Pith. sign in

Paper Citation Record · LEDGER

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

As of 8 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2507.00322.

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

pith.paper-citation-record.v1
2507.00322 v2

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:23:40.653122Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 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

47 of 47 outbound references displayed

  • verified exact1
  • verified fuzzy15
  • unresolved31
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5e856afd-33f1-4e5a-9952-bfe41eddfad3 · outbound

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

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:34.876185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:34.876185Z digest=sha256:80135e3d303afdcd27cf3bd947542b2ee0e733ddb7e5e755bc6032928c7a7a96

Observation a535a966-6130-4fbd-a6fa-21b2d11f48d6 · outbound

This paper cites GPT-4 Technical Report.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones GPT-4 Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.026143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.026143Z digest=sha256:a5addc8196f5343a631c2ce99ad6d4d2360f37288fa2a20392c3721af8f1bc77

Observation 0b62b822-411b-4e50-be6c-d0ecff9fa0b1 · outbound

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

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Refusal in Language Models Is Mediated by a Single Direction

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.120853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.120853Z digest=sha256:2b0e90629accc5e2c5b4625cfcd7c4e351e34f85dc7bd7e48ee2f28de9f04fd9

Observation c5912ac0-7a11-41db-ab5f-db247c0a94bf · outbound

This paper cites Program Synthesis with Large Language Models.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Program Synthesis with Large Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.262506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.262506Z digest=sha256:e5b0e926c8186cd062e29f5205e4dfbaa399158d82927802c54b63ac0a42648a

Observation f54fe905-c6e1-4591-b2a6-6a4e6e738f2f · outbound

This paper cites Mechanistic interpretability for AI safety - a re- view.Transactions on Machine Learning Research, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Mechanistic interpretability for AI safety - a re- view.Transactions on Machine Learning Research, 2024

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:45.154576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:35.412994Z digest=sha256:abd26a8d431c57b987ecd0a987f2edcc9d4cd983f363b3c3df405b4c4f648a98

Observation c5aedd5b-535c-4bf5-85a6-aaa96562c651 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Pythia: A suite for analyzing large language models across training and scaling

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.536905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.536905Z digest=sha256:ec8a2fce691cd95719ab534b8c42b93bbf64c041bc85fb3f2d0ed206f09eaf7c

Observation 6a5d405e-a3d7-4997-b08b-8b9496445206 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread, 2023

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.636587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.636587Z digest=sha256:d6e0c42ea975750075a98d9278a012fab688e7337e7668aef0ffb0f35895b751

Observation e141caff-ef8c-4178-859b-c7725809b015 · outbound

This paper cites Causal scrubbing: A method for rigorously testing interpretability hypotheses.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Causal scrubbing: A method for rigorously testing interpretability hypotheses

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:44.829435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:35.758200Z digest=sha256:762c4cde46341a9502904e9585c3db1ed7e9cfb21e2efc9b76755ecc8c6ee13e

Observation ff537701-90ea-4075-abfe-eb5453d7172e · outbound

This paper cites an unresolved cited work.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.887445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.887445Z digest=sha256:f51458d1dc98e6a8070fde3665751dbe2dfbbfa66aa153810c72a4d20bc33fe9

Observation 8e651267-9ff8-4c1e-bf5e-47a273ed6c41 · outbound

This paper cites Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:35.997228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:35.997228Z digest=sha256:7b4ee6e419e2aa104d30fa5f219762d4a80ac74961ab297aead28cda259fd580

Observation 4bea593a-9fa0-43a0-b6e7-132a52660b25 · outbound

This paper cites Analyzing Transformers in Embedding Space.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Analyzing Transformers in Embedding Space

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.096016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.096016Z digest=sha256:90d14a7b77b69d52b6117b1d3369250caf18c5104aab2ab36ec85826d5e02cc8

Observation 2770c8af-cfe3-4ad7-8a32-eeb6bef9b0c7 · outbound

This paper cites What’s wrong with your code generated by large language models? an extensive study.arXiv preprint arXiv:2407.06153, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones What’s wrong with your code generated by large language models? an extensive study.arXiv preprint arXiv:2407.06153, 2024

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.275163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.275163Z digest=sha256:5b1495cca543ca04862842e2586d2c90b773977c68967fd2e080c5582de01d86

Observation 5f928bd4-3bd9-467a-8a2c-34616035bfe7 · outbound

This paper cites The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.425964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.425964Z digest=sha256:e8092117ef7452addc12dca171c5a984aba87fabfe16ef6e84005ce7fd3ca221

Observation deca5664-4f0a-45e6-8967-c3901ecd20d5 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread,.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones A mathematical framework for transformer circuits.Transformer Circuits Thread,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:44.545040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:36.500467Z digest=sha256:8f4f873015a44744745edfecb96180edceaf3d13aa8f189289d871f4e91468e5

Observation 4d6e15ee-1f1a-4c5f-8aaf-35c71ffeaa7b · outbound

This paper cites InCoder: A Generative Model for Code Infilling and Synthesis.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones InCoder: A Generative Model for Code Infilling and Synthesis

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.844220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.844220Z digest=sha256:d02860ba745363e00e5ab919d0135e4f7015db0773fc9b495071c2e5583e9d78

Observation 5831349c-d295-444f-b1b7-462875a4b994 · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.966361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.966361Z digest=sha256:c43a89dd263f7531545eccaa17bc2802f00b0379182c4cfbb0b72e9160305aec

Observation 0922e5da-b6bf-496f-a2cc-c1a22bcf0f98 · outbound

This paper cites The Llama 3 Herd of Models.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones The Llama 3 Herd of Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:37.103551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:37.103551Z digest=sha256:f3c4ec41ecd30224ecf1b8ef513ecfe62178edca2f8e56beaf56b1295bd723b3

Observation 86c5e29a-1c40-41b9-80f4-611181896140 · outbound

This paper cites How does gpt-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.Advances in Neural Information Processing Systems, 36:76033–76060, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones How does gpt-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.Advances in Neural Information Processing Systems, 36:76033–76060, 2023

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:37.228251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:37.228251Z digest=sha256:423c615e5cb4c5d607e1c2da2602696b2482cbb1448ec29ecc1b455848c78035

Observation 189f0de1-afd7-4d09-83df-eadfb4e688d1 · outbound

This paper cites Have faith in faithfulness: Going be- yond circuit overlap when finding model mechanisms.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Have faith in faithfulness: Going be- yond circuit overlap when finding model mechanisms

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:44.349189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:37.349483Z digest=sha256:0b99081f5947a697697fa88dc7e3535baab52202ad8ca244c9a83a84a1ded5ba

Observation 73480e50-707f-49ea-9b18-8749d2e99412 · outbound

This paper cites How to use and interpret activation patching.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones How to use and interpret activation patching

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:37.459317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:37.459317Z digest=sha256:849b457eba1752b5e25cae5892ba2c374477602ae84b545dcd3e6314170db8c8

Observation f5664269-a8d1-4a1a-a51a-2b8296c8987e · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.CoRR, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Livecodebench: Holistic and contamination free evaluation of large language models for code.CoRR, 2024

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:44.106715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:37.590643Z digest=sha256:e186148aeca11f6d9b8c2c6a92f4a5cfe93ee471bf2c5cd351a6d1783263eeb4

Observation 25b3e83d-6176-4e35-940d-c901c6fd6c1f · outbound

This paper cites Inference- time intervention: Eliciting truthful answers from a language model.Advances in Neural Information Processing Systems, 36:41451–41530, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Inference- time intervention: Eliciting truthful answers from a language model.Advances in Neural Information Processing Systems, 36:41451–41530, 2023

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:43.797574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:37.725653Z digest=sha256:8efb337c6330075be0d4082cdc82955c1097d283baa8e21970e138584ece808a

Observation c932472a-f480-411a-9ee6-00cd753ee253 · outbound

This paper cites Starcoder: may the source be with you!Transactions on Machine Learning Research, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Starcoder: may the source be with you!Transactions on Machine Learning Research, 2023

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:43.525264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:37.780302Z digest=sha256:d3752f667020f7fd1b3eb60583eb4a90121216750962f7fac168ecad2ccdf221

Observation 91125b34-96a4-48c2-bd86-e36bdb4d8e73 · outbound

This paper cites an unresolved cited work.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:37.865288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:37.865288Z digest=sha256:1e171e5796328814e671d6d2b7fbc5bd3ce9eec68042968debe9a1254e4211a1

Observation 4b2c5672-c6e4-43e1-946b-0f72f9ca9025 · outbound

This paper cites In-context vectors: making in context learning more effective and controllable through latent space steering.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones In-context vectors: making in context learning more effective and controllable through latent space steering

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:43.215870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:38.056249Z digest=sha256:d47e90bd7aa7dc48b91184d1587e39aa44c4bc59d67a0115fa12d3f677749e43

Observation 6a4ab492-ec66-45b5-bd28-08b12e1b8253 · outbound

This paper cites Mechanistic Understanding of Language Models in Syntactic Code Completion.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Mechanistic Understanding of Language Models in Syntactic Code Completion

Reference 26

Resolution
verified exact
local_arxiv, observed 2026-08-06T21:23:41.120107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:38.192459Z digest=sha256:58d04c48fdb16adccd289ad9090583514db9b111e843ad17d95cc4a559811fc5

Observation a4c3e5f5-a8c7-4a92-91d8-7bae60c8462d · outbound

This paper cites CodeGen2: Lessons for Training LLMs on Programming and Natural Languages.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:38.275531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:38.275531Z digest=sha256:9a472695e80c6300295074eae4b7aa57a141a357ba8f1ef289764d3647b38944

Observation e01e7cb0-6b59-4ba9-a811-f362af5b0bf8 · outbound

This paper cites Arithmetic without algo- rithms: Language models solve math with a bag of heuristics.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Arithmetic without algo- rithms: Language models solve math with a bag of heuristics

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:42.965488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:38.424714Z digest=sha256:9ceb05500618c811ed839792ea77d4eb181168b9adb60f11dc8e0627121bd6da

Observation a181ac3f-1dcf-4626-87c0-045e527f6b99 · outbound

This paper cites Interpreting gpt: the logit lens.AI Alignment Forum, 2020.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Interpreting gpt: the logit lens.AI Alignment Forum, 2020

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:42.696090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:38.559614Z digest=sha256:094471dff6b4d7475b41980a27cd4aa966aa734948da4e327199c3c3f014f1d9

Observation 1688a73a-d51a-448f-a014-39ddc0e72272 · outbound

This paper cites Zoom in: An introduction to circuits.Distill, 5(3):e00024–001, 2020.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Zoom in: An introduction to circuits.Distill, 5(3):e00024–001, 2020

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:38.695811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:38.695811Z digest=sha256:16cb66b6e72f842402a7d86d2b060becf570196edcbb9a024588a04388a61e3f

Observation ac528d42-7175-4088-8bbc-08b87c788ba5 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:38.828464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:38.828464Z digest=sha256:463bce0f89fda8f8c72995e7c2250d13611bf7ad3cebf6bffecde66860203d99

Observation 4b2be69a-3714-4a37-9890-1a3f9ce5afb0 · outbound

This paper cites An investigation of neuron activation as a unified lens to explain chain-of-thought eliciting arithmetic reasoning of llms.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones An investigation of neuron activation as a unified lens to explain chain-of-thought eliciting arithmetic reasoning of llms

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:42.412988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:38.920816Z digest=sha256:63c0e5718c1e645eaa929b467a775df44218d3372995402539ce316aee36ab38

Observation 75dfdb9f-ce66-4464-9d8e-1fb16f1ed617 · outbound

This paper cites A practical review of mech- anistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones A practical review of mech- anistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646, 2024

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:39.079189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:39.079189Z digest=sha256:ac26e158ef743fba49859b26262d761f3669b8ef2eb9aa9e0a2b7e225d18453b

Observation 82549726-e047-4666-a98a-2264d29c3437 · outbound

This paper cites Red-teaming language models via activation engineering.Accessed: October, 13:2023, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Red-teaming language models via activation engineering.Accessed: October, 13:2023, 2023

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:42.135894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:39.208707Z digest=sha256:0b03e8b741c6b855d9fd22b1ff3ffda19783af2b35eaa95fd09900b006ca7aee

Observation 9891157f-3740-44ab-8e5d-c1ed42a41cbf · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Steering llama 2 via contrastive activation addition

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:39.348155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:39.348155Z digest=sha256:67793f2671f0434b804ae88fbc9a3824d1b9028c5ab23bd350ea56d86703ff8f

Observation 3edd397d-5696-40d1-b388-fd01b7e894df · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Code Llama: Open Foundation Models for Code

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:39.474269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:39.474269Z digest=sha256:11b9e50b470d660926352196cfdf640a6d195e28a4678620d3f3010d3832fc22

Observation 533344cc-2aa2-4f27-a1ef-38a631d0c7d7 · outbound

This paper cites Attribution patching outperforms automated circuit discovery.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Attribution patching outperforms automated circuit discovery

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:39.597473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:39.597473Z digest=sha256:db4588d17b0960133131c39711ad1ff5b21b1e49415f0447e8081b3b980ab490

Observation f6357461-1fef-439b-b87d-65af4519cad7 · outbound

This paper cites Linear representations of sentiment in large language models.CoRR, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Linear representations of sentiment in large language models.CoRR, 2023

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:41.877548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:39.709472Z digest=sha256:47651c7fa75ec0d827af8ee4cd5a15f052236c0c28cca34ee9390602697c4b13

Observation 2ad534bc-78ec-49c3-8e0b-fd5dec4098ff · outbound

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

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:39.890127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:39.890127Z digest=sha256:41ea6d8b87eb8ae67f9b2e633702e6703ab2ab18dab89e362a2b3604b1e4d831

Observation 8359c874-8dc3-4271-88a4-15e11a3f0309 · outbound

This paper cites Activation addition: Steering language models without optimization.CoRR, 2023.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Activation addition: Steering language models without optimization.CoRR, 2023

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:41.625855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:39.991931Z digest=sha256:4de7849f18f85449ed026f80c2b7a93452147b67fe08f45c56fa80768bfeab19

Observation 34339abf-a0ed-49e0-9a83-ceb3bba8cca8 · outbound

This paper cites Extending Activation Steering to Broad Skills and Multiple Behaviours.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Extending Activation Steering to Broad Skills and Multiple Behaviours

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:40.136142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:40.136142Z digest=sha256:c12fb3047ca4a114e128db4449fb2e50459d90ed4d2d0e390cace51ca1359865

Observation 3625b138-83b3-4f16-8f78-371a3a288972 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:40.263751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:40.263751Z digest=sha256:08027765b0a015a87772f8e91d35738c3e7ca86caa8dc20dc0ae21e312d88a8b

Observation f95f3fc4-d93b-41ac-835f-39db7d4b9be8 · outbound

This paper cites Interpretability in the wild: a circuit for indirect object identification in GPT-2 small.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Interpretability in the wild: a circuit for indirect object identification in GPT-2 small

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:40.392206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:40.392206Z digest=sha256:a270dd417bc07acbcae0d58b4845073138f7f2e707d1f241d9d56aa69a0bced0

Observation a70ee580-114b-4c14-b238-1cb1f7aa4d2d · outbound

This paper cites Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:40.494475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:40.494475Z digest=sha256:a5a275148b25693613cd1035928902049dbd1554d85f6a562b82f7903a49ead6

Observation e493e9e3-6a26-48e1-9a6b-e5092049b00b · outbound

This paper cites Reft: Representation finetuning for language models.Advances in Neural Information Processing Systems, 37:63908–63962, 2024.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Reft: Representation finetuning for language models.Advances in Neural Information Processing Systems, 37:63908–63962, 2024

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:40.556558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:40.556558Z digest=sha256:824d4694c7214f548f8bd6dd610c61ce965a54aec82a39315fac052255d72f6d

Observation 179d2a8f-c581-409d-9322-eafce77aa6f1 · outbound

This paper cites #print the string 160\nprint(str(160.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones #print the string 160\nprint(str(160

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T21:23:41.468495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T21:23:40.653122Z digest=sha256:0e788b9398898dcf449b2fecd48ddc5a3638f48d1c128cc1a8b127c10629dc9e

Observation 7b7c97ba-0bd8-4f50-8f3b-0eb864cdc40d · outbound

This paper cites an unresolved cited work.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones Unresolved cited work

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:36.670492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:36.670492Z digest=sha256:865ba96fe58e1dccabee28c406b017977828b4f01375e3b0cd76d220bcf21a26

Pith citing papers

No inbound Pith citation observations are available.