On the Robustness of LLMs' Internal Representation of Code Correctness | Paper Citation Record

Observation 6e93653f-e357-4836-9f0d-3e8cb519fa4c · outbound

This paper cites In- tellicode compose: code generation using transformer,.

On the Robustness of LLMs' Internal Representation of Code Correctness In- tellicode compose: code generation using transformer,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.889232Z

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 877a3a7d-f6f4-4373-9075-e6d02936af85 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

On the Robustness of LLMs' Internal Representation of Code Correctness Evaluating Large Language Models Trained on Code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.483965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d18d29-37c6-4de7-a433-60a30775feb4 · outbound

This paper cites SWE-bench: Can language models resolve real-world GitHub issues?.

On the Robustness of LLMs' Internal Representation of Code Correctness SWE-bench: Can language models resolve real-world GitHub issues?

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.872981Z

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 4a874b0f-f250-4d20-8977-143a61dee2ab · outbound

This paper cites Grounded copi- lot: How programmers interact with code-generating models,.

On the Robustness of LLMs' Internal Representation of Code Correctness Grounded copi- lot: How programmers interact with code-generating models,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.851862Z

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 06bddc3f-c8b3-4d2f-a2bd-bc7376315fdf · outbound

This paper cites Security weaknesses of copilot-generated code in GitHub projects: An empirical study,.

On the Robustness of LLMs' Internal Representation of Code Correctness Security weaknesses of copilot-generated code in GitHub projects: An empirical study,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.829988Z

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 951b6ab5-a4a3-43f2-aba8-f5472d1c9c20 · outbound

This paper cites Towards understanding the characteristics of code generation errors made by large language models,.

On the Robustness of LLMs' Internal Representation of Code Correctness Towards understanding the characteristics of code generation errors made by large language models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.812477Z

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 3577482a-3108-49f5-9e20-97a6e1c724f1 · outbound

This paper cites The counterfeit conundrum: Can code lan- guage models grasp the nuances of their incorrect generations?.

On the Robustness of LLMs' Internal Representation of Code Correctness The counterfeit conundrum: Can code lan- guage models grasp the nuances of their incorrect generations?

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.794242Z

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 04ac78fc-cb0a-42f1-bf13-fc8f9ecebb41 · outbound

This paper cites Theoracleprobleminsoftwaretesting:Asurvey,.

On the Robustness of LLMs' Internal Representation of Code Correctness Theoracleprobleminsoftwaretesting:Asurvey,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.773546Z

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 2e8662ee-86b1-44b1-b7c6-078b1641ed17 · outbound

This paper cites Justaskforcalibration:Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback,.

On the Robustness of LLMs' Internal Representation of Code Correctness Justaskforcalibration:Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.757064Z

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 ec70991c-df18-41cc-86e9-ae935561f171 · outbound

This paper cites Calibration and correctness of language models for code,.

On the Robustness of LLMs' Internal Representation of Code Correctness Calibration and correctness of language models for code,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.734956Z

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 e2f7a0e6-0154-4df4-bacf-c6fb1540aa19 · outbound

This paper cites On LLMs’ internal representation of code correctness,.

On the Robustness of LLMs' Internal Representation of Code Correctness On LLMs’ internal representation of code correctness,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.714600Z

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 10eeb383-e3d8-46ac-bf3b-12988748ab97 · outbound

This paper cites The internal state of an LLM knows when it’s lying,.

On the Robustness of LLMs' Internal Representation of Code Correctness The internal state of an LLM knows when it’s lying,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.693672Z

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 fbbc40d2-f6c0-426e-8212-1fc1624ccc49 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

On the Robustness of LLMs' Internal Representation of Code Correctness The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.555203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bbba6f8-3c22-4e6c-8a1a-5eef5803e0fb · outbound

This paper cites Discovering latent knowledge in language models without supervision,.

On the Robustness of LLMs' Internal Representation of Code Correctness Discovering latent knowledge in language models without supervision,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.677517Z

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 cf3d792a-fb7c-4c8a-bd53-e2aae564c61e · outbound

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

On the Robustness of LLMs' Internal Representation of Code Correctness Representation Engineering: A Top-Down Approach to AI Transparency

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.567144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a80088c-9d98-417a-8a8c-48449a052a0a · outbound

This paper cites A unified understanding and evaluation of steering methods,.

On the Robustness of LLMs' Internal Representation of Code Correctness A unified understanding and evaluation of steering methods,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.573341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 105803a4-9f5d-43df-80e7-d6e281737d44 · outbound

This paper cites BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions.

On the Robustness of LLMs' Internal Representation of Code Correctness BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.578999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9025859a-db23-4db2-b2f3-eafc183a55a7 · outbound

This paper cites Program Synthesis with Large Language Models.

On the Robustness of LLMs' Internal Representation of Code Correctness Program Synthesis with Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.585505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e907841-bae2-4bc3-a7e2-4ea34aacff98 · outbound

This paper cites Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation,.

On the Robustness of LLMs' Internal Representation of Code Correctness Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.658163Z

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 233147c0-30ef-416d-a4ed-8c18fcbb2844 · outbound

This paper cites Attention is all you need,.

On the Robustness of LLMs' Internal Representation of Code Correctness Attention is all you need,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.598961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca461b9f-42b8-47a6-9f2b-f94c33d1eeb1 · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model,.

On the Robustness of LLMs' Internal Representation of Code Correctness Inference-time intervention: Eliciting truthful answers from a language model,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.619242Z

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 3f69ca45-5c69-40c2-9c7b-aaee36175acc · outbound

This paper cites Principal component analysis,.

On the Robustness of LLMs' Internal Representation of Code Correctness Principal component analysis,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.599552Z

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 43971965-fdbb-4614-9411-a674dbb661da · outbound

This paper cites Language Models (Mostly) Know What They Know.

On the Robustness of LLMs' Internal Representation of Code Correctness Language Models (Mostly) Know What They Know

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.613962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55d5e476-13b2-402e-8cf5-c843dae8592e · outbound

This paper cites Sifting through the chaff: On utilizing execution feed- back for ranking the generated code candidates,.

On the Robustness of LLMs' Internal Representation of Code Correctness Sifting through the chaff: On utilizing execution feed- back for ranking the generated code candidates,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.580268Z

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 20abe70c-221c-4dbd-9983-ea0e058b2921 · outbound

This paper cites astroid: A common base representation of python source code,.

On the Robustness of LLMs' Internal Representation of Code Correctness astroid: A common base representation of python source code,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.556225Z

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 2f981508-16eb-4fd7-8584-a88651a0981b · outbound

This paper cites Are mutants a valid substitute for real faults in software testing?.

On the Robustness of LLMs' Internal Representation of Code Correctness Are mutants a valid substitute for real faults in software testing?

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.534463Z

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 f528ce79-a430-4fb0-ac23-0ad4d0db8031 · outbound

This paper cites Qwen2.5-Coder Technical Report.

On the Robustness of LLMs' Internal Representation of Code Correctness Qwen2.5-Coder Technical Report

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.634934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984e61b7-771f-46f0-bc32-0b30099aa377 · outbound

This paper cites Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection,.

On the Robustness of LLMs' Internal Representation of Code Correctness Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.508624Z

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 3a0aa7bc-35bf-49a6-9bdc-9a6ab97dd86a · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances,.

On the Robustness of LLMs' Internal Representation of Code Correctness Probing classifiers: Promises, shortcomings, and advances,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.483479Z

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 1b5ee281-1079-4a65-9025-3e0d51655520 · outbound

This paper cites Designing and interpreting probes with control tasks,.

On the Robustness of LLMs' Internal Representation of Code Correctness Designing and interpreting probes with control tasks,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.457140Z

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 866dd0fd-62fe-44eb-9d9d-72a05f3bdee6 · outbound

This paper cites Probingtheprobing paradigm: Does probing accuracy entail task relevance?.

On the Robustness of LLMs' Internal Representation of Code Correctness Probingtheprobing paradigm: Does probing accuracy entail task relevance?

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.437575Z

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 956918f9-deee-45ce-9b85-6fce21efb410 · outbound

This paper cites Amnesic probing: Behavioral explanation with amnesic counterfactuals,.

On the Robustness of LLMs' Internal Representation of Code Correctness Amnesic probing: Behavioral explanation with amnesic counterfactuals,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.420608Z

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 a3fc7e49-cf0b-4259-9e35-fa3a61a3e823 · outbound

This paper cites Probing classifiers are unreliable for concept removal and detection,.

On the Robustness of LLMs' Internal Representation of Code Correctness Probing classifiers are unreliable for concept removal and detection,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.393262Z

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 49a90a7e-46d7-432e-ae7a-57799b7e2ee0 · outbound

This paper cites Semantic bug seeding: A learning- based approach for creating realistic bugs,.

On the Robustness of LLMs' Internal Representation of Code Correctness Semantic bug seeding: A learning- based approach for creating realistic bugs,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.368419Z

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 c2a10e7b-199b-453c-844e-3db071438fb9 · outbound

This paper cites Learningrealisticmutations:Bug creation for neural bug detectors,.

On the Robustness of LLMs' Internal Representation of Code Correctness Learningrealisticmutations:Bug creation for neural bug detectors,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.346430Z

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 e1cf6848-5e56-42e2-8d63-b78a11d1df34 · outbound

This paper cites On distribution shift in learning-based bug detectors,.

On the Robustness of LLMs' Internal Representation of Code Correctness On distribution shift in learning-based bug detectors,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.309513Z

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 f4d00e17-e670-4c54-b3c7-4069bbd6b41d · outbound

This paper cites Large language models of code fail at completing code with potential bugs,.

On the Robustness of LLMs' Internal Representation of Code Correctness Large language models of code fail at completing code with potential bugs,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.267087Z

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 c170a50a-94a1-4359-8d7d-2097cd0429b2 · outbound

This paper cites On the universal truthfulness hyperplane inside LLMs,.

On the Robustness of LLMs' Internal Representation of Code Correctness On the universal truthfulness hyperplane inside LLMs,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.209872Z

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 27d87201-f698-42ec-b0e1-b566be2bdec8 · outbound

This paper cites Probing the geometry of truth: Consistency and generalization of truth directions in LLMs across logical transformations and question answering tasks,.

On the Robustness of LLMs' Internal Representation of Code Correctness Probing the geometry of truth: Consistency and generalization of truth directions in LLMs across logical transformations and question answering tasks,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.181399Z

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 7e286f9b-bd6c-4a1e-b83c-affe119ff2b7 · outbound

This paper cites The truth- fulness spectrum hypothesis,.

On the Robustness of LLMs' Internal Representation of Code Correctness The truth- fulness spectrum hypothesis,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.710684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e1ab20-b429-4726-9e1d-2b8936af9daa · outbound

This paper cites Correctness assessment of code generated by large language models using internal representations,.

On the Robustness of LLMs' Internal Representation of Code Correctness Correctness assessment of code generated by large language models using internal representations,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.158848Z

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 04b114ee-6da1-4788-8b3f-b491e1c509b9 · outbound

This paper cites LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations.

On the Robustness of LLMs' Internal Representation of Code Correctness LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.720442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa053f60-75e7-4c9b-bf44-6b01ead5317f · outbound

This paper cites Risk assess- ment framework for code LLMs via leveraging internal states,.

On the Robustness of LLMs' Internal Representation of Code Correctness Risk assess- ment framework for code LLMs via leveraging internal states,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.134448Z

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 e87dedce-ebf2-449e-947e-1bf07837bfb8 · outbound

This paper cites Localized calibrated uncertainty in code language models,.

On the Robustness of LLMs' Internal Representation of Code Correctness Localized calibrated uncertainty in code language models,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.731169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a283e3-e804-485b-b22f-0e0d1d3b3185 · outbound

This paper cites Mechanistic interpretability of code correctness in llms via sparse autoencoders,.

On the Robustness of LLMs' Internal Representation of Code Correctness Mechanistic interpretability of code correctness in llms via sparse autoencoders,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.736628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78d22ae2-ec23-4f3c-b2d8-e9ad0c32b590 · outbound

This paper cites Code- Circuit: Toward inferring LLM-generated code correctness via attribution graphs,.

On the Robustness of LLMs' Internal Representation of Code Correctness Code- Circuit: Toward inferring LLM-generated code correctness via attribution graphs,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.741684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ca37055-02f3-42b8-8c18-d758295ca45e · outbound

This paper cites Emergentrepresentationsofprogramse- manticsinlanguagemodelstrainedonprograms,.

On the Robustness of LLMs' Internal Representation of Code Correctness Emergentrepresentationsofprogramse- manticsinlanguagemodelstrainedonprograms,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.108509Z

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 6595ae70-6712-4d79-9955-54747d398513 · outbound

This paper cites Large language models for code: Security hardening and adversarial testing,.

On the Robustness of LLMs' Internal Representation of Code Correctness Large language models for code: Security hardening and adversarial testing,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.082713Z

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 4787b928-da74-40c0-8b65-ba750ea9d413 · outbound

This paper cites A Mixture of Linear Corrections Generates Secure Code.

On the Robustness of LLMs' Internal Representation of Code Correctness A Mixture of Linear Corrections Generates Secure Code

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-08-12T00:15:28.059625Z

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 91bdffa1-6118-4ea0-be7b-7aab2a813383 · outbound

This paper cites Steering large language models for vulnerability detection,.

On the Robustness of LLMs' Internal Representation of Code Correctness Steering large language models for vulnerability detection,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.063678Z

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 edf809b3-65eb-45f6-8e16-3ebf8a04af48 · outbound

This paper cites Are Sparse Autoencoders Useful for Java Function Bug Detection?.

On the Robustness of LLMs' Internal Representation of Code Correctness Are Sparse Autoencoders Useful for Java Function Bug Detection?

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.770578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 344778ce-3ac8-441f-9c03-a599cab63584 · outbound

This paper cites Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification.

On the Robustness of LLMs' Internal Representation of Code Correctness Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.776270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 313d14a4-4f59-4cc0-ae99-8c5a7c4ceba2 · outbound

This paper cites No answer needed: Predicting llm answer accuracy from question-only linear probes,.

On the Robustness of LLMs' Internal Representation of Code Correctness No answer needed: Predicting llm answer accuracy from question-only linear probes,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.783096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f40d70a3-dee2-49ce-982f-779c15591e09 · outbound

This paper cites The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models.

On the Robustness of LLMs' Internal Representation of Code Correctness The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.787692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e204c350-10ab-4e78-952a-f3bdaafc945f · outbound

This paper cites ReCode: Robustness evaluation of code generation models,.

On the Robustness of LLMs' Internal Representation of Code Correctness ReCode: Robustness evaluation of code generation models,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.046534Z

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 4fca3363-7114-4e61-9223-9b1fec745fc3 · outbound

This paper cites Semantic robustness of models of source code,.

On the Robustness of LLMs' Internal Representation of Code Correctness Semantic robustness of models of source code,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T00:15:27.798858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 685770ba-b533-4edc-8bc9-14f6fac4d64e · outbound

This paper cites Contrastive code representation learning,.

On the Robustness of LLMs' Internal Representation of Code Correctness Contrastive code representation learning,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:29.019004Z

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 3768ae7c-8ebf-4c5a-bc02-f04928fba6f4 · outbound

This paper cites An automated methodol- ogy for generating labeled datasets of semantic errors in code,.

On the Robustness of LLMs' Internal Representation of Code Correctness An automated methodol- ogy for generating labeled datasets of semantic errors in code,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:15:28.993340Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers