ba06a347a847051e3be534c31b00e78a18f1ab528

Observation 58f3b57a-92b3-41e2-826d-de99b636b5ac · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.738500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.222298Z digest=sha256:1d3e426e87a70fd5eb61c5ee0ec15c654e19f552baf9cecc6f3353bb4bea9cf7

Observation ed05fa9a-f531-4d33-804a-e13190ce54ea · outbound

This paper cites Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.224895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.224895Z digest=sha256:7c3d7f439eabdc4d57a0c1467e6408df1261e50c28b3ff826ea97fb4500091d0

Observation 728c8cfe-1e8f-4c12-80b0-fd75e67e042d · outbound

This paper cites Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.227529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.227529Z digest=sha256:1e1a231996500cd028799c3fd7e468135f13ad5ad2f656c2253cdfd967a4c32a

Observation e56e8c6a-4b6b-4391-8b9e-bcf6f62bdabe · outbound

This paper cites Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.230774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.230774Z digest=sha256:026221d851a9bd8aa393d7296919beed39df5f2f09157f2e596b09301d43aee0

Observation fc969488-0a24-4961-a66a-5053cf2fbe05 · outbound

This paper cites Dissecting Fine-Tuning Unlearning in Large Language Models.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Dissecting Fine-Tuning Unlearning in Large Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.234407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.234407Z digest=sha256:081c9b836f1072892f8c18ef423b3b5a9949ee9cc673be92bc50fbc588057b08

Observation dd377cdb-eca5-4ce2-84a0-584caeb11410 · outbound

This paper cites Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.237635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.237635Z digest=sha256:e797dadb10550576b64c1bfa403cc969a1db1fe02104bbb883addedefd0e0e64

Observation 35c43142-21db-4b91-80fa-4a5a3d1e237c · outbound

This paper cites A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.240820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.240820Z digest=sha256:b2898609faeb57244faa84942251b3e7a1da6eed761cf171d56006e6f285cf3b

Observation d5c88a1e-d1cc-4146-8a08-03ab947f16e3 · outbound

This paper cites Improving interpretation faithfulness for vision transformers.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Improving interpretation faithfulness for vision transformers

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:56:40.729346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.244052Z digest=sha256:e7d96097486478e636322c8ff4beb027bf562972d7ce7990485d7dd45cd8938e

Observation cbe1c203-d382-4d65-a179-91236d2cfdbb · outbound

This paper cites Editable Concept Bottleneck Models.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Editable Concept Bottleneck Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.246779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.246779Z digest=sha256:6f06be6d4e3712d14b67eb0f123e1b632a87cc444622e41ea74c89d620776b66

Observation f7397341-01c6-4494-b578-3ac3d44ee7af · outbound

This paper cites Dissecting Representation Misalignment in Contrastive Learning via Influence Function.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Dissecting Representation Misalignment in Contrastive Learning via Influence Function

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.249660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.249660Z digest=sha256:ca51bb435ac2738f19a4d1641755efaf16b0330b14d3b4e5a4582b24fdce68f7

Observation 4b9f692b-0a59-45c6-8871-7d9084462454 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.252591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.252591Z digest=sha256:1364fc61fcabbb14c715402f4a84b75cf36e5e4b2d816c9b11cb11e177e1c5ed

Observation afbe2020-f2ae-424b-b599-2a6460c0835b · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.255100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.255100Z digest=sha256:2a00c6272afa7236d104aca36d56367a302d7feb83a38ac0b66bc1ad9a687733

Observation acdcfaec-03f6-4c44-8d41-b6099eab5b5c · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.710072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.258937Z digest=sha256:8c86583c7972fb3e2b8ea42030e0daaf111482ebd4ccedd6a387de3641b24332

Observation 19c8fe2f-fd10-49b4-a57c-df3b1c1e47e2 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.702564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.261893Z digest=sha256:5c10e101c89f3e7c18284f1d72bc12abff0e43aaede2852b4384dfa4328e239b

Observation d18eace2-b63d-4478-a9e9-6d6f7db46ccd · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 37

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.694599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.264848Z digest=sha256:b1fde9337febe0a61ec3afb9d2b8e0fb622fff67bbd1debb23b3bab23c5b1caa

Observation 88b9e0a2-fcd1-438f-9e82-4d67e5d25e7a · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.685969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.267839Z digest=sha256:76a2ab3c34f593929a992ef1681e82cba6e0d507a58c2b1ad85ae4376658967e

Observation 9ab55f4a-fa4a-4e01-af1f-a820fefb7a0e · outbound

This paper cites Transformer Circuit Faithfulness Metrics are not Robust.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Transformer Circuit Faithfulness Metrics are not Robust

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.270810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.270810Z digest=sha256:b6da8a70bfb284caee118b2597f2e82379422a6d4ff96828d7390be4e44d0316

Observation 0675cd0b-cfd4-4bb8-bcdb-810cfd9ef59f · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.676958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.274449Z digest=sha256:60215933da73c3a1a0bf69c8bd1e1d4fc0003f364606e910ca0352b972ac4572

Observation 8d807b7e-b600-490a-b226-bd5d8c5e3b81 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.668009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.277329Z digest=sha256:e647656e1a6eb92333fcc296a8f4d44cf94cd2fc9fd1eedb59ee3e02cc3b4776

Observation b864c94e-1220-423e-b9d4-43c9b422ec03 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.280236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.280236Z digest=sha256:07344b1b402079f442fbb2a5647ef6336d3be556c98395cb22332059bfd4c1d2

Observation c74e9c93-a9a9-469e-8bda-5c5848fb126f · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.658929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.282954Z digest=sha256:3815d961db17aaa24a6bcedb35ee4a1f01a34eca90c68ca3177f331a832f848b

Observation 7708b928-4f9c-4133-855a-9a88875aa441 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 44

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.649955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.285399Z digest=sha256:23979cb4068500d6c2c3ed46820bb43f9e781b24d6af75a73255d3398369e857

Observation 1a534364-44d3-4de9-ba08-9482194b00ca · outbound

This paper cites SmoothGrad: removing noise by adding noise.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning SmoothGrad: removing noise by adding noise

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.287869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.287869Z digest=sha256:21fee3aebef685bb1a29ae738df2293bcceef5f7221957f5f9e1b3ccda8f25fd

Observation 02152dc9-3064-4fd6-a1e3-94fef301fd82 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.290472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.290472Z digest=sha256:60c512af7d66a4e27381f615a38b8bed662ecf4b9b0ce2f431e871e9071811ef

Observation 7a7a161d-b607-4ec2-b266-dd6549f76f18 · outbound

This paper cites Attribution Patching Outperforms Automated Circuit Discovery.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Attribution Patching Outperforms Automated Circuit Discovery

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.292900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.292900Z digest=sha256:1a036b69939bfe29ccb7334c30b2958f6edab8fc676a8ac47be1d17d202a33a6

Observation 96767b1b-6a25-4381-8947-4cf2db95bc2e · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.635059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.295508Z digest=sha256:78c4d59923d9b9e95ec3eac785879d830e82b2f5b127ce73a81e1639fe720e54

Observation afdd7259-4e7b-435b-b6bd-65da501de66f · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.625715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.297922Z digest=sha256:8aa149de61a5c247ba979207eca082103816dcd5011ec1b777b0688c6f9090ce

Observation edb7054f-6d58-4845-83de-4659040a41f8 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.300816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.300816Z digest=sha256:21e66c248e576de699eeebafb9f84ef13fdfa68828c6c86678eda7a6de768757

Observation 83b156a6-48fb-4ac9-b3df-6de16fb95e71 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.617003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.304345Z digest=sha256:05c01ee7db9d35efd512eef5fe79335093243c6c9144e329e94f11de7ef4b8a3

Observation 8c05b4a3-6371-43ff-b572-07da36934ec7 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 52

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.608188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.307381Z digest=sha256:9351136be6c0ec64e10b0b5e28093488617a904306d55d17d35750b1f109cde2

Observation 48c7708d-2386-4d4d-a06d-61926726f0f6 · outbound

This paper cites Chi, Quoc V.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Chi, Quoc V

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:56:40.599028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.310379Z digest=sha256:e2f027dfab8c3df0ffb91270de30d75fc154b2402ac056c1160b453d0d485d94

Observation efd74c77-f1ab-45f0-a524-876d46e3d17b · outbound

This paper cites MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.313381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.313381Z digest=sha256:23ed8841fd42f8f2d3ee323c585c8f425a8c61f00f09dc8651b29f9c61cbf642

Observation d2471825-cd9a-44f1-8473-ae4c2161e84a · outbound

This paper cites Exploring the Personality Traits of LLMs through Latent Features Steering.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Exploring the Personality Traits of LLMs through Latent Features Steering

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.316503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.316503Z digest=sha256:a8a75849fe1e96850e36386a88e5ca1d31d3ea6b5a53ddb689013998db4fb1d9

Observation b8a97691-e9d2-4afb-8bac-849289a8579a · outbound

This paper cites Knowledge Circuits in Pretrained Transformers.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Knowledge Circuits in Pretrained Transformers

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.319847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.319847Z digest=sha256:d7644705e6cd2e1886845303a73a3767c42eed5ed8ebb59c556dd0049d513b3d

Observation fe5e6b56-1a33-445d-bfaa-2c01077e6c36 · outbound

This paper cites Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.322869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.322869Z digest=sha256:15fd18fc09ef066170f4b2f2008064131217e3725d6272963aa54cbb0fcbab23

Observation 864794d1-582e-4409-9d51-3094aa0def90 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 58

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:56:40.589693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-07T22:56:40.325430Z digest=sha256:00c4d8b2507621a653fd2050663017b25c66430399586f4db893f2446a1f7741

Observation 3fab9eef-33bb-4787-a053-3d45f3bb2049 · outbound

This paper cites online" 'onlinestring :=.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning online" 'onlinestring :=

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.328000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.328000Z digest=sha256:08b1a8bb05e35ae3c121fd773f0a75d5119bbb310b5c576d3bf9a2094717f34f

Observation fb40fa17-c3f7-4823-b733-9e4d49fab41f · outbound

This paper cites write newline.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning write newline

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.331315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.331315Z digest=sha256:1c9571cf43401716e6d289627485d1eaaae4c214788426c77f5f05b689ed94af

Observation 5f4ac1dd-8da2-4b63-8678-5192f775718d · outbound

This paper cites @esa (Ref.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning @esa (Ref

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.334364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.334364Z digest=sha256:f727007c91bd4ecb3d1ceeced343c2e4640eccc7f12839d4ce88415a6f544e1c

Observation 3b1ae482-7a93-409f-af72-0334f417340e · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.337616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.337616Z digest=sha256:c7c5b8b50f1e1e51e988f8a4f76f37a4187cc0361270cff7ef7a5abf50c97ed3

Observation 0d359cf6-9022-44f3-8e7e-038062a63d99 · outbound

This paper cites an unresolved cited work.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Unresolved cited work

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T22:56:40.340931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:56:40.340931Z digest=sha256:32b46ee3e14cb9d368a8f7103738be67291d6b78366aeed517f1e5c9ea0bf6f5

Pith citing papers

Observation 5febf7ad-c375-45ed-af4e-807efbf882c9 · inbound

COMPKE: Complex Question Answering under Knowledge Editing cites this paper.

COMPKE: Complex Question Answering under Knowledge Editing Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-07T12:00:23.921056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:00:23.921056Z digest=sha256:0a2a27d847de954ae704aacad6a50e487bf6858dd2b1cad2c76f16781b4cac02

Observation d6158e5e-016c-4ef7-9f1f-8cc880c85cdd · inbound

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images cites this paper.

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T05:43:36.750878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T05:43:36.750878Z digest=sha256:031731e51c6ef8c75b3725a47ef6b63866fc5b0ce3e2717eb8647c9780adea37

Observation 141e81d1-9a6f-46a0-b21b-76ad9bcf47a8 · inbound

The Compositional Architecture of Regret in Large Language Models cites this paper.

The Compositional Architecture of Regret in Large Language Models Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:59:46.484853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:59:46.484853Z digest=sha256:3cb6a5deac14e7830a1374011bf32734f190792973870b5df8a18c26c5924137

Observation 3d07b06f-dd56-4116-8543-90e42b0b70d5 · inbound

Attributing Data for Sharpness-Aware Minimization cites this paper.

Attributing Data for Sharpness-Aware Minimization Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Reference 65

Resolution
verified exact
local_arxiv, observed 2026-08-06T20:02:11.960151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:02:11.474879Z digest=sha256:b9e5ded852d263b0eda3aa8f33a06fccc57cdf0fade99faec7137b4319972d2d