Paper Citation Record · LEDGER

On Mechanistic Circuits for Extractive Question-Answering

As of 23 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2502.08059.

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

pith.paper-citation-record.v1
2502.08059 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:01:28.985951Z

measured 41 of 41 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 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 exact0
verified fuzzy5
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3db0227b-826c-4686-af4d-96ce1335bc5d · outbound

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

On Mechanistic Circuits for Extractive Question-Answering Mechanistic Interpretability for AI Safety -- A Review

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.842173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 385ebfff-dbb6-455c-8a60-446965398ae6 · outbound

This paper cites Attribute or Abstain: Large Language Models as Long Document Assistants.

On Mechanistic Circuits for Extractive Question-Answering Attribute or Abstain: Large Language Models as Long Document Assistants

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.846203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6e6f3d8-46d8-4c40-9b51-7ea998bec344 · outbound

This paper cites an unresolved cited work.

On Mechanistic Circuits for Extractive Question-Answering Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-08T11:01:29.412650Z

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.

Observation e8852c9f-4833-489a-9e1f-591d4a62d168 · outbound

This paper cites The Llama 3 Herd of Models.

On Mechanistic Circuits for Extractive Question-Answering The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.854207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b434568-9eaa-4557-80c5-baba5fab4e39 · outbound

This paper cites Enabling Large Language Models to Generate Text with Citations.

On Mechanistic Circuits for Extractive Question-Answering Enabling Large Language Models to Generate Text with Citations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.857999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25f3b576-39e0-43c3-84c4-f967ea83d9a6 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

On Mechanistic Circuits for Extractive Question-Answering Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.862108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b19002-e07b-47b1-9546-a01bdb3afaee · outbound

This paper cites Successor Heads: Recurring, Interpretable Attention Heads In The Wild.

On Mechanistic Circuits for Extractive Question-Answering Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.865958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 775b86ba-2ead-4d2f-8e0d-54c49a9d4319 · outbound

This paper cites How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.

On Mechanistic Circuits for Extractive Question-Answering How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.869981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ea8440c-8b7d-40c7-b550-a4105023802a · outbound

This paper cites We provide the patching steps as follows: Step 1: Copy the activation of a node (e.g., a12) from the corrupted model to the clean model to create the patched model.

On Mechanistic Circuits for Extractive Question-Answering We provide the patching steps as follows: Step 1: Copy the activation of a node (e.g., a12) from the corrupted model to the clean model to create the patched model

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:01:29.377587Z

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.

Observation d7577348-6696-43a2-8bce-9a691f32c98f · outbound

This paper cites Citation: A Key to Building Responsible and Accountable Large Language Models.

On Mechanistic Circuits for Extractive Question-Answering Citation: A Key to Building Responsible and Accountable Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.877720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f818be-d539-427e-b27f-25c823d3294b · outbound

This paper cites Mistral 7B.

On Mechanistic Circuits for Extractive Question-Answering Mistral 7B

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.881526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b96b06d-2fe5-4e05-9ca9-ab3ccfd04388 · outbound

This paper cites Source-Aware Training Enables Knowledge Attribution in Language Models.

On Mechanistic Circuits for Extractive Question-Answering Source-Aware Training Enables Knowledge Attribution in Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.885199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e53981-1b6b-4b89-889f-3559b3013dfb · outbound

This paper cites Bob ’s your uncle.

On Mechanistic Circuits for Extractive Question-Answering Bob ’s your uncle

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:01:29.345845Z

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.

Observation c9797742-6f66-42c8-8476-da7123b0bf24 · outbound

This paper cites A Survey of Large Language Models Attribution.

On Mechanistic Circuits for Extractive Question-Answering A Survey of Large Language Models Attribution

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.893099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef13a62-55e5-430e-90fa-f363fbfc176d · outbound

This paper cites Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

On Mechanistic Circuits for Extractive Question-Answering Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.896966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c120d16-5b32-42e8-8dcb-ece247f6d54d · outbound

This paper cites Across various extractive QA benchmarks, we obtain improved performances over different attribution baselines.

On Mechanistic Circuits for Extractive Question-Answering Across various extractive QA benchmarks, we obtain improved performances over different attribution baselines

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:01:29.334117Z

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.

Observation d717227c-de33-4a67-acff-348bbaefdf1c · outbound

This paper cites When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.

On Mechanistic Circuits for Extractive Question-Answering When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.905672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1192216f-d4fc-4221-9c18-8203ebf96a88 · outbound

This paper cites Copy Suppression: Comprehensively Understanding an Attention Head.

On Mechanistic Circuits for Extractive Question-Answering Copy Suppression: Comprehensively Understanding an Attention Head

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.909500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2311225c-2970-4325-aba0-8cc71d9d0d1f · outbound

This paper cites Locating and Editing Factual Associations in GPT.

On Mechanistic Circuits for Extractive Question-Answering Locating and Editing Factual Associations in GPT

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.913194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdcfd47e-57bd-4cba-aa6f-c13a8ff8b1cf · outbound

This paper cites Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking.

On Mechanistic Circuits for Extractive Question-Answering Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.916768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e626d1c4-8200-40dd-9985-f682b95a2afc · outbound

This paper cites Trusting Your Evidence: Hallucinate Less with Context-aware Decoding.

On Mechanistic Circuits for Extractive Question-Answering Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.920447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebcfd7cc-a302-41f5-a4cd-5bd71bded08f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

On Mechanistic Circuits for Extractive Question-Answering Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.924150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46e639a1-87fe-42a7-a011-39d407589ad9 · outbound

This paper cites Steering Language Models With Activation Engineering.

On Mechanistic Circuits for Extractive Question-Answering Steering Language Models With Activation Engineering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.927664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43ceb3a-bc7d-49f0-8ed7-1d01645c071e · outbound

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

On Mechanistic Circuits for Extractive Question-Answering Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.934946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c24aeb-0820-4b64-8237-b98e902084a4 · outbound

This paper cites ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence.

On Mechanistic Circuits for Extractive Question-Answering ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.938242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb00042-789c-48a9-9ea1-f977bd3c8227 · outbound

This paper cites Effective Large Language Model Adaptation for Improved Grounding and Citation Generation.

On Mechanistic Circuits for Extractive Question-Answering Effective Large Language Model Adaptation for Improved Grounding and Citation Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.945396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39adbcf4-a31e-4516-bffc-cc50875fe705 · outbound

This paper cites Interpreting Language Models with Contrastive Explanations.

On Mechanistic Circuits for Extractive Question-Answering Interpreting Language Models with Contrastive Explanations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.949049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd400d7-a251-4c71-aba7-9d409e7b8602 · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

On Mechanistic Circuits for Extractive Question-Answering Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.952612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34aed3da-dc3d-4333-8dd2-2419daa0ea03 · outbound

This paper cites The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models.

On Mechanistic Circuits for Extractive Question-Answering The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.956246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e74ee48-9eb7-4872-8849-0398cf4b24bf · outbound

This paper cites On Prompt-Driven Safeguarding for Large Language Models.

On Mechanistic Circuits for Extractive Question-Answering On Prompt-Driven Safeguarding for Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.960192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76fd06e3-2699-4eb2-ae8d-79119b757a20 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

On Mechanistic Circuits for Extractive Question-Answering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.963888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6bcf08-711b-42c9-b8ad-b21c07cf8bff · outbound

This paper cites an unresolved cited work.

On Mechanistic Circuits for Extractive Question-Answering Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-08T11:01:29.389671Z

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.

Observation 2370dd9f-590f-48db-88c7-c317a8d6d5fb · outbound

This paper cites 17 On Mechanistic Circuits for Extractive Question-Answering H.

On Mechanistic Circuits for Extractive Question-Answering 17 On Mechanistic Circuits for Extractive Question-Answering H

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:01:29.367004Z

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.

Observation 38aaecc5-c649-4854-87be-3b455353cdab · outbound

This paper cites In this example, Russia (which is the answer) is present at multiple places.

On Mechanistic Circuits for Extractive Question-Answering In this example, Russia (which is the answer) is present at multiple places

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:01:29.356725Z

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.

Observation ec949702-e343-428e-991e-77506ef55798 · outbound

This paper cites Teaching Machines to Read and Comprehend.

On Mechanistic Circuits for Extractive Question-Answering Teaching Machines to Read and Comprehend

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.873717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02a83fd1-e126-48fa-8cf7-5025f960cf21 · outbound

This paper cites Attention Is All You Need.

On Mechanistic Circuits for Extractive Question-Answering Attention Is All You Need

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.931641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58835322-92af-42c5-80c7-15fd5430e172 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

On Mechanistic Circuits for Extractive Question-Answering HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.941681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2185c2-3bca-45cd-8c9a-1afa337f97c5 · outbound

This paper cites an unresolved cited work.

On Mechanistic Circuits for Extractive Question-Answering Unresolved cited work

Reference 2021

Resolution: unresolved; raw_fallback, observed 2026-08-08T11:01:29.401657Z

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.

Observation 431f0993-eebd-472d-b081-73674ba32cde · outbound

This paper cites Entity-Based Knowledge Conflicts in Question Answering.

On Mechanistic Circuits for Extractive Question-Answering Entity-Based Knowledge Conflicts in Question Answering

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.900880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31002728-0aec-46e8-9d1f-748eb1022ffa · outbound

This paper cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection.

On Mechanistic Circuits for Extractive Question-Answering Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.837807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fca6270-4616-45db-a820-06fb812ea14e · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

On Mechanistic Circuits for Extractive Question-Answering Refusal in Language Models Is Mediated by a Single Direction

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.824316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.