Paper Citation Record · LEDGER

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference

As of 15 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2412.15750.

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

pith.paper-citation-record.v1
2412.15750 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:12:57.956319Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

26 of 26 outbound references displayed

verified exact1
verified fuzzy7
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ddad7123-beb5-4ad5-a409-fe0906be8c9a · outbound

This paper cites Frantar, E.; and Alistarh, D.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Frantar, E.; and Alistarh, D

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.264660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 169fcbef-6b05-4749-acbf-4032fac2c4c6 · outbound

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

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.875562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45df0b4a-33ca-4c9c-958a-3fa98f7bc5a5 · outbound

This paper cites In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.883145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ec9166-0ce8-4f13-b9ff-68134fd3d618 · outbound

This paper cites In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8046–8056.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8046–8056

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.253991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4651da23-7547-414d-8e37-7ec3e2c67bcf · outbound

This paper cites Scaling Laws for Neural Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Scaling Laws for Neural Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.891817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac5574f-07ba-4730-b1b8-de3cf0bf1b3c · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.899535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ab1cce8-5160-4710-b4e9-d7e339452e26 · outbound

This paper cites The Hydra Effect: Emergent Self-repair in Language Model Computations.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference The Hydra Effect: Emergent Self-repair in Language Model Computations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.903041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72e91eb0-6257-4452-906c-18a85d60044c · outbound

This paper cites Advances in Neural Information Processing Systems, NeurIPS 2022 , 35: 17359–17372.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Advances in Neural Information Processing Systems, NeurIPS 2022 , 35: 17359–17372

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.242297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b6e721a2-b73f-46c6-ab9e-eeb311cc3ebc · outbound

This paper cites Https://transformer-circuits.pub/2022/in-context- learning-and-induction-heads/index.html.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Https://transformer-circuits.pub/2022/in-context- learning-and-induction-heads/index.html

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.229590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d55f039c-770e-4a77-89ff-9c17ddc0b075 · outbound

This paper cites LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.915322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b759b7-c049-45ed-b124-21e351c3c0c9 · outbound

This paper cites What Matters In The Structured Pruning of Generative Language Models?.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference What Matters In The Structured Pruning of Generative Language Models?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.923654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7483f48-7b7c-400d-adac-bd1bc89fa158 · outbound

This paper cites In Rogers, A.; Boyd-Graber, J.; and Okazaki, N., eds., Find- ings of the Association for Computational Linguistics: ACL 2023, 7059–7073.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference In Rogers, A.; Boyd-Graber, J.; and Okazaki, N., eds., Find- ings of the Association for Computational Linguistics: ACL 2023, 7059–7073

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.205408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 70a7926c-4bda-4bdc-9b7c-f379e1663fdb · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference A Simple and Effective Pruning Approach for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.932676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5471bffd-e177-4bf7-bffa-59f1c0a4fbe2 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference LaMDA: Language Models for Dialog Applications

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.940954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1feb37e5-379d-44d0-b937-ca86ba6afdbc · outbound

This paper cites In Proceedings of the 2020 Confer- ence on Empirical Methods in Natural Language Process- ing: System Demonstrations, 38–45.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference In Proceedings of the 2020 Confer- ence on Empirical Methods in Natural Language Process- ing: System Demonstrations, 38–45

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.180697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 86e9b979-4933-4fda-8396-03b73a1673aa · outbound

This paper cites LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.952950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1587f2f9-a5d6-4e24-9ea5-e37b9dc581d4 · outbound

This paper cites A Survey on Model Compression for Large Language Models.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference A Survey on Model Compression for Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.956319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684f48ae-0f98-47cc-bc33-1835c2e87470 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Adam: A Method for Stochastic Optimization

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.895877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87063ed9-9559-4f93-9fa7-a1577da29aa9 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Distilling the Knowledge in a Neural Network

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.879496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d5e3cc3-a973-4bc7-acf8-76a7662710b9 · outbound

This paper cites an unresolved cited work.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Unresolved cited work

Reference 2017

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:12:58.193208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fe72f192-da06-46d1-bef3-e84268b28754 · outbound

This paper cites an unresolved cited work.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Unresolved cited work

Reference 2018

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:12:58.217338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 623c61a6-7a4c-4037-95d7-babf3dc0cf0d · outbound

This paper cites Distilling Task-Specific Knowledge from BERT into Simple Neural Networks.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.936739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1a2462-150c-45b5-b790-efb8293bb271 · outbound

This paper cites Ad- vances in Neural Information Processing Systems, NeurIPS 2020, 33: 1877–1901.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Ad- vances in Neural Information Processing Systems, NeurIPS 2020, 33: 1877–1901

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:12:58.275830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 224feb25-e902-4a3b-9169-ff53d94157e8 · outbound

This paper cites Toy Models of Superposition.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Toy Models of Superposition

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.868130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c994f6d3-a967-47ea-82b0-c7969aa1c62c · outbound

This paper cites GPT-4 Technical Report.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference GPT-4 Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T11:12:57.854841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e75e75f-8280-42d0-af80-4d9fcdd79c3e · outbound

This paper cites Finding Transformer Circuits with Edge Pruning.

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference Finding Transformer Circuits with Edge Pruning

Reference 2024

Resolution: verified exact; local_arxiv, observed 2026-08-11T11:12:58.155851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.